diff --git "a/Generation/meta/val/origin_format/full_single_multi_contact_obj_traj_qa.json" "b/Generation/meta/val/origin_format/full_single_multi_contact_obj_traj_qa.json" new file mode 100644--- /dev/null +++ "b/Generation/meta/val/origin_format/full_single_multi_contact_obj_traj_qa.json" @@ -0,0 +1,42002 @@ +[ + { + "id": "75136_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the green object from one stove to the other', and now you are performing subtask 'move the green object from one stove to the other.'\nYou start from [93.0, 0.0]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[93.0, 0.0], [120.0, 34.0], [138.0, 79.0], [139.0, 123.0], [130.0, 118.0], [163.0, 118.0], [167.0, 125.0], [163.0, 141.0], [141.0, 116.0], [140.0, 122.0]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/75136_exterior_image_1_left#0.jpg", + "gt": "[[93.0, 0.0], [120.0, 34.0], [138.0, 79.0], [139.0, 123.0], [130.0, 118.0], [163.0, 118.0], [167.0, 125.0], [163.0, 141.0], [141.0, 116.0], [140.0, 122.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "84561_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the brown block in the plate', and now you are performing subtask 'put the brown block in the plate.'\nBegin at [200, 5] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[200, 5], [195, 28], [201, 26], [202, 31], [201, 77], [184, 99], [177, 96], [179, 120], [175, 105], [172, 106]]}" + } + ], + "images": "84561_exterior_image_2_left#0", + "gt": "[[200, 5], [195, 28], [201, 26], [202, 31], [201, 77], [184, 99], [177, 96], [179, 120], [175, 105], [172, 106]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0127_user_0010_scene_0001_cfg_0004_036422060909#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'plug in the power cord of the desk lamp, turn on the socket, and light up the desk lamp', and now you are performing subtask 'insert the power cable into the socket on the table, press the button on the socket to turn it on.'\nYour initial coordinate is [328, 135]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[328, 135], [312, 134], [309, 123], [342, 142], [288, 146], [293, 111], [319, 82], [337, 87], [337, 114], [337, 114]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg4_task_0127_user_0010_scene_0001_cfg_0004_036422060909#248.jpg", + "gt": "[[328, 135], [312, 134], [309, 123], [342, 142], [288, 146], [293, 111], [319, 82], [337, 87], [337, 114], [337, 114]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "79766_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'straighten the cable', and now you are performing subtask 'place the line on the tabletop.'\nStart at [235, 87]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[235, 87], [203, 74], [205, 82], [199, 82], [199, 91], [201, 88], [145, 74], [97, 81], [61, 98], [80, 57]]}" + } + ], + "images": "79766_exterior_image_1_left#305", + "gt": "[[235, 87], [203, 74], [205, 82], [199, 82], [199, 91], [201, 88], [145, 74], [97, 81], [61, 98], [80, 57]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0044_user_0010_scene_0002_cfg_0005_104122061850#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up a bag of things', and now you are performing subtask 'pick up a bag of things.'\nWith start location [311, 50], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[311, 50], [328, 81], [352, 94], [356, 128], [375, 157], [374, 171], [372, 144], [353, 95], [352, 79], [333, 59]]}" + } + ], + "images": "RH20T_cfg5_task_0044_user_0010_scene_0002_cfg_0005_104122061850#0", + "gt": "[[311, 50], [328, 81], [352, 94], [356, 128], [375, 157], [374, 171], [372, 144], [353, 95], [352, 79], [333, 59]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "37061_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the object from the cup and put it on the table', and now you are performing subtask 'remove the object from the cup and put it on the table.'\nYour initial coordinate is [318, 30]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[318, 30], [195, 21], [183, 52], [190, 51], [209, 16], [231, 17], [260, 33], [266, 51], [252, 72], [254, 47]]}" + } + ], + "images": "37061_exterior_image_1_left#0", + "gt": "[[318, 30], [195, 21], [183, 52], [190, 51], [209, 16], [231, 17], [260, 33], [266, 51], [252, 72], [254, 47]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0037_user_0020_scene_0004_cfg_0006_104122060811#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'pick up the block on the surface, transfer the block from the surface to the other block, place the block on the other block, pick up the block on the surface.'\nYour starting position is [345, 129]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[345, 129], [340, 143], [345, 130], [351, 129], [358, 138], [363, 154], [367, 139], [365, 123], [365, 126], [372, 129]]}" + } + ], + "images": "RH20T_cfg6_task_0037_user_0020_scene_0004_cfg_0006_104122060811#737", + "gt": "[[345, 129], [340, 143], [345, 130], [351, 129], [358, 138], [363, 154], [367, 139], [365, 123], [365, 126], [372, 129]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "66422_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'place the orange block on top of the green block', and now you are performing subtask 'place the orange block on top of the green block.'\nYou begin at [66, 90]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[66, 90], [86, 100], [89, 109], [91, 126], [107, 102], [110, 103], [113, 109], [116, 111], [115, 112], [115, 108]]}" + } + ], + "images": "66422_exterior_image_2_left#0", + "gt": "[[66, 90], [86, 100], [89, 109], [91, 126], [107, 102], [110, 103], [113, 109], [116, 111], [115, 112], [115, 108]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0061_user_0020_scene_0001_cfg_0007_104122061602#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the lid of the gift box on the table, then take everything out of the gift box and place it all on the table', and now you are performing subtask 'pick up the lid from the gift box, transfer the lid from the gift box to the tabletop, place the lid on the tabletop.'\nBegin at [448, 116] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[448, 116], [456, 115], [456, 131], [438, 132], [452, 133], [453, 141], [444, 99], [400, 76], [387, 77], [395, 109]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg7_task_0061_user_0020_scene_0001_cfg_0007_104122061602#0.jpg", + "gt": "[[448, 116], [456, 115], [456, 131], [438, 132], [452, 133], [453, 141], [444, 99], [400, 76], [387, 77], [395, 109]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "19695_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn the faucet to the right', and now you are performing subtask 'turn the faucet to the right.'\nYour starting position is [130.5, 77.0]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[130.5, 77.0], [142.5, 74.0], [161.5, 74.0], [158.5, 77.0], [192.5, 71.0], [203.5, 81.0], [247.5, 95.0], [274.5, 89.0], [234.5, 97.0], [197.5, 83.0]]}" + } + ], + "images": "19695_exterior_image_1_left#0", + "gt": "[[130.5, 77.0], [142.5, 74.0], [161.5, 74.0], [158.5, 77.0], [192.5, 71.0], [203.5, 81.0], [247.5, 95.0], [274.5, 89.0], [234.5, 97.0], [197.5, 83.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "72121_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the pen on the table', and now you are performing subtask 'put the pen on the table.'\nThe trajectory starts at [191, 95]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[191, 95], [218, 95], [220, 87], [244, 90], [243, 98], [234, 88], [245, 82], [267, 111], [258, 125], [236, 98]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/72121_exterior_image_1_left#0.jpg", + "gt": "[[191, 95], [218, 95], [220, 87], [244, 90], [243, 98], [234, 88], [245, 82], [267, 111], [258, 125], [236, 98]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0004_user_0014_scene_0004_cfg_0001_038522062547#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the small block on the left and move it to the right', and now you are performing subtask 'pick up the small block on the left and move it to the right.'\nYou begin at [406, 133]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[406, 133], [450, 135], [450, 145], [415, 182], [416, 118], [426, 140], [436, 83], [420, 42], [412, 71], [407, 16]]}" + } + ], + "images": "RH20T_cfg1_task_0004_user_0014_scene_0004_cfg_0001_038522062547#0", + "gt": "[[406, 133], [450, 135], [450, 145], [415, 182], [416, 118], [426, 140], [436, 83], [420, 42], [412, 71], [407, 16]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "40127_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'the charger on the folding table', and now you are performing subtask 'fold the charger on the table.'\nStarting at [202, 76], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[202, 76], [175, 62], [162, 83], [147, 79], [187, 73], [211, 90], [208, 100], [198, 78], [210, 66], [210, 66]]}" + } + ], + "images": "40127_exterior_image_1_left#158", + "gt": "[[202, 76], [175, 62], [162, 83], [147, 79], [187, 73], [211, 90], [208, 100], [198, 78], [210, 66], [210, 66]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0069_user_0015_scene_0001_cfg_0004_104122062823#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'assemble one piece of a puzzle', and now you are performing subtask 'pick up the puzzle piece from the table.'\nFrom start point [392, 80], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[392, 80], [403, 80], [405, 77], [403, 75], [403, 79], [400, 78], [398, 73], [388, 68], [386, 70], [388, 72]]}" + } + ], + "images": "RH20T_cfg4_task_0069_user_0015_scene_0001_cfg_0004_104122062823#423", + "gt": "[[392, 80], [403, 80], [405, 77], [403, 75], [403, 79], [400, 78], [398, 73], [388, 68], [386, 70], [388, 72]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "68845_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the marker out of the pot and put it on the table', and now you are performing subtask 'take the marker out of the pot and put it on the table.'\nStart at [189, 9]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[189, 9], [169, 26], [147, 66], [144, 46], [147, 25], [151, 22], [154, 25], [153, 62], [153, 45], [150, 46]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/68845_exterior_image_2_left#0.jpg", + "gt": "[[189, 9], [169, 26], [147, 66], [144, 46], [147, 25], [151, 22], [154, 25], [153, 62], [153, 45], [150, 46]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "51385_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'straighten the cloth', and now you are performing subtask 'pick up the cloth on the table.'\nYour starting position is [304, 13]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[304, 13], [203, 50], [185, 78], [159, 85], [165, 99], [159, 68], [145, 51], [181, 90], [182, 82], [171, 86]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/51385_exterior_image_1_left#0.jpg", + "gt": "[[304, 13], [203, 50], [185, 78], [159, 85], [165, 99], [159, 68], [145, 51], [181, 90], [182, 82], [171, 86]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0037_user_0007_scene_0008_cfg_0005_104122061850#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'place the block on the other blocks, pick up the block on the plane, transfer the block from the plane to the other blocks, place the block on the other blocks.'\nStarting at [327, 64], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[327, 64], [349, 72], [370, 136], [405, 188], [400, 186], [384, 122], [332, 56], [318, 53], [320, 40], [323, 44]]}" + } + ], + "images": "RH20T_cfg5_task_0037_user_0007_scene_0008_cfg_0005_104122061850#580", + "gt": "[[327, 64], [349, 72], [370, 136], [405, 188], [400, 186], [384, 122], [332, 56], [318, 53], [320, 40], [323, 44]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "78514_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick the gray object and move it to the left on the table', and now you are performing subtask 'pick the gray object and move it to the left on the table.'\nFrom start point [238, 1], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[238, 1], [218, 31], [207, 70], [203, 53], [193, 55], [190, 70], [198, 81], [193, 74], [190, 96], [209, 67]]}" + } + ], + "images": "78514_exterior_image_2_left#0", + "gt": "[[238, 1], [218, 31], [207, 70], [203, 53], [193, 55], [190, 70], [198, 81], [193, 74], [190, 96], [209, 67]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "51951_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the black marker in the pot', and now you are performing subtask 'put the black marker in the pot.'\nYou start from [225, 0]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[225, 0], [172, 70], [170, 89], [162, 92], [158, 89], [153, 56], [173, 50], [186, 57], [185, 67], [180, 59]]}" + } + ], + "images": "51951_exterior_image_2_left#0", + "gt": "[[225, 0], [172, 70], [170, 89], [162, 92], [158, 89], [153, 56], [173, 50], [186, 57], [185, 67], [180, 59]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0003_user_0014_scene_0010_cfg_0006_104122060811#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press three buttons from left to right in sequence', and now you are performing subtask 'press the green button in the middle, press the yellow button at the top.'\nYour initial coordinate is [388, 117]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[388, 117], [382, 114], [375, 114], [368, 117], [367, 119], [361, 121], [360, 123], [361, 123], [363, 117], [365, 116]]}" + } + ], + "images": "RH20T_cfg6_task_0003_user_0014_scene_0010_cfg_0006_104122060811#167", + "gt": "[[388, 117], [382, 114], [375, 114], [368, 117], [367, 119], [361, 121], [360, 123], [361, 123], [363, 117], [365, 116]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "44145_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the purple object in the bowl', and now you are performing subtask 'put the purple object in the bowl.'\nFrom start point [111, 98], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[111, 98], [163, 107], [176, 126], [174, 140], [193, 110], [221, 92], [234, 94], [227, 115], [238, 126], [249, 96]]}" + } + ], + "images": "44145_exterior_image_2_left#0", + "gt": "[[111, 98], [163, 107], [176, 126], [174, 140], [193, 110], [221, 92], [234, 94], [227, 115], [238, 126], [249, 96]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0066_user_0014_scene_0005_cfg_0007_104122064161#TrajectoryPrediction_Task#8", + "task": "TrajectoryPrediction_Task", + "p_index": 8, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with large Megabloks for the nth time with n blocks', and now you are performing subtask 'place the block on the other blocks, pick up the block on the flat surface, transfer the block from the flat surface to the other blocks, place the block on the other blocks.'\nYour starting position is [354, 160]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[354, 160], [397, 167], [409, 157], [420, 172], [414, 153], [387, 136], [359, 145], [345, 163], [360, 158], [363, 130]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg7_task_0066_user_0014_scene_0005_cfg_0007_104122064161#523.jpg", + "gt": "[[354, 160], [397, 167], [409, 157], [420, 172], [414, 153], [387, 136], [359, 145], [345, 163], [360, 158], [363, 130]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0065_user_0015_scene_0001_cfg_0001_038522062547#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with small Lego blocks for the nth time with n blocks', and now you are performing subtask 'pick up the black block from the table, transfer the black block from the table to above the base plate, press the black block onto the base plate.'\nFrom start point [406, 134], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[406, 134], [424, 151], [414, 126], [425, 55], [420, 41], [387, 31], [391, 24], [391, 42], [369, 65], [379, 122]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0065_user_0015_scene_0001_cfg_0001_038522062547#0.jpg", + "gt": "[[406, 134], [424, 151], [414, 126], [425, 55], [420, 41], [387, 31], [391, 24], [391, 42], [369, 65], [379, 122]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "78597_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'fold the towel', and now you are performing subtask 'fold the towel on the countertop.'\nStart at [179, 110]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[179, 110], [199, 102], [195, 101], [195, 106], [191, 100], [191, 105], [199, 96], [186, 83], [175, 85], [182, 92]]}" + } + ], + "images": "78597_exterior_image_1_left#162", + "gt": "[[179, 110], [199, 102], [195, 101], [195, 106], [191, 100], [191, 105], [199, 96], [186, 83], [175, 85], [182, 92]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "40176_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the green-white mug to the right', and now you are performing subtask 'move the green-white mug to the right.'\nStarting at [128, 58], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[128, 58], [167, 70], [170, 74], [176, 98], [185, 98], [201, 103], [202, 106], [198, 109], [190, 98], [183, 71]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/40176_exterior_image_1_left#0.jpg", + "gt": "[[128, 58], [167, 70], [170, 74], [176, 98], [185, 98], [201, 103], [202, 106], [198, 109], [190, 98], [183, 71]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "66631_exterior_image_1_left#TrajectoryPrediction_Task#8", + "task": "TrajectoryPrediction_Task", + "p_index": 8, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'use the towel to wipe the table', and now you are performing subtask 'wipe the table.'\nYou start from [238, 93]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[238, 93], [231, 88], [236, 111], [252, 136], [213, 86], [199, 108], [199, 132], [210, 139], [227, 94], [290, 16]]}" + } + ], + "images": "66631_exterior_image_1_left#415", + "gt": "[[238, 93], [231, 88], [236, 111], [252, 136], [213, 86], [199, 108], [199, 132], [210, 139], [227, 94], [290, 16]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "13859_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the contents in the silver pot into the bowl', and now you are performing subtask 'put the contents in the silver pot into the bowl.'\nYour starting position is [186, 11]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[186, 11], [198, 57], [188, 81], [248, 29], [231, 43], [229, 9], [185, 60], [190, 79], [204, 53], [188, 13]]}" + } + ], + "images": "13859_exterior_image_1_left#0", + "gt": "[[186, 11], [198, 57], [188, 81], [248, 29], [231, 43], [229, 9], [185, 60], [190, 79], [204, 53], [188, 13]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0011_user_0007_scene_0004_cfg_0005_104122063678#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'water the plant', and now you are performing subtask 'water the plant.'\nYou start from [213, 120]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[213, 120], [218, 68], [237, 73], [247, 104], [244, 135], [239, 83], [195, 1], [134, 0], [210, 0], [207, 44]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0011_user_0007_scene_0004_cfg_0005_104122063678#0.jpg", + "gt": "[[213, 120], [218, 68], [237, 73], [247, 104], [244, 135], [239, 83], [195, 1], [134, 0], [210, 0], [207, 44]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "25515_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn off the big switch on the adapter', and now you are performing subtask 'press the big switch on the adapter.'\nStart at [143, 59]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[143, 59], [144, 76], [139, 87], [135, 87], [121, 117], [116, 121], [117, 125], [107, 134], [110, 133], [121, 112]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/25515_exterior_image_2_left#0.jpg", + "gt": "[[143, 59], [144, 76], [139, 87], [135, 87], [121, 117], [116, 121], [117, 125], [107, 134], [110, 133], [121, 112]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "61124_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the plastic broccoli in the orange bowl', and now you are performing subtask 'put the plastic broccoli in the orange bowl.'\nStarting at [158, 1], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[158, 1], [171, 28], [174, 74], [183, 88], [177, 102], [187, 106], [199, 82], [187, 116], [200, 98], [211, 93]]}" + } + ], + "images": "61124_exterior_image_1_left#0", + "gt": "[[158, 1], [171, 28], [174, 74], [183, 88], [177, 102], [187, 106], [199, 82], [187, 116], [200, 98], [211, 93]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0003_user_0014_scene_0010_cfg_0006_104122061018#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press three buttons from left to right in sequence', and now you are performing subtask 'press the red button at the bottom.'\nWith start location [367, 28], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[367, 28], [335, 27], [308, 34], [285, 45], [280, 52], [269, 49], [263, 51], [253, 58], [259, 59], [263, 56]]}" + } + ], + "images": "RH20T_cfg6_task_0003_user_0014_scene_0010_cfg_0006_104122061018#0", + "gt": "[[367, 28], [335, 27], [308, 34], [285, 45], [280, 52], [269, 49], [263, 51], [253, 58], [259, 59], [263, 56]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0006_user_0014_scene_0005_cfg_0006_104122064161#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'use the gripper to push the small block from left to right', and now you are performing subtask 'use the gripper to push the small block from left to right.'\nThe trajectory starts at [338, 110]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[338, 110], [363, 151], [375, 236], [366, 235], [365, 199], [373, 185], [372, 158], [383, 139], [379, 129], [368, 137]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg6_task_0006_user_0014_scene_0005_cfg_0006_104122064161#0.jpg", + "gt": "[[338, 110], [363, 151], [375, 236], [366, 235], [365, 199], [373, 185], [372, 158], [383, 139], [379, 129], [368, 137]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "31525_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'wipe the table with the yellow towel', and now you are performing subtask 'wipe the table with the yellow towel.'\nWith start location [175, 2], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[175, 2], [223, 68], [199, 77], [199, 99], [230, 102], [202, 83], [138, 74], [133, 86], [223, 111], [212, 75]]}" + } + ], + "images": "31525_exterior_image_1_left#0", + "gt": "[[175, 2], [223, 68], [199, 77], [199, 99], [230, 102], [202, 83], [138, 74], [133, 86], [223, 111], [212, 75]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0108_user_0015_scene_0009_cfg_0004_104122062823#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'sharpen the pencil with a pencil sharpener', and now you are performing subtask 'twist the handle of the pencil sharpener clockwise.'\nYour initial coordinate is [332, 113]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[332, 113], [365, 147], [358, 157], [338, 157], [358, 154], [356, 167], [332, 166], [327, 133], [306, 99], [306, 99]]}" + } + ], + "images": "RH20T_cfg4_task_0108_user_0015_scene_0009_cfg_0004_104122062823#191", + "gt": "[[332, 113], [365, 147], [358, 157], [338, 157], [358, 154], [356, 167], [332, 166], [327, 133], [306, 99], [306, 99]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "91638_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'fold the shirt', and now you are performing subtask 'fold the shirt's other sleeve.'\nBegin at [209, 51] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[209, 51], [219, 55], [214, 56], [220, 70], [246, 103], [209, 77], [189, 40], [196, 6], [214, 2], [222, 19]]}" + } + ], + "images": "91638_exterior_image_1_left#161", + "gt": "[[209, 51], [219, 55], [214, 56], [220, 70], [246, 103], [209, 77], [189, 40], [196, 6], [214, 2], [222, 19]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0012_user_0010_scene_0005_cfg_0004_104122062823#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'push the soccer ball into the goal', and now you are performing subtask 'push the soccer ball toward the goal.'\nStart at [265, 59]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[265, 59], [271, 75], [263, 89], [241, 93], [245, 86], [237, 80], [221, 86], [218, 90], [225, 104], [220, 111]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg4_task_0012_user_0010_scene_0005_cfg_0004_104122062823#187.jpg", + "gt": "[[265, 59], [271, 75], [263, 89], [241, 93], [245, 86], [237, 80], [221, 86], [218, 90], [225, 104], [220, 111]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "48959_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the pineapple plush toy in the black pot, and the pear in the box', and now you are performing subtask 'pick up the pear from the table.'\nYou begin at [197.5, 17.0]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[197.5, 17.0], [203.5, 7.0], [221.5, 0.0], [212.5, 5.0], [220.5, 23.0], [211.5, 7.0], [214.5, 10.0], [210.5, 9.0], [201.5, 31.0], [210.5, 59.0]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/48959_exterior_image_1_left#103.jpg", + "gt": "[[197.5, 17.0], [203.5, 7.0], [221.5, 0.0], [212.5, 5.0], [220.5, 23.0], [211.5, 7.0], [214.5, 10.0], [210.5, 9.0], [201.5, 31.0], [210.5, 59.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "1032_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'fold the peach towel into a triangle thrice', and now you are performing subtask 'fold the peach towel into a triangle.'\nFrom start point [150, 103], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[150, 103], [171, 95], [185, 98], [195, 105], [206, 126], [200, 137], [207, 130], [186, 98], [168, 82], [156, 79]]}" + } + ], + "images": "1032_exterior_image_1_left#156", + "gt": "[[150, 103], [171, 95], [185, 98], [195, 105], [206, 126], [200, 137], [207, 130], [186, 98], [168, 82], [156, 79]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "8995_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pour the contents in the green bowl onto the white plate on the left', and now you are performing subtask 'pour the contents in the green bowl onto the white plate on the left.'\nStarting at [214.5, 34.0], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[214.5, 34.0], [129.5, 71.0], [109.5, 91.0], [116.5, 100.0], [111.5, 80.0], [90.5, 86.0], [91.5, 64.0], [117.5, 62.0], [109.5, 100.0], [127.5, 66.0]]}" + } + ], + "images": "8995_exterior_image_1_left#0", + "gt": "[[214.5, 34.0], [129.5, 71.0], [109.5, 91.0], [116.5, 100.0], [111.5, 80.0], [90.5, 86.0], [91.5, 64.0], [117.5, 62.0], [109.5, 100.0], [127.5, 66.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "19769_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the yellow plate from the right side to the left side', and now you are performing subtask 'move the yellow plate from the right side to the left side.'\nYour initial coordinate is [226, 0]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[226, 0], [215, 11], [215, 38], [205, 53], [203, 68], [205, 49], [202, 47], [167, 64], [155, 82], [156, 67]]}" + } + ], + "images": "19769_exterior_image_2_left#0", + "gt": "[[226, 0], [215, 11], [215, 38], [205, 53], [203, 68], [205, 49], [202, 47], [167, 64], [155, 82], [156, 67]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg2_task_0034_user_0003_scene_0006_cfg_0002_104422070044#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the squares into a pyramid shape', and now you are performing subtask 'place the square on top of the existing square in the center, pick up the second square next to the first square, transfer the second square from the countertop to the left side of the first square, place the second square to the left of the first square.'\nYour initial coordinate is [388, 239]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[388, 239], [381, 214], [380, 225], [374, 217], [370, 220], [377, 227], [372, 223], [366, 229], [368, 238], [376, 230]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg2_task_0034_user_0003_scene_0006_cfg_0002_104422070044#107.jpg", + "gt": "[[388, 239], [381, 214], [380, 225], [374, 217], [370, 220], [377, 227], [372, 223], [366, 229], [368, 238], [376, 230]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "27099_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the white cloth on the black rod', and now you are performing subtask 'put the white cloth on the black rod.'\nYour initial coordinate is [171.0, 40.0]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[171.0, 40.0], [189.0, 103.0], [180.0, 100.0], [178.0, 124.0], [148.0, 27.0], [146.0, 46.0], [126.0, 85.0], [137.0, 100.0], [133.0, 111.0], [152.0, 106.0]]}" + } + ], + "images": "27099_exterior_image_1_left#0", + "gt": "[[171.0, 40.0], [189.0, 103.0], [180.0, 100.0], [178.0, 124.0], [148.0, 27.0], [146.0, 46.0], [126.0, 85.0], [137.0, 100.0], [133.0, 111.0], [152.0, 106.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0003_user_0008_scene_0002_cfg_0001_039422060546#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press three buttons from left to right in sequence', and now you are performing subtask 'press the first button on the desk, press the second button on the desk.'\nWith start location [260, 123], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[260, 123], [240, 147], [222, 244], [211, 266], [219, 286], [205, 303], [213, 310], [208, 299], [213, 306], [235, 249]]}" + } + ], + "images": "RH20T_cfg1_task_0003_user_0008_scene_0002_cfg_0001_039422060546#0", + "gt": "[[260, 123], [240, 147], [222, 244], [211, 266], [219, 286], [205, 303], [213, 310], [208, 299], [213, 306], [235, 249]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "38503_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the cloth off the glass then put it back', and now you are performing subtask 'transfer the cloth from the table back to the glass.'\nThe trajectory starts at [193, 93]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[193, 93], [189, 97], [192, 94], [193, 107], [190, 128], [181, 111], [159, 40], [160, 28], [168, 43], [171, 39]]}" + } + ], + "images": "38503_exterior_image_1_left#101", + "gt": "[[193, 93], [189, 97], [192, 94], [193, 107], [190, 128], [181, 111], [159, 40], [160, 28], [168, 43], [171, 39]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "13954_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the black pen in the bowl', and now you are performing subtask 'put the black pen in the bowl.'\nFrom start point [169.0, 2.5], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[169.0, 2.5], [180.0, 35.5], [180.0, 47.5], [178.0, 47.5], [179.0, 68.5], [177.0, 43.5], [170.0, 33.5], [167.0, 32.5], [165.0, 36.5], [163.0, 34.5]]}" + } + ], + "images": "13954_exterior_image_1_left#0", + "gt": "[[169.0, 2.5], [180.0, 35.5], [180.0, 47.5], [178.0, 47.5], [179.0, 68.5], [177.0, 43.5], [170.0, 33.5], [167.0, 32.5], [165.0, 36.5], [163.0, 34.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "77449_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the washing machine's detergent compartment', and now you are performing subtask 'open the washing machine's detergent compartment.'\nWith start location [171, 60], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[171, 60], [183, 63], [186, 47], [174, 106], [169, 114], [165, 104], [173, 103], [175, 113], [186, 109], [174, 84]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/77449_exterior_image_2_left#0.jpg", + "gt": "[[171, 60], [183, 63], [186, 47], [174, 106], [169, 114], [165, 104], [173, 103], [175, 113], [186, 109], [174, 84]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "63709_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the blue marker from the blue bowl and place it on the table', and now you are performing subtask 'remove the blue marker from the blue bowl and place it on the table.'\nYour starting position is [177, 113]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[177, 113], [158, 113], [162, 115], [158, 130], [160, 127], [157, 122], [163, 106], [169, 101], [181, 101], [173, 93]]}" + } + ], + "images": "63709_exterior_image_1_left#0", + "gt": "[[177, 113], [158, 113], [162, 115], [158, 130], [160, 127], [157, 122], [163, 106], [169, 101], [181, 101], [173, 93]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "76361_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the lid on the counter', and now you are performing subtask 'put the lid on the counter.'\nYou begin at [254, 136]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[254, 136], [183, 97], [162, 109], [192, 106], [225, 135], [240, 173], [240, 147], [250, 178], [250, 152], [211, 129]]}" + } + ], + "images": "76361_exterior_image_2_left#0", + "gt": "[[254, 136], [183, 97], [162, 109], [192, 106], [225, 135], [240, 173], [240, 147], [250, 178], [250, 152], [211, 129]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "20237_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stir the contents in the green bowl using a spatula', and now you are performing subtask 'stir the contents in the green bowl using a spatula.'\nStarting at [131, 86], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[131, 86], [166, 105], [161, 111], [159, 100], [166, 109], [162, 100], [173, 110], [167, 100], [182, 105], [156, 93]]}" + } + ], + "images": "20237_exterior_image_2_left#0", + "gt": "[[131, 86], [166, 105], [161, 111], [159, 100], [166, 109], [162, 100], [173, 110], [167, 100], [182, 105], [156, 93]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0066_user_0014_scene_0005_cfg_0007_104122064161#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with large Megabloks for the nth time with n blocks', and now you are performing subtask 'place the block on the block board, pick up the block on the flat surface, transfer the block from the flat surface to the other blocks, place the block on the other blocks.'\nFrom start point [366, 145], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[366, 145], [402, 166], [419, 190], [410, 173], [377, 160], [367, 168], [353, 162], [344, 185], [337, 177], [354, 160]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg7_task_0066_user_0014_scene_0005_cfg_0007_104122064161#394.jpg", + "gt": "[[366, 145], [402, 166], [419, 190], [410, 173], [377, 160], [367, 168], [353, 162], [344, 185], [337, 177], [354, 160]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "36160_exterior_image_2_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the cloth on the table', and now you are performing subtask 'unfold the cloth.'\nWith start location [202, 52], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[202, 52], [163, 62], [161, 67], [159, 83], [166, 90], [175, 70], [182, 64], [205, 61], [203, 52], [208, 33]]}" + } + ], + "images": "36160_exterior_image_2_left#150", + "gt": "[[202, 52], [163, 62], [161, 67], [159, 83], [166, 90], [175, 70], [182, 64], [205, 61], [203, 52], [208, 33]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "7347_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the marker from the right side of the table to the left side of the table', and now you are performing subtask 'move the marker from the right side of the table to the left side of the table.'\nYour starting position is [176, 2]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[176, 2], [171, 19], [180, 45], [175, 57], [164, 64], [173, 86], [164, 62], [159, 63], [160, 79], [148, 67]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/7347_exterior_image_2_left#0.jpg", + "gt": "[[176, 2], [171, 19], [180, 45], [175, 57], [164, 64], [173, 86], [164, 62], [159, 63], [160, 79], [148, 67]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "54529_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'fold the shirt', and now you are performing subtask 'fold the shirt.'\nYou begin at [78, 90]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[78, 90], [126, 95], [197, 134], [182, 129], [171, 154], [176, 141], [166, 121], [148, 122], [165, 128], [134, 139]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/54529_exterior_image_2_left#0.jpg", + "gt": "[[78, 90], [126, 95], [197, 134], [182, 129], [171, 154], [176, 141], [166, 121], [148, 122], [165, 128], [134, 139]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0073_user_0001_scene_0003_cfg_0001_035622060973#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the things in the drawer', and now you are performing subtask 'pick up the block on the drawer, transfer the block from above the drawer to inside the drawer, place the block in the drawer, push the drawer handle to close the drawer.'\nFrom start point [245, 130], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[245, 130], [239, 112], [253, 57], [234, 37], [251, 82], [258, 87], [259, 112], [262, 98], [278, 119], [278, 119]]}" + } + ], + "images": "RH20T_cfg1_task_0073_user_0001_scene_0003_cfg_0001_035622060973#0", + "gt": "[[245, 130], [239, 112], [253, 57], [234, 37], [251, 82], [258, 87], [259, 112], [262, 98], [278, 119], [278, 119]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "44219_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the pen out of the mug and put it on the table', and now you are performing subtask 'take the pen out of the mug and put it on the table.'\nBegin at [109.5, 1.0] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[109.5, 1.0], [82.5, 66.0], [85.5, 95.0], [77.5, 54.0], [72.5, 48.0], [53.5, 53.0], [37.5, 70.0], [36.5, 86.0], [45.5, 110.0], [39.5, 91.0]]}" + } + ], + "images": "44219_exterior_image_1_left#0", + "gt": "[[109.5, 1.0], [82.5, 66.0], [85.5, 95.0], [77.5, 54.0], [72.5, 48.0], [53.5, 53.0], [37.5, 70.0], [36.5, 86.0], [45.5, 110.0], [39.5, 91.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "1962_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the marker out of the box and place it on the table', and now you are performing subtask 'take the marker out of the box and place it on the table.'\nStarting at [136, 35], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[136, 35], [166, 47], [183, 100], [174, 119], [177, 130], [180, 125], [166, 110], [149, 116], [143, 129], [146, 101]]}" + } + ], + "images": "1962_exterior_image_2_left#0", + "gt": "[[136, 35], [166, 47], [183, 100], [174, 119], [177, 130], [180, 125], [166, 110], [149, 116], [143, 129], [146, 101]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "58731_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the object out of the bowl and place it on the table', and now you are performing subtask 'take the object out of the bowl and place it on the table.'\nYou begin at [151, 26]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[151, 26], [174, 14], [206, 19], [220, 33], [213, 62], [223, 39], [244, 32], [255, 45], [255, 56], [242, 68]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/58731_exterior_image_1_left#0.jpg", + "gt": "[[151, 26], [174, 14], [206, 19], [220, 33], [213, 62], [223, 39], [244, 32], [255, 45], [255, 56], [242, 68]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "33844_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the button atop the flask', and now you are performing subtask 'press the button atop the flask.'\nThe trajectory starts at [320.0, 112.0]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[320.0, 112.0], [275.0, 139.0], [270.0, 154.0], [287.0, 162.0], [278.0, 163.0], [273.0, 155.0], [280.0, 164.0], [275.0, 149.0], [292.0, 113.0], [292.0, 113.0]]}" + } + ], + "images": "33844_exterior_image_1_left#0", + "gt": "[[320.0, 112.0], [275.0, 139.0], [270.0, 154.0], [287.0, 162.0], [278.0, 163.0], [273.0, 155.0], [280.0, 164.0], [275.0, 149.0], [292.0, 113.0], [292.0, 113.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "21171_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the lid and close the pot', and now you are performing subtask 'pick up the lid and close the pot.'\nYou start from [131.5, 0.5]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[131.5, 0.5], [146.5, 46.5], [122.5, 83.5], [124.5, 57.5], [137.5, 57.5], [151.5, 65.5], [154.5, 80.5], [150.5, 84.5], [156.5, 80.5], [145.5, 70.5]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/21171_exterior_image_1_left#0.jpg", + "gt": "[[131.5, 0.5], [146.5, 46.5], [122.5, 83.5], [124.5, 57.5], [137.5, 57.5], [151.5, 65.5], [154.5, 80.5], [150.5, 84.5], [156.5, 80.5], [145.5, 70.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "27562_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'fold the towel then remove the object from the drawer', and now you are performing subtask 'fold the green towel on the table.'\nStart at [291, 3]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[291, 3], [265, 16], [241, 41], [226, 66], [227, 84], [216, 65], [204, 63], [187, 76], [187, 89], [189, 66]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/27562_exterior_image_2_left#0.jpg", + "gt": "[[291, 3], [265, 16], [241, 41], [226, 66], [227, 84], [216, 65], [204, 63], [187, 76], [187, 89], [189, 66]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "84608_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the lid on the pot', and now you are performing subtask 'put the lid on the pot.'\nStart at [30, 43]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[30, 43], [61, 39], [87, 75], [105, 75], [105, 102], [99, 68], [112, 73], [115, 86], [129, 86], [126, 100]]}" + } + ], + "images": "84608_exterior_image_1_left#0", + "gt": "[[30, 43], [61, 39], [87, 75], [105, 75], [105, 102], [99, 68], [112, 73], [115, 86], [129, 86], [126, 100]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0029_user_0014_scene_0005_cfg_0006_104122064161#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the drawer', and now you are performing subtask 'open the drawer.'\nYour initial coordinate is [338, 110]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[338, 110], [344, 107], [311, 138], [309, 162], [310, 136], [314, 124], [334, 96], [332, 90], [322, 84], [311, 89]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg6_task_0029_user_0014_scene_0005_cfg_0006_104122064161#0.jpg", + "gt": "[[338, 110], [344, 107], [311, 138], [309, 162], [310, 136], [314, 124], [334, 96], [332, 90], [322, 84], [311, 89]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0065_user_0015_scene_0001_cfg_0001_038522062547#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with small Lego blocks for the nth time with n blocks', and now you are performing subtask 'press the black block onto the base plate.'\nStart at [379, 122]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[379, 122], [381, 126], [381, 123], [372, 123], [377, 121], [374, 100], [379, 73], [381, 50], [379, 36], [381, 34]]}" + } + ], + "images": "RH20T_cfg1_task_0065_user_0015_scene_0001_cfg_0001_038522062547#466", + "gt": "[[379, 122], [381, 126], [381, 123], [372, 123], [377, 121], [374, 100], [379, 73], [381, 50], [379, 36], [381, 34]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0063_user_0020_scene_0008_cfg_0007_104122060811#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'use a shovel to scoop up an object', and now you are performing subtask 'use a shovel to scoop up an object.'\nStarting at [387, 130], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[387, 130], [320, 160], [344, 139], [359, 141], [345, 145], [372, 143], [353, 145], [346, 155], [368, 134], [387, 131]]}" + } + ], + "images": "RH20T_cfg7_task_0063_user_0020_scene_0008_cfg_0007_104122060811#0", + "gt": "[[387, 130], [320, 160], [344, 139], [359, 141], [345, 145], [372, 143], [353, 145], [346, 155], [368, 134], [387, 131]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0065_user_0010_scene_0005_cfg_0001_038522063145#TrajectoryPrediction_Task#18", + "task": "TrajectoryPrediction_Task", + "p_index": 18, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with small Lego blocks for the nth time with n blocks', and now you are performing subtask 'pick up the yellow small Lego block from the desktop, transfer the yellow small Lego block from the desktop to the red small Lego block, place the yellow small Lego block on the red small Lego block.'\nYou begin at [432, 104]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[432, 104], [427, 118], [437, 113], [443, 141], [456, 150], [459, 145], [451, 150], [451, 160], [454, 142], [439, 124]]}" + } + ], + "images": "RH20T_cfg1_task_0065_user_0010_scene_0005_cfg_0001_038522063145#1681", + "gt": "[[432, 104], [427, 118], [437, 113], [443, 141], [456, 150], [459, 145], [451, 150], [451, 160], [454, 142], [439, 124]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "18085_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'folded shirt', and now you are performing subtask 'fold the shirt on the table.'\nWith start location [107, 149], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[107, 149], [110, 110], [118, 106], [122, 110], [126, 124], [123, 116], [114, 109], [110, 125], [113, 128], [113, 134]]}" + } + ], + "images": "18085_exterior_image_1_left#233", + "gt": "[[107, 149], [110, 110], [118, 106], [122, 110], [126, 124], [123, 116], [114, 109], [110, 125], [113, 128], [113, 134]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0123_user_0010_scene_0004_cfg_0005_104122063678#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the knife on the knife rack', and now you are performing subtask 'pick up the knife on the table, transfer the knife from the table to the knife rack, place the knife on the knife rack.'\nYour initial coordinate is [212, 120]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[212, 120], [197, 161], [220, 162], [230, 176], [221, 186], [260, 160], [264, 190], [253, 206], [259, 208], [260, 187]]}" + } + ], + "images": "RH20T_cfg5_task_0123_user_0010_scene_0004_cfg_0005_104122063678#0", + "gt": "[[212, 120], [197, 161], [220, 162], [230, 176], [221, 186], [260, 160], [264, 190], [253, 206], [259, 208], [260, 187]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "7219_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close the top drawer of the cabinet at the right', and now you are performing subtask 'close the top drawer of the cabinet at the right.'\nThe trajectory starts at [233, 178]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[233, 178], [226, 159], [231, 137], [231, 126], [228, 115], [233, 109], [233, 107], [227, 104], [223, 105], [215, 100]]}" + } + ], + "images": "7219_exterior_image_1_left#0", + "gt": "[[233, 178], [226, 159], [231, 137], [231, 126], [228, 115], [233, 109], [233, 107], [227, 104], [223, 105], [215, 100]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "59697_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the objects from the orange bowl to the black pot, then cover the black pot with the glass lid', and now you are performing subtask 'place the glass lid on the black pot.'\nStart at [170, 49]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[170, 49], [198, 72], [200, 89], [187, 96], [208, 74], [204, 44], [187, 14], [174, 46], [160, 49], [170, 22]]}" + } + ], + "images": "59697_exterior_image_1_left#333", + "gt": "[[170, 49], [198, 72], [200, 89], [187, 96], [208, 74], [204, 44], [187, 14], [174, 46], [160, 49], [170, 22]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0065_user_0010_scene_0005_cfg_0001_038522062547#TrajectoryPrediction_Task#8", + "task": "TrajectoryPrediction_Task", + "p_index": 8, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with small Lego blocks for the nth time with n blocks', and now you are performing subtask 'press the red small Lego block, pick up the yellow small Lego block from the desktop, transfer the yellow small Lego block from the desktop to the red small Lego block, place the yellow small Lego block on the red small Lego block.'\nYour initial coordinate is [415, 178]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[415, 178], [457, 140], [453, 120], [460, 129], [411, 167], [419, 185], [427, 182], [416, 182], [419, 189], [415, 150]]}" + } + ], + "images": "RH20T_cfg1_task_0065_user_0010_scene_0005_cfg_0001_038522062547#1692", + "gt": "[[415, 178], [457, 140], [453, 120], [460, 129], [411, 167], [419, 185], [427, 182], [416, 182], [419, 189], [415, 150]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "14696_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove an object from the clear container and put back an object into the container then press down on the extension cable', and now you are performing subtask 'pick up an object from the transparent container.'\nFrom start point [288.0, 46.0], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[288.0, 46.0], [265.0, 57.0], [198.0, 121.0], [176.0, 123.0], [172.0, 104.0], [163.0, 105.0], [159.0, 110.0], [173.0, 114.0], [179.0, 119.0], [181.0, 128.0]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/14696_exterior_image_1_left#0.jpg", + "gt": "[[288.0, 46.0], [265.0, 57.0], [198.0, 121.0], [176.0, 123.0], [172.0, 104.0], [163.0, 105.0], [159.0, 110.0], [173.0, 114.0], [179.0, 119.0], [181.0, 128.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "81533_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the lid', and now you are performing subtask 'open the lid.'\nWith start location [146, 2], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[146, 2], [157, 37], [152, 59], [136, 78], [131, 82], [113, 70], [62, 51], [60, 46], [74, 43], [103, 46]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/81533_exterior_image_1_left#0.jpg", + "gt": "[[146, 2], [157, 37], [152, 59], [136, 78], [131, 82], [113, 70], [62, 51], [60, 46], [74, 43], [103, 46]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "91549_exterior_image_2_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the towel then move the pot to the right', and now you are performing subtask 'place the pot on the specified position on the surface.'\nWith start location [207, 99], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[207, 99], [192, 127], [185, 119], [176, 120], [174, 130], [187, 115], [202, 78], [219, 82], [228, 104], [216, 79]]}" + } + ], + "images": "91549_exterior_image_2_left#168", + "gt": "[[207, 99], [192, 127], [185, 119], [176, 120], [174, 130], [187, 115], [202, 78], [219, 82], [228, 104], [216, 79]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "8647_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the bottle from the table and put it in the clear container', and now you are performing subtask 'pick up the bottle from the table and put it in the clear container.'\nFrom start point [133, 21], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[133, 21], [167, 55], [187, 98], [179, 108], [189, 119], [190, 139], [181, 131], [177, 107], [156, 110], [165, 102]]}" + } + ], + "images": "8647_exterior_image_2_left#0", + "gt": "[[133, 21], [167, 55], [187, 98], [179, 108], [189, 119], [190, 139], [181, 131], [177, 107], [156, 110], [165, 102]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "44871_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the black cloth and put it on the table', and now you are performing subtask 'pick up the black cloth and put it on the table.'\nYou start from [146, 53]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[146, 53], [174, 58], [186, 68], [189, 88], [172, 89], [201, 46], [223, 28], [212, 81], [238, 116], [194, 97]]}" + } + ], + "images": "44871_exterior_image_1_left#0", + "gt": "[[146, 53], [174, 58], [186, 68], [189, 88], [172, 89], [201, 46], [223, 28], [212, 81], [238, 116], [194, 97]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0037_user_0014_scene_0010_cfg_0001_819112070044#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'pick up a block from the table, transfer a block from the table to the top of a block.'\nStarting at [400, 167], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[400, 167], [386, 173], [367, 192], [360, 193], [350, 199], [348, 207], [344, 211], [345, 217], [342, 187], [335, 178]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0037_user_0014_scene_0010_cfg_0001_819112070044#0.jpg", + "gt": "[[400, 167], [386, 173], [367, 192], [360, 193], [350, 199], [348, 207], [344, 211], [345, 217], [342, 187], [335, 178]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "30828_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the bottle from the table and place it inside the clear container', and now you are performing subtask 'pick up the bottle from the table and place it inside the clear container.'\nYour starting position is [205, 1]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[205, 1], [195, 29], [176, 42], [183, 44], [162, 62], [150, 93], [152, 103], [149, 85], [157, 95], [149, 81]]}" + } + ], + "images": "30828_exterior_image_1_left#0", + "gt": "[[205, 1], [195, 29], [176, 42], [183, 44], [162, 62], [150, 93], [152, 103], [149, 85], [157, 95], [149, 81]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "51601_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the pen into the bowl, then take it out and put it back on the table', and now you are performing subtask 'put the pen into the bowl.'\nYour initial coordinate is [283, 0]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[283, 0], [256, 10], [230, 28], [173, 98], [171, 109], [175, 80], [191, 39], [191, 30], [186, 26], [177, 33]]}" + } + ], + "images": "51601_exterior_image_2_left#0", + "gt": "[[283, 0], [256, 10], [230, 28], [173, 98], [171, 109], [175, 80], [191, 39], [191, 30], [186, 26], [177, 33]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "69053_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'transfer the white cloth from the transparent board to the table', and now you are performing subtask 'transfer the white cloth from the transparent board to the table.'\nWith start location [216, 41], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[216, 41], [181, 63], [166, 53], [183, 45], [173, 59], [156, 51], [206, 78], [208, 102], [198, 84], [201, 70]]}" + } + ], + "images": "69053_exterior_image_1_left#0", + "gt": "[[216, 41], [181, 63], [166, 53], [183, 45], [173, 59], [156, 51], [206, 78], [208, 102], [198, 84], [201, 70]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "53731_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the glue stick out of the cup and place it on the black box', and now you are performing subtask 'take the glue stick out of the cup and place it on the black box.'\nYou begin at [319.0, 51.5]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[319.0, 51.5], [205.0, 83.5], [218.0, 89.5], [191.0, 85.5], [200.0, 90.5], [184.0, 97.5], [204.0, 73.5], [231.0, 80.5], [231.0, 94.5], [230.0, 78.5]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/53731_exterior_image_1_left#0.jpg", + "gt": "[[319.0, 51.5], [205.0, 83.5], [218.0, 89.5], [191.0, 85.5], [200.0, 90.5], [184.0, 97.5], [204.0, 73.5], [231.0, 80.5], [231.0, 94.5], [230.0, 78.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "36877_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'twist the upper knob on the oven', and now you are performing subtask 'twist the upper knob on the oven.'\nBegin at [211, 54] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[211, 54], [202, 52], [184, 61], [199, 63], [204, 72], [188, 69], [182, 79], [203, 71], [198, 62], [197, 70]]}" + } + ], + "images": "36877_exterior_image_1_left#0", + "gt": "[[211, 54], [202, 52], [184, 61], [199, 63], [204, 72], [188, 69], [182, 79], [203, 71], [198, 62], [197, 70]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "10952_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick the wooden object on the table, put it on the case cover, take the container out of the case and put it on the box then place the dumbbell at the edge of the box', and now you are performing subtask 'place the dumbbell at the edge of the box.'\nYou start from [170.5, 103.0]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[170.5, 103.0], [172.5, 105.0], [168.5, 110.0], [168.5, 104.0], [166.5, 106.0], [155.5, 103.0], [152.5, 106.0], [162.5, 96.0], [182.5, 90.0], [192.5, 91.0]]}" + } + ], + "images": "10952_exterior_image_1_left#550", + "gt": "[[170.5, 103.0], [172.5, 105.0], [168.5, 110.0], [168.5, 104.0], [166.5, 106.0], [155.5, 103.0], [152.5, 106.0], [162.5, 96.0], [182.5, 90.0], [192.5, 91.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0057_user_0015_scene_0009_cfg_0001_819112070044#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn them on', and now you are performing subtask 'press the first button on the right side of the power strip.'\nBegin at [400, 168] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[400, 168], [402, 171], [447, 169], [460, 175], [501, 179], [498, 187], [504, 200], [499, 203], [504, 189], [509, 184]]}" + } + ], + "images": "RH20T_cfg1_task_0057_user_0015_scene_0009_cfg_0001_819112070044#0", + "gt": "[[400, 168], [402, 171], [447, 169], [460, 175], [501, 179], [498, 187], [504, 200], [499, 203], [504, 189], [509, 184]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "57139_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the mug closer to the sharpie', and now you are performing subtask 'move the mug closer to the sharpie.'\nYou begin at [131, 30]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[131, 30], [145, 39], [160, 54], [174, 75], [176, 87], [163, 79], [154, 79], [152, 81], [153, 83], [152, 71]]}" + } + ], + "images": "57139_exterior_image_1_left#0", + "gt": "[[131, 30], [145, 39], [160, 54], [174, 75], [176, 87], [163, 79], [154, 79], [152, 81], [153, 83], [152, 71]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "24484_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the yellow block in the orange pan', and now you are performing subtask 'put the yellow block in the orange pan.'\nYour starting position is [199, 0]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[199, 0], [187, 43], [175, 56], [181, 46], [198, 43], [229, 59], [221, 61], [217, 72], [220, 52], [216, 57]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/24484_exterior_image_2_left#0.jpg", + "gt": "[[199, 0], [187, 43], [175, 56], [181, 46], [198, 43], [229, 59], [221, 61], [217, 72], [220, 52], [216, 57]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "86920_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'cover the pot and fold the cloth', and now you are performing subtask 'fold the cloth on the table.'\nThe trajectory starts at [183, 111]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[183, 111], [142, 103], [154, 103], [156, 90], [146, 79], [144, 90], [135, 73], [148, 79], [152, 92], [150, 78]]}" + } + ], + "images": "86920_exterior_image_1_left#109", + "gt": "[[183, 111], [142, 103], [154, 103], [156, 90], [146, 79], [144, 90], [135, 73], [148, 79], [152, 92], [150, 78]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0011_user_0007_scene_0004_cfg_0005_104122061850#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'water the plant', and now you are performing subtask 'water the plant.'\nYou start from [311, 50]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[311, 50], [339, 0], [366, 1], [393, 27], [399, 74], [385, 0], [288, 0], [382, 0], [383, 14], [359, 0]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0011_user_0007_scene_0004_cfg_0005_104122061850#0.jpg", + "gt": "[[311, 50], [339, 0], [366, 1], [393, 27], [399, 74], [385, 0], [288, 0], [382, 0], [383, 14], [359, 0]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "89189_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the faucet spout to the left and move the doll forward', and now you are performing subtask 'place doll at edge of countertop.'\nYou begin at [154, 49]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[154, 49], [123, 55], [124, 66], [119, 74], [127, 80], [111, 75], [105, 87], [110, 90], [104, 79], [108, 81]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/89189_exterior_image_1_left#177.jpg", + "gt": "[[154, 49], [123, 55], [124, 66], [119, 74], [127, 80], [111, 75], [105, 87], [110, 90], [104, 79], [108, 81]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "37562_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the banana and pineapple plush on the table', and now you are performing subtask 'put the banana and pineapple plush on the table.'\nStart at [156, 38]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[156, 38], [160, 35], [171, 41], [198, 71], [195, 95], [205, 70], [232, 67], [250, 69], [243, 72], [243, 72]]}" + } + ], + "images": "37562_exterior_image_2_left#0", + "gt": "[[156, 38], [160, 35], [171, 41], [198, 71], [195, 95], [205, 70], [232, 67], [250, 69], [243, 72], [243, 72]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg3_task_0059_user_0010_scene_0004_cfg_0003_104122062823#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn the knob to increase the volume of the speaker', and now you are performing subtask 'twist the knob on the speaker clockwise to increase the volume, twist the knob on the speaker clockwise to increase the volume.'\nYou start from [249, 90]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[249, 90], [251, 87], [244, 81], [245, 89], [254, 95], [256, 93], [256, 96], [261, 91], [255, 89], [255, 89]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg3_task_0059_user_0010_scene_0004_cfg_0003_104122062823#187.jpg", + "gt": "[[249, 90], [251, 87], [244, 81], [245, 89], [254, 95], [256, 93], [256, 96], [261, 91], [255, 89], [255, 89]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "74032_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stir with a ladle in the bowl', and now you are performing subtask 'stir with a ladle in the bowl.'\nStarting at [122, 91], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[122, 91], [161, 89], [167, 104], [162, 90], [169, 85], [168, 91], [162, 86], [146, 96], [145, 77], [145, 77]]}" + } + ], + "images": "74032_exterior_image_2_left#0", + "gt": "[[122, 91], [161, 89], [167, 104], [162, 90], [169, 85], [168, 91], [162, 86], [146, 96], [145, 77], [145, 77]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "5154_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the marker from the center of the table to the bottom of the table', and now you are performing subtask 'move the marker from the center of the table to the bottom of the table.'\nStart at [271, 4]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[271, 4], [235, 16], [194, 48], [177, 73], [163, 84], [163, 89], [166, 93], [202, 87], [209, 72], [204, 74]]}" + } + ], + "images": "5154_exterior_image_2_left#0", + "gt": "[[271, 4], [235, 16], [194, 48], [177, 73], [163, 84], [163, 89], [166, 93], [202, 87], [209, 72], [204, 74]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0018_user_0008_scene_0007_cfg_0001_750612070853#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'play jenga', and now you are performing subtask 'play jenga.'\nStart at [350, 66]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[350, 66], [338, 148], [364, 226], [451, 314], [401, 284], [382, 239], [378, 197], [396, 185], [406, 197], [415, 173]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0018_user_0008_scene_0007_cfg_0001_750612070853#0.jpg", + "gt": "[[350, 66], [338, 148], [364, 226], [451, 314], [401, 284], [382, 239], [378, 197], [396, 185], [406, 197], [415, 173]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "78799_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the blue object on top of the orange one', and now you are performing subtask 'put the blue object on top of the orange one.'\nWith start location [162, 72], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[162, 72], [146, 76], [138, 83], [137, 79], [142, 89], [164, 76], [173, 77], [168, 64], [163, 62], [168, 62]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/78799_exterior_image_1_left#0.jpg", + "gt": "[[162, 72], [146, 76], [138, 83], [137, 79], [142, 89], [164, 76], [173, 77], [168, 64], [163, 62], [168, 62]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0066_user_0014_scene_0005_cfg_0001_038522062547#TrajectoryPrediction_Task#8", + "task": "TrajectoryPrediction_Task", + "p_index": 8, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with large Megabloks for the nth time with n blocks', and now you are performing subtask 'place the nth Megablock on the green base.'\nWith start location [358, 117], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[358, 117], [404, 115], [403, 104], [455, 162], [463, 139], [397, 73], [375, 79], [378, 94], [344, 39], [344, 39]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0066_user_0014_scene_0005_cfg_0001_038522062547#632.jpg", + "gt": "[[358, 117], [404, 115], [403, 104], [455, 162], [463, 139], [397, 73], [375, 79], [378, 94], [344, 39], [344, 39]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "84471_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the lid from the pot and place it on the table', and now you are performing subtask 'remove the lid from the pot and place it on the table.'\nFrom start point [318, 38], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[318, 38], [302, 48], [259, 87], [246, 113], [249, 109], [248, 105], [238, 112], [217, 144], [218, 155], [235, 141]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/84471_exterior_image_2_left#0.jpg", + "gt": "[[318, 38], [302, 48], [259, 87], [246, 113], [249, 109], [248, 105], [238, 112], [217, 144], [218, 155], [235, 141]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0081_user_0015_scene_0002_cfg_0004_104422070011#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the leg of the glasses (with one hand)', and now you are performing subtask 'pick up the glasses on the table.'\nThe trajectory starts at [282, 191]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[282, 191], [275, 192], [273, 191], [273, 190], [280, 181], [281, 177], [284, 173], [287, 175], [287, 177], [283, 183]]}" + } + ], + "images": "RH20T_cfg4_task_0081_user_0015_scene_0002_cfg_0004_104422070011#263", + "gt": "[[282, 191], [275, 192], [273, 191], [273, 190], [280, 181], [281, 177], [284, 173], [287, 175], [287, 177], [283, 183]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "71404_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the cloth from the stand and put it on the table', and now you are performing subtask 'take the cloth from the stand and put it on the table.'\nYour starting position is [102, 0]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[102, 0], [153, 26], [159, 36], [153, 49], [149, 19], [161, 25], [172, 48], [171, 83], [161, 63], [161, 63]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/71404_exterior_image_2_left#0.jpg", + "gt": "[[102, 0], [153, 26], [159, 36], [153, 49], [149, 19], [161, 25], [172, 48], [171, 83], [161, 63], [161, 63]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0094_user_0007_scene_0003_cfg_0004_104122063550#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the box', and now you are performing subtask 'push the lid of the box.'\nYou begin at [279, 190]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[279, 190], [280, 200], [278, 185], [282, 186], [283, 192], [265, 197], [294, 193], [306, 187], [319, 177], [297, 178]]}" + } + ], + "images": "RH20T_cfg4_task_0094_user_0007_scene_0003_cfg_0004_104122063550#0", + "gt": "[[279, 190], [280, 200], [278, 185], [282, 186], [283, 192], [265, 197], [294, 193], [306, 187], [319, 177], [297, 178]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "18425_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'switch on the toaster', and now you are performing subtask 'switch on the toaster.'\nYou start from [90.0, 37.0]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[90.0, 37.0], [163.0, 28.0], [198.0, 36.0], [214.0, 57.0], [225.0, 113.0], [220.0, 102.0], [225.0, 113.0], [202.0, 92.0], [179.0, 55.0], [160.0, 50.0]]}" + } + ], + "images": "18425_exterior_image_1_left#0", + "gt": "[[90.0, 37.0], [163.0, 28.0], [198.0, 36.0], [214.0, 57.0], [225.0, 113.0], [220.0, 102.0], [225.0, 113.0], [202.0, 92.0], [179.0, 55.0], [160.0, 50.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0013_user_0014_scene_0007_cfg_0006_104122061018#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'place the block on the scale', and now you are performing subtask 'place the block on the scale.'\nStart at [367, 28]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[367, 28], [387, 78], [378, 106], [387, 97], [396, 103], [396, 146], [398, 116], [385, 69], [387, 1], [392, 10]]}" + } + ], + "images": "RH20T_cfg6_task_0013_user_0014_scene_0007_cfg_0006_104122061018#0", + "gt": "[[367, 28], [387, 78], [378, 106], [387, 97], [396, 103], [396, 146], [398, 116], [385, 69], [387, 1], [392, 10]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "81019_exterior_image_2_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the fruits on the bowl and put them on the counter', and now you are performing subtask 'transfer the second fruit from the bowl to the countertop.'\nYour starting position is [193, 92]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[193, 92], [193, 79], [184, 76], [174, 93], [183, 78], [190, 76], [196, 90], [194, 113], [206, 126], [206, 120]]}" + } + ], + "images": "81019_exterior_image_2_left#135", + "gt": "[[193, 92], [193, 79], [184, 76], [174, 93], [183, 78], [190, 76], [196, 90], [194, 113], [206, 126], [206, 120]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "22312_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the curtain', and now you are performing subtask 'pull the curtain right.'\nYour initial coordinate is [220, 152]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[220, 152], [182, 130], [160, 96], [160, 43], [154, 53], [163, 64], [220, 98], [197, 96], [175, 83], [204, 107]]}" + } + ], + "images": "22312_exterior_image_1_left#0", + "gt": "[[220, 152], [182, 130], [160, 96], [160, 43], [154, 53], [163, 64], [220, 98], [197, 96], [175, 83], [204, 107]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0121_user_0010_scene_0002_cfg_0001_819112070044#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'taking out the light bulb by rotating it', and now you are performing subtask 'twist the light bulb counterclockwise to loosen it.'\nStart at [400, 167]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[400, 167], [401, 144], [403, 139], [399, 117], [394, 115], [398, 119], [397, 123], [395, 124], [396, 132], [400, 132]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0121_user_0010_scene_0002_cfg_0001_819112070044#0.jpg", + "gt": "[[400, 167], [401, 144], [403, 139], [399, 117], [394, 115], [398, 119], [397, 123], [395, 124], [396, 132], [400, 132]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0013_user_0020_scene_0010_cfg_0007_104122061330#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'place the block on the scale', and now you are performing subtask 'pick up the big block from the table, transfer the big block from the table to the scale, place the big block on the scale.'\nYou start from [266, 103]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[266, 103], [274, 122], [280, 123], [282, 151], [303, 182], [309, 207], [337, 249], [331, 204], [337, 178], [337, 178]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg7_task_0013_user_0020_scene_0010_cfg_0007_104122061330#0.jpg", + "gt": "[[266, 103], [274, 122], [280, 123], [282, 151], [303, 182], [309, 207], [337, 249], [331, 204], [337, 178], [337, 178]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "46919_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the door of the washing machine and push the tray back in', and now you are performing subtask 'push the tray back into the washing machine.'\nYou start from [209, 89]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[209, 89], [184, 107], [160, 163], [188, 180], [211, 179], [206, 162], [224, 124], [214, 120], [234, 122], [234, 122]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/46919_exterior_image_2_left#0.jpg", + "gt": "[[209, 89], [184, 107], [160, 163], [188, 180], [211, 179], [206, 162], [224, 124], [214, 120], [234, 122], [234, 122]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg3_task_0058_user_0010_scene_0010_cfg_0003_036422060909#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn off the power strips', and now you are performing subtask 'press the button on the power strip above, press the button on the power strip above.'\nBegin at [337, 88] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[337, 88], [300, 72], [323, 113], [233, 117], [217, 108], [198, 121], [206, 130], [212, 154], [204, 136], [204, 136]]}" + } + ], + "images": "RH20T_cfg3_task_0058_user_0010_scene_0010_cfg_0003_036422060909#0", + "gt": "[[337, 88], [300, 72], [323, 113], [233, 117], [217, 108], [198, 121], [206, 130], [212, 154], [204, 136], [204, 136]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "53838_exterior_image_2_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the glue stick in, take it out, and then put it back in the mug', and now you are performing subtask 'place the glue stick in the cup.'\nYou start from [180, 138]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[180, 138], [161, 121], [175, 96], [183, 148], [158, 112], [138, 109], [147, 106], [148, 128], [146, 116], [146, 116]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/53838_exterior_image_2_left#445.jpg", + "gt": "[[180, 138], [161, 121], [175, 96], [183, 148], [158, 112], [138, 109], [147, 106], [148, 128], [146, 116], [146, 116]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0101_user_0007_scene_0010_cfg_0005_104422070044#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'clean the table with a cloth', and now you are performing subtask 'clean the table with a cloth.'\nThe trajectory starts at [374, 132]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[374, 132], [395, 131], [430, 155], [448, 184], [442, 197], [411, 177], [414, 175], [455, 193], [410, 170], [397, 152]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0101_user_0007_scene_0010_cfg_0005_104422070044#0.jpg", + "gt": "[[374, 132], [395, 131], [430, 155], [448, 184], [442, 197], [411, 177], [414, 175], [455, 193], [410, 170], [397, 152]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "32537_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the black dish from the sink onto the rack', and now you are performing subtask 'put the black dish from the sink onto the rack.'\nYou begin at [230, 66]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[230, 66], [207, 75], [182, 118], [188, 100], [176, 79], [135, 68], [136, 49], [134, 79], [175, 73], [210, 94]]}" + } + ], + "images": "32537_exterior_image_1_left#0", + "gt": "[[230, 66], [207, 75], [182, 118], [188, 100], [176, 79], [135, 68], [136, 49], [134, 79], [175, 73], [210, 94]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0018_user_0016_scene_0001_cfg_0004_104122062823#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the block from the tower and place it on the table', and now you are performing subtask 'move the block from the tower and place it on the table.'\nYou begin at [243, 0]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[243, 0], [199, 0], [286, 0], [282, 27], [311, 68], [296, 49], [290, 73], [309, 70], [272, 49], [248, 4]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg4_task_0018_user_0016_scene_0001_cfg_0004_104122062823#0.jpg", + "gt": "[[243, 0], [199, 0], [286, 0], [282, 27], [311, 68], [296, 49], [290, 73], [309, 70], [272, 49], [248, 4]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "24876_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the three cups on the table together', and now you are performing subtask 'place the cup into the cup.'\nYou start from [248.0, 98.5]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[248.0, 98.5], [254.0, 108.5], [251.0, 119.5], [239.0, 77.5], [235.0, 90.5], [233.0, 83.5], [228.0, 86.5], [231.0, 101.5], [238.0, 78.5], [234.0, 83.5]]}" + } + ], + "images": "24876_exterior_image_1_left#188", + "gt": "[[248.0, 98.5], [254.0, 108.5], [251.0, 119.5], [239.0, 77.5], [235.0, 90.5], [233.0, 83.5], [228.0, 86.5], [231.0, 101.5], [238.0, 78.5], [234.0, 83.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0034_user_0007_scene_0005_cfg_0005_104122063678#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the squares in a row', and now you are performing subtask 'place the second square on the table next to the first square, pick up the third square from the table.'\nYour initial coordinate is [327, 194]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[327, 194], [329, 182], [321, 180], [297, 257], [292, 291], [289, 285], [301, 262], [332, 233], [323, 237], [323, 237]]}" + } + ], + "images": "RH20T_cfg5_task_0034_user_0007_scene_0005_cfg_0005_104122063678#568", + "gt": "[[327, 194], [329, 182], [321, 180], [297, 257], [292, 291], [289, 285], [301, 262], [332, 233], [323, 237], [323, 237]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0007_user_0020_scene_0004_cfg_0007_104122064161#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'holding a small block with the gripper and sweeping it from left to right on the table', and now you are performing subtask 'holding a small block with the gripper and sweeping it from left to right on the table.'\nYour starting position is [337, 115]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[337, 115], [352, 216], [368, 245], [380, 251], [378, 268], [387, 155], [380, 128], [388, 112], [377, 117], [377, 117]]}" + } + ], + "images": "RH20T_cfg7_task_0007_user_0020_scene_0004_cfg_0007_104122064161#0", + "gt": "[[337, 115], [352, 216], [368, 245], [380, 251], [378, 268], [387, 155], [380, 128], [388, 112], [377, 117], [377, 117]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0061_user_0020_scene_0002_cfg_0007_104122064161#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take everything out of the gift box', and now you are performing subtask 'place the object on the tabletop, pick up the cube in the box, transfer the cube from the box to the tabletop, place the cube on the tabletop.'\nFrom start point [372, 226], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[372, 226], [381, 189], [373, 161], [366, 158], [360, 176], [366, 149], [364, 171], [347, 212], [368, 119], [362, 113]]}" + } + ], + "images": "RH20T_cfg7_task_0061_user_0020_scene_0002_cfg_0007_104122064161#453", + "gt": "[[372, 226], [381, 189], [373, 161], [366, 158], [360, 176], [366, 149], [364, 171], [347, 212], [368, 119], [362, 113]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0108_user_0015_scene_0009_cfg_0004_104122062823#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'sharpen the pencil with a pencil sharpener', and now you are performing subtask 'twist the handle of the pencil sharpener clockwise.'\nThe trajectory starts at [306, 127]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[306, 127], [297, 124], [290, 130], [290, 141], [298, 153], [320, 134], [341, 133], [344, 131], [343, 121], [332, 113]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg4_task_0108_user_0015_scene_0009_cfg_0004_104122062823#153.jpg", + "gt": "[[306, 127], [297, 124], [290, 130], [290, 141], [298, 153], [320, 134], [341, 133], [344, 131], [343, 121], [332, 113]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "19841_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'change the position of the donut on the counter', and now you are performing subtask 'change the position of the donut on the counter.'\nYou begin at [232, 7]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[232, 7], [224, 32], [216, 47], [201, 67], [195, 84], [179, 76], [170, 74], [158, 75], [166, 63], [166, 63]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/19841_exterior_image_1_left#0.jpg", + "gt": "[[232, 7], [224, 32], [216, 47], [201, 67], [195, 84], [179, 76], [170, 74], [158, 75], [166, 63], [166, 63]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg3_task_0092_user_0010_scene_0003_cfg_0003_104122062823#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn the hands of the clock clockwise', and now you are performing subtask 'turn the hands of a clock clockwise.'\nYour initial coordinate is [242, 0]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[242, 0], [222, 9], [231, 2], [243, 6], [293, 66], [271, 124], [275, 129], [250, 137], [258, 129], [258, 129]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg3_task_0092_user_0010_scene_0003_cfg_0003_104122062823#0.jpg", + "gt": "[[242, 0], [222, 9], [231, 2], [243, 6], [293, 66], [271, 124], [275, 129], [250, 137], [258, 129], [258, 129]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "5583_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the blue marker into the bowl', and now you are performing subtask 'put the blue marker into the bowl.'\nYou begin at [140, 65]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[140, 65], [140, 67], [154, 60], [167, 60], [182, 68], [191, 82], [225, 82], [229, 86], [219, 103], [209, 96]]}" + } + ], + "images": "5583_exterior_image_1_left#0", + "gt": "[[140, 65], [140, 67], [154, 60], [167, 60], [182, 68], [191, 82], [225, 82], [229, 86], [219, 103], [209, 96]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0094_user_0014_scene_0010_cfg_0001_750612070851#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open a box', and now you are performing subtask 'fold the first lid on the box on the table.'\nYou start from [413, 178]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[413, 178], [314, 150], [297, 114], [288, 111], [284, 118], [288, 110], [274, 125], [268, 150], [272, 124], [287, 122]]}" + } + ], + "images": "RH20T_cfg1_task_0094_user_0014_scene_0010_cfg_0001_750612070851#0", + "gt": "[[413, 178], [314, 150], [297, 114], [288, 111], [284, 118], [288, 110], [274, 125], [268, 150], [272, 124], [287, 122]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0046_user_0014_scene_0001_cfg_0007_104122060811#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the cup on the cup rack', and now you are performing subtask 'put the cup on the cup rack.'\nWith start location [387, 130], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[387, 130], [372, 122], [360, 122], [352, 129], [352, 134], [333, 158], [319, 161], [315, 173], [325, 152], [363, 140]]}" + } + ], + "images": "RH20T_cfg7_task_0046_user_0014_scene_0001_cfg_0007_104122060811#0", + "gt": "[[387, 130], [372, 122], [360, 122], [352, 129], [352, 134], [333, 158], [319, 161], [315, 173], [325, 152], [363, 140]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0066_user_0014_scene_0005_cfg_0001_038522063145#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with large Megabloks for the nth time with n blocks', and now you are performing subtask 'pick up the first Megablock from the left side of the table, place the first Megablock on the green base.'\nWith start location [441, 97], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[441, 97], [461, 116], [542, 152], [544, 165], [532, 175], [541, 155], [539, 149], [522, 140], [492, 144], [473, 161]]}" + } + ], + "images": "RH20T_cfg1_task_0066_user_0014_scene_0005_cfg_0001_038522063145#0", + "gt": "[[441, 97], [461, 116], [542, 152], [544, 165], [532, 175], [541, 155], [539, 149], [522, 140], [492, 144], [473, 161]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "18274_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'use the pen to stir the contents of the mug, pour the contents of the mug on the table, then sweep them', and now you are performing subtask 'place the pen on the table.'\nStart at [36, 117]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[36, 117], [65, 128], [55, 153], [82, 140], [99, 169], [83, 138], [96, 107], [115, 128], [96, 119], [93, 147]]}" + } + ], + "images": "18274_exterior_image_1_left#0", + "gt": "[[36, 117], [65, 128], [55, 153], [82, 140], [99, 169], [83, 138], [96, 107], [115, 128], [96, 119], [93, 147]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0061_user_0020_scene_0001_cfg_0007_104122063633#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the lid of the gift box on the table, then take everything out of the gift box and place it all on the table', and now you are performing subtask 'place the cube on the tabletop, pick up the object from the gift box, transfer the object from the gift box to the tabletop, place the object on the tabletop.'\nYou start from [177, 153]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[177, 153], [171, 138], [170, 154], [186, 184], [185, 198], [179, 166], [180, 140], [186, 137], [205, 153], [205, 160]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg7_task_0061_user_0020_scene_0001_cfg_0007_104122063633#379.jpg", + "gt": "[[177, 153], [171, 138], [170, 154], [186, 184], [185, 198], [179, 166], [180, 140], [186, 137], [205, 153], [205, 160]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0064_user_0016_scene_0003_cfg_0004_036422060909#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the roll of paper down from the shelf', and now you are performing subtask 'pick up the roll of paper from the shelf, transfer the roll of paper from the shelf to the workspace, place the roll of paper in the workspace.'\nYou start from [339, 83]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[339, 83], [332, 82], [330, 66], [345, 59], [350, 68], [343, 81], [344, 77], [284, 79], [306, 73], [316, 54]]}" + } + ], + "images": "RH20T_cfg4_task_0064_user_0016_scene_0003_cfg_0004_036422060909#168", + "gt": "[[339, 83], [332, 82], [330, 66], [345, 59], [350, 68], [343, 81], [344, 77], [284, 79], [306, 73], [316, 54]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0029_user_0020_scene_0010_cfg_0007_104122061602#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'grasp the handle and open the drawer', and now you are performing subtask 'grasp the handle and open the drawer.'\nFrom start point [448, 116], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[448, 116], [449, 132], [429, 138], [423, 133], [426, 124], [441, 125], [438, 140], [483, 188], [488, 130], [469, 97]]}" + } + ], + "images": "RH20T_cfg7_task_0029_user_0020_scene_0010_cfg_0007_104122061602#0", + "gt": "[[448, 116], [449, 132], [429, 138], [423, 133], [426, 124], [441, 125], [438, 140], [483, 188], [488, 130], [469, 97]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "66066_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the fabric', and now you are performing subtask 'pick up the fabric on the table.'\nYou begin at [225, 3]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[225, 3], [206, 24], [216, 24], [208, 28], [206, 52], [225, 50], [222, 61], [222, 48], [216, 42], [217, 46]]}" + } + ], + "images": "66066_exterior_image_1_left#0", + "gt": "[[225, 3], [206, 24], [216, 24], [208, 28], [206, 52], [225, 50], [222, 61], [222, 48], [216, 42], [217, 46]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0034_user_0007_scene_0005_cfg_0005_104122061850#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the squares in a row', and now you are performing subtask 'pick up the first square from the table, transfer the first square from the table to the center of the table, place the first square in the center of the table, pick up the second square from the table.'\nYou start from [303, 47]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[303, 47], [303, 56], [325, 85], [311, 74], [307, 80], [333, 128], [333, 137], [332, 123], [351, 113], [395, 115]]}" + } + ], + "images": "RH20T_cfg5_task_0034_user_0007_scene_0005_cfg_0005_104122061850#0", + "gt": "[[303, 47], [303, 56], [325, 85], [311, 74], [307, 80], [333, 128], [333, 137], [332, 123], [351, 113], [395, 115]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0036_user_0014_scene_0001_cfg_0007_104122064161#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take a test tube from the rightmost side of the test tube rack, shake it in the air, and then place it back on the test tube rack', and now you are performing subtask 'take a test tube from the rightmost side of the test tube rack, shake it in the air, and then place it back on the test tube rack.'\nYour starting position is [337, 115]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[337, 115], [373, 159], [359, 204], [383, 140], [355, 106], [376, 137], [363, 112], [373, 157], [358, 196], [370, 155]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg7_task_0036_user_0014_scene_0001_cfg_0007_104122064161#0.jpg", + "gt": "[[337, 115], [373, 159], [359, 204], [383, 140], [355, 106], [376, 137], [363, 112], [373, 157], [358, 196], [370, 155]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0015_user_0008_scene_0002_cfg_0001_819112071037#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'play the drum', and now you are performing subtask 'pick up the drumsticks from the right table.'\nStarting at [343, 0], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[343, 0], [344, 41], [348, 57], [385, 123], [398, 163], [397, 146], [395, 151], [398, 156], [395, 151], [392, 171]]}" + } + ], + "images": "RH20T_cfg1_task_0015_user_0008_scene_0002_cfg_0001_819112071037#0", + "gt": "[[343, 0], [344, 41], [348, 57], [385, 123], [398, 163], [397, 146], [395, 151], [398, 156], [395, 151], [392, 171]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "17981_exterior_image_2_left#TrajectoryPrediction_Task#18", + "task": "TrajectoryPrediction_Task", + "p_index": 18, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the orange cloth', and now you are performing subtask 'fold the cloth on the table for the last time.'\nWith start location [196, 131], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[196, 131], [212, 117], [229, 117], [251, 124], [272, 142], [281, 169], [278, 180], [272, 178], [283, 136], [281, 103]]}" + } + ], + "images": "17981_exterior_image_2_left#462", + "gt": "[[196, 131], [212, 117], [229, 117], [251, 124], [272, 142], [281, 169], [278, 180], [272, 178], [283, 136], [281, 103]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0096_user_0015_scene_0005_cfg_0001_038522063145#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the block out of the drawer and put it on the table', and now you are performing subtask 'pull the drawer handle to open the drawer.'\nFrom start point [445, 48], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[445, 48], [443, 49], [443, 39], [440, 34], [432, 43], [435, 48], [429, 51], [433, 47], [441, 44], [446, 37]]}" + } + ], + "images": "RH20T_cfg1_task_0096_user_0015_scene_0005_cfg_0001_038522063145#187", + "gt": "[[445, 48], [443, 49], [443, 39], [440, 34], [432, 43], [435, 48], [429, 51], [433, 47], [441, 44], [446, 37]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "10945_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the cup to the left', and now you are performing subtask 'move the cup to the left.'\nThe trajectory starts at [122, 9]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[122, 9], [142, 19], [172, 56], [178, 74], [177, 86], [179, 88], [166, 75], [154, 75], [155, 79], [152, 62]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/10945_exterior_image_1_left#0.jpg", + "gt": "[[122, 9], [142, 19], [172, 56], [178, 74], [177, 86], [179, 88], [166, 75], [154, 75], [155, 79], [152, 62]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0130_user_0020_scene_0004_cfg_0006_104122060811#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'plug in the bulb holder with a bulb to the socket and turn on the switch of the bulb', and now you are performing subtask 'press the switch on the bulb.'\nStarting at [365, 123], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[365, 123], [363, 122], [364, 124], [372, 113], [371, 110], [371, 117], [374, 116], [383, 127], [388, 124], [382, 125]]}" + } + ], + "images": "RH20T_cfg6_task_0130_user_0020_scene_0004_cfg_0006_104122060811#496", + "gt": "[[365, 123], [363, 122], [364, 124], [372, 113], [371, 110], [371, 117], [374, 116], [383, 127], [388, 124], [382, 125]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "76408_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close the drawer', and now you are performing subtask 'close the drawer.'\nYou start from [193, 175]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[193, 175], [196, 160], [207, 147], [220, 138], [229, 129], [231, 124], [231, 116], [226, 104], [212, 102], [212, 102]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/76408_exterior_image_1_left#0.jpg", + "gt": "[[193, 175], [196, 160], [207, 147], [220, 138], [229, 129], [231, 124], [231, 116], [226, 104], [212, 102], [212, 102]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0037_user_0007_scene_0010_cfg_0005_104122061850#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'pick up the first block on the table, transfer the first block from the table to the position above the second block, place the first block on top of the second block.'\nBegin at [305, 50] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[305, 50], [316, 106], [312, 139], [298, 144], [301, 162], [290, 149], [310, 151], [324, 160], [322, 171], [330, 172]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0037_user_0007_scene_0010_cfg_0005_104122061850#0.jpg", + "gt": "[[305, 50], [316, 106], [312, 139], [298, 144], [301, 162], [290, 149], [310, 151], [324, 160], [322, 171], [330, 172]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0001_user_0014_scene_0007_cfg_0007_104122061330#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the nearest green button', and now you are performing subtask 'press the nearest green button.'\nYour starting position is [266, 103]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[266, 103], [261, 102], [285, 132], [323, 193], [322, 206], [326, 200], [325, 193], [309, 165], [277, 125], [255, 110]]}" + } + ], + "images": "RH20T_cfg7_task_0001_user_0014_scene_0007_cfg_0007_104122061330#0", + "gt": "[[266, 103], [261, 102], [285, 132], [323, 193], [322, 206], [326, 200], [325, 193], [309, 165], [277, 125], [255, 110]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "56568_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'slide the black lid off', and now you are performing subtask 'slide the black lid off.'\nStart at [130.0, 71.5]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[130.0, 71.5], [146.0, 59.5], [173.0, 57.5], [224.0, 95.5], [226.0, 104.5], [206.0, 116.5], [204.0, 109.5], [212.0, 111.5], [205.0, 113.5], [201.0, 99.5]]}" + } + ], + "images": "56568_exterior_image_1_left#0", + "gt": "[[130.0, 71.5], [146.0, 59.5], [173.0, 57.5], [224.0, 95.5], [226.0, 104.5], [206.0, 116.5], [204.0, 109.5], [212.0, 111.5], [205.0, 113.5], [201.0, 99.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "21686_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the stapler', and now you are performing subtask 'press the stapler.'\nYour initial coordinate is [279, 12]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[279, 12], [280, 42], [294, 75], [301, 81], [301, 108], [294, 135], [305, 155], [320, 166], [283, 130], [281, 123]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/21686_exterior_image_1_left#0.jpg", + "gt": "[[279, 12], [280, 42], [294, 75], [301, 81], [301, 108], [294, 135], [305, 155], [320, 166], [283, 130], [281, 123]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "91405_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the can and place it on the lower shelf', and now you are performing subtask 'pick up the can and place it on the lower shelf.'\nFrom start point [50, 100], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[50, 100], [75, 112], [82, 138], [99, 131], [81, 88], [88, 34], [105, 17], [128, 44], [101, 44], [85, 68]]}" + } + ], + "images": "91405_exterior_image_1_left#0", + "gt": "[[50, 100], [75, 112], [82, 138], [99, 131], [81, 88], [88, 34], [105, 17], [128, 44], [101, 44], [85, 68]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "66608_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'place the spoon with the other cutlery then put the red ball on the plate', and now you are performing subtask 'place the red ball on the plate.'\nStart at [195, 97]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[195, 97], [234, 145], [212, 129], [198, 137], [195, 123], [185, 121], [177, 152], [186, 180], [176, 180], [198, 138]]}" + } + ], + "images": "66608_exterior_image_1_left#272", + "gt": "[[195, 97], [234, 145], [212, 129], [198, 137], [195, 123], [185, 121], [177, 152], [186, 180], [176, 180], [198, 138]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "592_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the drawer then place the green pear inside the drawer', and now you are performing subtask 'pick up the green pear from the box on the countertop.'\nYou start from [240, 79]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[240, 79], [189, 35], [209, 46], [195, 40], [204, 57], [183, 78], [181, 91], [228, 84], [203, 53], [169, 40]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/592_exterior_image_1_left#0.jpg", + "gt": "[[240, 79], [189, 35], [209, 46], [195, 40], [204, 57], [183, 78], [181, 91], [228, 84], [203, 53], [169, 40]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "3579_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the orange and pineapple plushies on the black tray', and now you are performing subtask 'place the pineapple plush toy on the black tray.'\nYour starting position is [181.0, 78.0]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[181.0, 78.0], [145.0, 92.0], [136.0, 102.0], [133.0, 84.0], [157.0, 75.0], [177.0, 109.0], [215.0, 117.0], [229.0, 132.0], [243.0, 127.0], [179.0, 108.0]]}" + } + ], + "images": "3579_exterior_image_1_left#192", + "gt": "[[181.0, 78.0], [145.0, 92.0], [136.0, 102.0], [133.0, 84.0], [157.0, 75.0], [177.0, 109.0], [215.0, 117.0], [229.0, 132.0], [243.0, 127.0], [179.0, 108.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "12799_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the cup', and now you are performing subtask 'move the cup.'\nFrom start point [242, 6], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[242, 6], [173, 24], [165, 28], [177, 24], [175, 30], [149, 27], [142, 55], [154, 54], [164, 70], [169, 62]]}" + } + ], + "images": "12799_exterior_image_1_left#0", + "gt": "[[242, 6], [173, 24], [165, 28], [177, 24], [175, 30], [149, 27], [142, 55], [154, 54], [164, 70], [169, 62]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "51674_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the silver cup from the stove to the counter-top', and now you are performing subtask 'move the silver cup from the stove to the counter-top.'\nStart at [107, 127]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[107, 127], [170, 120], [202, 146], [193, 136], [194, 101], [174, 86], [116, 104], [110, 97], [119, 131], [117, 110]]}" + } + ], + "images": "51674_exterior_image_1_left#0", + "gt": "[[107, 127], [170, 120], [202, 146], [193, 136], [194, 101], [174, 86], [116, 104], [110, 97], [119, 131], [117, 110]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "85017_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'slide the white cup on the desk', and now you are performing subtask 'slide the white cup on the desk.'\nYou begin at [263.5, 13.0]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[263.5, 13.0], [241.5, 19.0], [223.5, 54.0], [183.5, 79.0], [187.5, 82.0], [179.5, 88.0], [167.5, 91.0], [182.5, 93.0], [184.5, 97.0], [184.5, 85.0]]}" + } + ], + "images": "85017_exterior_image_1_left#0", + "gt": "[[263.5, 13.0], [241.5, 19.0], [223.5, 54.0], [183.5, 79.0], [187.5, 82.0], [179.5, 88.0], [167.5, 91.0], [182.5, 93.0], [184.5, 97.0], [184.5, 85.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "19382_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn off the light and then turn it back on', and now you are performing subtask 'press the switch on the wall to turn on the light.'\nYour starting position is [96, 80]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[96, 80], [88, 77], [86, 73], [96, 70], [92, 70], [90, 78], [87, 78], [88, 71], [94, 70], [94, 70]]}" + } + ], + "images": "19382_exterior_image_1_left#142", + "gt": "[[96, 80], [88, 77], [86, 73], [96, 70], [92, 70], [90, 78], [87, 78], [88, 71], [94, 70], [94, 70]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0065_user_0010_scene_0005_cfg_0001_819112070044#TrajectoryPrediction_Task#8", + "task": "TrajectoryPrediction_Task", + "p_index": 8, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with small Lego blocks for the nth time with n blocks', and now you are performing subtask 'place the red small Lego block on the blue small Lego block, press the red small Lego block, pick up the yellow small Lego block from the desktop, transfer the yellow small Lego block from the desktop to the red small Lego block, place the yellow small Lego block on the red small Lego block.'\nThe trajectory starts at [393, 209]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[393, 209], [397, 193], [371, 175], [343, 181], [331, 195], [354, 184], [391, 194], [395, 187], [394, 200], [386, 187]]}" + } + ], + "images": "RH20T_cfg1_task_0065_user_0010_scene_0005_cfg_0001_819112070044#1596", + "gt": "[[393, 209], [397, 193], [371, 175], [343, 181], [331, 195], [354, 184], [391, 194], [395, 187], [394, 200], [386, 187]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0032_user_0020_scene_0009_cfg_0006_104122063633#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'slide the outer casing onto the gift box', and now you are performing subtask 'slide the outer casing onto the gift box.'\nStart at [232, 119]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[232, 119], [227, 98], [215, 101], [213, 96], [212, 118], [195, 145], [194, 105], [194, 110], [186, 108], [189, 87]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg6_task_0032_user_0020_scene_0009_cfg_0006_104122063633#0.jpg", + "gt": "[[232, 119], [227, 98], [215, 101], [213, 96], [212, 118], [195, 145], [194, 105], [194, 110], [186, 108], [189, 87]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "4810_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove one white plate from the dishwasher and place it on top of the white plate on the countertop', and now you are performing subtask 'remove one white plate from the dishwasher and place it on top of the white plate on the countertop.'\nYou begin at [146, 64]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[146, 64], [177, 75], [172, 103], [178, 75], [195, 63], [208, 65], [235, 84], [222, 86], [182, 71], [158, 74]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/4810_exterior_image_2_left#0.jpg", + "gt": "[[146, 64], [177, 75], [172, 103], [178, 75], [195, 63], [208, 65], [235, 84], [222, 86], [182, 71], [158, 74]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "56707_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the landfill bin to the left then right', and now you are performing subtask 'place the trash can to the right side of the table.'\nWith start location [171.0, 115.0], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[171.0, 115.0], [171.0, 120.0], [171.0, 114.0], [176.0, 116.0], [177.0, 124.0], [187.0, 122.0], [190.0, 125.0], [191.0, 122.0], [183.0, 110.0], [167.0, 104.0]]}" + } + ], + "images": "56707_exterior_image_1_left#197", + "gt": "[[171.0, 115.0], [171.0, 120.0], [171.0, 114.0], [176.0, 116.0], [177.0, 124.0], [187.0, 122.0], [190.0, 125.0], [191.0, 122.0], [183.0, 110.0], [167.0, 104.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg2_task_0003_user_0006_scene_0007_cfg_0002_037522062165#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the three buttons in sequence', and now you are performing subtask 'press the gray base green button.'\nStarting at [282, 174], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[282, 174], [202, 151], [182, 135], [185, 144], [179, 130], [187, 153], [178, 155], [189, 174], [187, 142], [226, 133]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg2_task_0003_user_0006_scene_0007_cfg_0002_037522062165#0.jpg", + "gt": "[[282, 174], [202, 151], [182, 135], [185, 144], [179, 130], [187, 153], [178, 155], [189, 174], [187, 142], [226, 133]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "865_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'use the wooden spoon to stir the contents of the pot', and now you are performing subtask 'use the wooden spoon to stir the contents of the pot.'\nYou start from [140, 115]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[140, 115], [103, 124], [94, 101], [106, 120], [102, 97], [122, 95], [91, 95], [126, 98], [97, 112], [89, 98]]}" + } + ], + "images": "865_exterior_image_2_left#0", + "gt": "[[140, 115], [103, 124], [94, 101], [106, 120], [102, 97], [122, 95], [91, 95], [126, 98], [97, 112], [89, 98]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0083_user_0007_scene_0005_cfg_0005_037522062165#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'swat with a flyswatter', and now you are performing subtask 'swat with a flyswatter.'\nYour initial coordinate is [288, 152]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[288, 152], [301, 162], [334, 283], [340, 345], [337, 360], [328, 360], [394, 331], [391, 295], [308, 259], [308, 259]]}" + } + ], + "images": "RH20T_cfg5_task_0083_user_0007_scene_0005_cfg_0005_037522062165#0", + "gt": "[[288, 152], [301, 162], [334, 283], [340, 345], [337, 360], [328, 360], [394, 331], [391, 295], [308, 259], [308, 259]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "46463_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'rotate the first rod on the foosball table', and now you are performing subtask 'rotate the first rod on the foosball table.'\nStarting at [157, 60], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[157, 60], [173, 60], [212, 102], [206, 102], [226, 132], [219, 133], [229, 131], [222, 121], [232, 123], [217, 117]]}" + } + ], + "images": "46463_exterior_image_1_left#0", + "gt": "[[157, 60], [173, 60], [212, 102], [206, 102], [226, 132], [219, 133], [229, 131], [222, 121], [232, 123], [217, 117]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0012_user_0014_scene_0004_cfg_0001_038522062547#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'push the soccer ball to the front of the goal', and now you are performing subtask 'push the soccer ball to the front of the goal.'\nFrom start point [406, 137], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[406, 137], [417, 127], [482, 110], [483, 120], [471, 131], [461, 131], [465, 130], [461, 138], [400, 146], [400, 146]]}" + } + ], + "images": "RH20T_cfg1_task_0012_user_0014_scene_0004_cfg_0001_038522062547#0", + "gt": "[[406, 137], [417, 127], [482, 110], [483, 120], [471, 131], [461, 131], [465, 130], [461, 138], [400, 146], [400, 146]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0003_user_0015_scene_0008_cfg_0001_038522062547#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the three buttons from left to right in sequence', and now you are performing subtask 'press the green button on the right.'\nYou begin at [407, 136]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[407, 136], [416, 123], [423, 151], [386, 187], [391, 195], [401, 184], [399, 194], [399, 177], [431, 142], [419, 119]]}" + } + ], + "images": "RH20T_cfg1_task_0003_user_0015_scene_0008_cfg_0001_038522062547#0", + "gt": "[[407, 136], [416, 123], [423, 151], [386, 187], [391, 195], [401, 184], [399, 194], [399, 177], [431, 142], [419, 119]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "60705_exterior_image_2_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the table cloth', and now you are performing subtask 'fold the tablecloth.'\nYou begin at [189, 113]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[189, 113], [193, 118], [195, 124], [196, 121], [201, 117], [204, 115], [207, 115], [201, 110], [198, 110], [195, 113]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/60705_exterior_image_2_left#264.jpg", + "gt": "[[189, 113], [193, 118], [195, 124], [196, 121], [201, 117], [204, 115], [207, 115], [201, 110], [198, 110], [195, 113]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "38695_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the cup to the left', and now you are performing subtask 'move the cup to the left.'\nThe trajectory starts at [241.0, 55.5]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[241.0, 55.5], [234.0, 46.5], [228.0, 48.5], [233.0, 50.5], [223.0, 56.5], [209.0, 84.5], [214.0, 83.5], [202.0, 97.5], [184.0, 105.5], [176.0, 89.5]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/38695_exterior_image_1_left#0.jpg", + "gt": "[[241.0, 55.5], [234.0, 46.5], [228.0, 48.5], [233.0, 50.5], [223.0, 56.5], [209.0, 84.5], [214.0, 83.5], [202.0, 97.5], [184.0, 105.5], [176.0, 89.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0058_user_0007_scene_0002_cfg_0005_104122061850#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press a row of two power strip buttons to turn off the power strips', and now you are performing subtask 'press the first button on the power socket, press the second button on the power socket.'\nStart at [305, 50]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[305, 50], [316, 53], [330, 70], [348, 110], [349, 145], [353, 148], [351, 163], [347, 153], [332, 149], [332, 149]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0058_user_0007_scene_0002_cfg_0005_104122061850#0.jpg", + "gt": "[[305, 50], [316, 53], [330, 70], [348, 110], [349, 145], [353, 148], [351, 163], [347, 153], [332, 149], [332, 149]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg2_task_0022_user_0003_scene_0004_cfg_0002_104422070044#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'wave the flag', and now you are performing subtask 'wave the flag.'\nYou begin at [310, 190]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[310, 190], [308, 179], [333, 159], [322, 164], [293, 150], [291, 160], [285, 140], [352, 154], [277, 136], [310, 158]]}" + } + ], + "images": "RH20T_cfg2_task_0022_user_0003_scene_0004_cfg_0002_104422070044#0", + "gt": "[[310, 190], [308, 179], [333, 159], [322, 164], [293, 150], [291, 160], [285, 140], [352, 154], [277, 136], [310, 158]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "40510_exterior_image_1_left#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the glue stick from the cup, place it on the box, then on the table, back into the cup, and lastly on the table', and now you are performing subtask 'twist glue stick clockwise and place it on the table.'\nYour starting position is [251, 124]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[251, 124], [261, 125], [250, 124], [238, 132], [241, 134], [261, 109], [230, 91], [211, 101], [201, 126], [207, 111]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/40510_exterior_image_1_left#295.jpg", + "gt": "[[251, 124], [261, 125], [250, 124], [238, 132], [241, 134], [261, 109], [230, 91], [211, 101], [201, 126], [207, 111]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg2_task_0096_user_0007_scene_0005_cfg_0002_105422061350#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take something out of the drawer, put it on the table', and now you are performing subtask 'pull the drawer handle to pull out the drawer, pick up the object from the drawer.'\nFrom start point [264, 216], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[264, 216], [266, 216], [263, 215], [263, 208], [247, 177], [244, 165], [235, 154], [238, 152], [242, 167], [242, 167]]}" + } + ], + "images": "RH20T_cfg2_task_0096_user_0007_scene_0005_cfg_0002_105422061350#0", + "gt": "[[264, 216], [266, 216], [263, 215], [263, 208], [247, 177], [244, 165], [235, 154], [238, 152], [242, 167], [242, 167]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "36863_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the towel from the backrest to the seat of the chair', and now you are performing subtask 'move the towel from the backrest to the seat of the chair.'\nFrom start point [212, 63], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[212, 63], [180, 55], [166, 43], [146, 46], [135, 62], [129, 57], [138, 84], [160, 106], [154, 105], [172, 132]]}" + } + ], + "images": "36863_exterior_image_1_left#0", + "gt": "[[212, 63], [180, 55], [166, 43], [146, 46], [135, 62], [129, 57], [138, 84], [160, 106], [154, 105], [172, 132]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0003_user_0010_scene_0005_cfg_0005_037522062165#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press three buttons from left to right in sequence', and now you are performing subtask 'press the green button on the right, press the red button in the middle.'\nThe trajectory starts at [253, 206]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[253, 206], [253, 216], [255, 216], [253, 221], [255, 208], [259, 202], [271, 204], [340, 238], [353, 249], [350, 252]]}" + } + ], + "images": "RH20T_cfg5_task_0003_user_0010_scene_0005_cfg_0005_037522062165#244", + "gt": "[[253, 206], [253, 216], [255, 216], [253, 221], [255, 208], [259, 202], [271, 204], [340, 238], [353, 249], [350, 252]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "2362_exterior_image_2_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the wallet from the table and put it in the black bag', and now you are performing subtask 'pick up the wallet from the table.'\nYou start from [174, 126]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[174, 126], [199, 130], [179, 149], [180, 167], [168, 154], [183, 168], [171, 137], [186, 148], [191, 130], [191, 130]]}" + } + ], + "images": "2362_exterior_image_2_left#240", + "gt": "[[174, 126], [199, 130], [179, 149], [180, 167], [168, 154], [183, 168], [171, 137], [186, 148], [191, 130], [191, 130]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0013_user_0020_scene_0010_cfg_0007_104122061330#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'place the block on the scale', and now you are performing subtask 'place the big block on the scale, pick up the small block from the table, transfer the small block from the table to the big block, place the small block on the big block.'\nThe trajectory starts at [337, 178]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[337, 178], [319, 190], [297, 227], [300, 230], [310, 219], [319, 195], [336, 176], [326, 179], [311, 191], [282, 189]]}" + } + ], + "images": "RH20T_cfg7_task_0013_user_0020_scene_0010_cfg_0007_104122061330#252", + "gt": "[[337, 178], [319, 190], [297, 227], [300, 230], [310, 219], [319, 195], [336, 176], [326, 179], [311, 191], [282, 189]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0004_user_0001_scene_0005_cfg_0001_039422060546#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the small block on the right side of the desk and move it to the left side of the desk', and now you are performing subtask 'pick up the small block on the right side of the desk and move it to the left side of the desk.'\nStarting at [255, 128], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[255, 128], [255, 158], [177, 232], [190, 248], [175, 243], [221, 273], [213, 262], [247, 223], [256, 157], [293, 74]]}" + } + ], + "images": "RH20T_cfg1_task_0004_user_0001_scene_0005_cfg_0001_039422060546#0", + "gt": "[[255, 128], [255, 158], [177, 232], [190, 248], [175, 243], [221, 273], [213, 262], [247, 223], [256, 157], [293, 74]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0014_user_0016_scene_0003_cfg_0004_036422060909#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'place the block on the table next to the scale', and now you are performing subtask 'place the block on the table next to the scale.'\nYou begin at [337, 78]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[337, 78], [383, 99], [357, 102], [317, 72], [323, 133], [303, 123], [275, 140], [295, 116], [284, 119], [284, 119]]}" + } + ], + "images": "RH20T_cfg4_task_0014_user_0016_scene_0003_cfg_0004_036422060909#0", + "gt": "[[337, 78], [383, 99], [357, 102], [317, 72], [323, 133], [303, 123], [275, 140], [295, 116], [284, 119], [284, 119]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0081_user_0007_scene_0003_cfg_0005_105422061350#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the leg of the glasses (with one hand)', and now you are performing subtask 'fold the legs of the glasses to unfold them.'\nFrom start point [189, 130], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[189, 130], [195, 131], [202, 138], [204, 144], [201, 157], [192, 139], [193, 123], [195, 119], [194, 112], [176, 94]]}" + } + ], + "images": "RH20T_cfg5_task_0081_user_0007_scene_0003_cfg_0005_105422061350#399", + "gt": "[[189, 130], [195, 131], [202, 138], [204, 144], [201, 157], [192, 139], [193, 123], [195, 119], [194, 112], [176, 94]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "31978_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'lay the bottle on its side then place it upside down', and now you are performing subtask 'place the bottle upside down on the table.'\nBegin at [200, 67] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[200, 67], [201, 79], [200, 66], [204, 59], [192, 77], [190, 66], [190, 56], [191, 56], [191, 59], [191, 57]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/31978_exterior_image_1_left#175.jpg", + "gt": "[[200, 67], [201, 79], [200, 66], [204, 59], [192, 77], [190, 66], [190, 56], [191, 56], [191, 59], [191, 57]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "27913_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pour the contents of the cup into the bowl', and now you are performing subtask 'pour the contents of the cup into the bowl.'\nFrom start point [134, 107], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[134, 107], [144, 97], [153, 107], [161, 101], [159, 98], [157, 102], [158, 97], [157, 99], [156, 96], [156, 96]]}" + } + ], + "images": "27913_exterior_image_2_left#0", + "gt": "[[134, 107], [144, 97], [153, 107], [161, 101], [159, 98], [157, 102], [158, 97], [157, 99], [156, 96], [156, 96]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0010_user_0007_scene_0003_cfg_0005_104122063678#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'place the handset of the telephone on the corresponding phone cradle', and now you are performing subtask 'place the handset of the telephone on the corresponding phone cradle.'\nYour initial coordinate is [212, 120]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[212, 120], [200, 58], [213, 61], [204, 139], [217, 127], [242, 168], [240, 198], [223, 215], [237, 186], [231, 162]]}" + } + ], + "images": "RH20T_cfg5_task_0010_user_0007_scene_0003_cfg_0005_104122063678#0", + "gt": "[[212, 120], [200, 58], [213, 61], [204, 139], [217, 127], [242, 168], [240, 198], [223, 215], [237, 186], [231, 162]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "85048_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the marker inside the cup', and now you are performing subtask 'put the marker inside the cup.'\nYou start from [189, 3]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[189, 3], [177, 113], [157, 125], [167, 129], [163, 147], [162, 115], [183, 103], [195, 108], [166, 105], [154, 119]]}" + } + ], + "images": "85048_exterior_image_1_left#0", + "gt": "[[189, 3], [177, 113], [157, 125], [167, 129], [163, 147], [162, 115], [183, 103], [195, 108], [166, 105], [154, 119]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0003_user_0010_scene_0001_cfg_0005_104422070044#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press three buttons from left to right in sequence', and now you are performing subtask 'press the red button in the middle, press the green button on the left.'\nYou start from [394, 152]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[394, 152], [387, 142], [349, 137], [352, 134], [353, 144], [349, 128], [355, 123], [352, 114], [378, 122], [388, 131]]}" + } + ], + "images": "RH20T_cfg5_task_0003_user_0010_scene_0001_cfg_0005_104422070044#161", + "gt": "[[394, 152], [387, 142], [349, 137], [352, 134], [353, 144], [349, 128], [355, 123], [352, 114], [378, 122], [388, 131]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "43389_exterior_image_1_left#TrajectoryPrediction_Task#8", + "task": "TrajectoryPrediction_Task", + "p_index": 8, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the top drawer, pick up the watermelon plush toy from the countertop and put it in the basket. pick up the banana plush toy from the basket in the drawer and put it on the countertop. close the top drawer', and now you are performing subtask 'push the handle of the top drawer to close the drawer.'\nThe trajectory starts at [140, 125]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[140, 125], [224, 129], [252, 144], [237, 154], [195, 151], [204, 147], [215, 152], [213, 158], [173, 162], [215, 109]]}" + } + ], + "images": "43389_exterior_image_1_left#476", + "gt": "[[140, 125], [224, 129], [252, 144], [237, 154], [195, 151], [204, 147], [215, 152], [213, 158], [173, 162], [215, 109]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0217_user_0010_scene_0003_cfg_0004_104122062823#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'plug in the bulb holder to the socket', and now you are performing subtask 'plug in the bulb holder to the socket.'\nThe trajectory starts at [293, 0]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[293, 0], [268, 8], [305, 7], [304, 0], [292, 35], [293, 0], [352, 7], [356, 42], [328, 98], [328, 98]]}" + } + ], + "images": "RH20T_cfg4_task_0217_user_0010_scene_0003_cfg_0004_104122062823#0", + "gt": "[[293, 0], [268, 8], [305, 7], [304, 0], [292, 35], [293, 0], [352, 7], [356, 42], [328, 98], [328, 98]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "89810_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the blue cloth from the back of the chair', and now you are performing subtask 'pick up the blue fabric on the back of the chair.'\nFrom start point [241, 119], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[241, 119], [216, 106], [206, 105], [208, 107], [202, 113], [196, 113], [197, 125], [195, 128], [193, 121], [195, 126]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/89810_exterior_image_1_left#0.jpg", + "gt": "[[241, 119], [216, 106], [206, 105], [208, 107], [202, 113], [196, 113], [197, 125], [195, 128], [193, 121], [195, 126]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "7719_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the green bag of snacks in the sink', and now you are performing subtask 'put the green bag of snacks in the sink.'\nYour initial coordinate is [225, 86]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[225, 86], [211, 101], [207, 144], [203, 128], [218, 123], [222, 127], [222, 141], [218, 135], [226, 132], [224, 136]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/7719_exterior_image_2_left#0.jpg", + "gt": "[[225, 86], [211, 101], [207, 144], [203, 128], [218, 123], [222, 127], [222, 141], [218, 135], [226, 132], [224, 136]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0082_user_0007_scene_0004_cfg_0005_104122061850#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'scoop water with a large spoon from one bowl to another', and now you are performing subtask 'scoop water with a large spoon from one bowl to another.'\nWith start location [305, 50], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[305, 50], [340, 89], [344, 106], [326, 115], [321, 92], [330, 92], [370, 146], [374, 199], [359, 120], [342, 122]]}" + } + ], + "images": "RH20T_cfg5_task_0082_user_0007_scene_0004_cfg_0005_104122061850#0", + "gt": "[[305, 50], [340, 89], [344, 106], [326, 115], [321, 92], [330, 92], [370, 146], [374, 199], [359, 120], [342, 122]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0103_user_0010_scene_0005_cfg_0001_819112070044#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the plate to the goal post', and now you are performing subtask 'move the plate to the goal post.'\nBegin at [400, 169] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[400, 169], [400, 190], [416, 193], [426, 213], [412, 202], [294, 223], [285, 243], [316, 201], [360, 176], [356, 165]]}" + } + ], + "images": "RH20T_cfg1_task_0103_user_0010_scene_0005_cfg_0001_819112070044#0", + "gt": "[[400, 169], [400, 190], [416, 193], [426, 213], [412, 202], [294, 223], [285, 243], [316, 201], [360, 176], [356, 165]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "26304_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the black bin to the left', and now you are performing subtask 'move the black bin to the left.'\nYou start from [161, 69]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[161, 69], [185, 47], [211, 34], [203, 42], [252, 43], [262, 62], [224, 54], [179, 58], [178, 65], [169, 52]]}" + } + ], + "images": "26304_exterior_image_1_left#0", + "gt": "[[161, 69], [185, 47], [211, 34], [203, 42], [252, 43], [262, 62], [224, 54], [179, 58], [178, 65], [169, 52]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "54208_exterior_image_2_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'place the pen inside the cup', and now you are performing subtask 'place the pen inside the cup.'\nFrom start point [148, 81], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[148, 81], [143, 67], [122, 43], [112, 48], [114, 56], [108, 60], [109, 71], [130, 54], [143, 54], [143, 54]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/54208_exterior_image_2_left#136.jpg", + "gt": "[[148, 81], [143, 67], [122, 43], [112, 48], [114, 56], [108, 60], [109, 71], [130, 54], [143, 54], [143, 54]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "23955_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pour the contents in the cup into the bowl', and now you are performing subtask 'pour the contents in the cup into the bowl.'\nYour initial coordinate is [125, 121]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[125, 121], [143, 102], [161, 107], [164, 113], [164, 117], [161, 117], [158, 108], [161, 117], [166, 112], [165, 109]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/23955_exterior_image_2_left#0.jpg", + "gt": "[[125, 121], [143, 102], [161, 107], [164, 113], [164, 117], [161, 117], [158, 108], [161, 117], [166, 112], [165, 109]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0023_user_0010_scene_0007_cfg_0005_104422070044#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn on the power strip by pressing the button', and now you are performing subtask 'turn on the power strip by pressing the button.'\nYou begin at [374, 132]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[374, 132], [365, 168], [338, 168], [340, 177], [349, 175], [342, 200], [341, 184], [360, 150], [377, 140], [387, 143]]}" + } + ], + "images": "RH20T_cfg5_task_0023_user_0010_scene_0007_cfg_0005_104422070044#0", + "gt": "[[374, 132], [365, 168], [338, 168], [340, 177], [349, 175], [342, 200], [341, 184], [360, 150], [377, 140], [387, 143]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "77489_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the carrot in the pot, move the banana to the left of the counter, then slide the spout to the right', and now you are performing subtask 'twist the faucet clockwise.'\nFrom start point [112, 78], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[112, 78], [113, 76], [124, 76], [169, 57], [172, 65], [167, 74], [176, 94], [174, 106], [146, 92], [146, 92]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/77489_exterior_image_1_left#262.jpg", + "gt": "[[112, 78], [113, 76], [124, 76], [169, 57], [172, 65], [167, 74], [176, 94], [174, 106], [146, 92], [146, 92]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "79932_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the smaller mug on the counter, fill it with water and place it on the left side of the counter', and now you are performing subtask 'take the smaller mug on the counter, fill it with water and place it on the left side of the counter.'\nWith start location [172, 55], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[172, 55], [195, 62], [188, 81], [150, 80], [137, 110], [121, 97], [118, 109], [88, 106], [34, 141], [69, 110]]}" + } + ], + "images": "79932_exterior_image_1_left#0", + "gt": "[[172, 55], [195, 62], [188, 81], [150, 80], [137, 110], [121, 97], [118, 109], [88, 106], [34, 141], [69, 110]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg2_task_0037_user_0007_scene_0006_cfg_0002_037522062165#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'pick up the third block on the table, transfer the third block from the table to the top of the fourth block, place the third block on the fourth block, pick up the fourth block on the table.'\nYour initial coordinate is [275, 275]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[275, 275], [272, 287], [281, 287], [267, 291], [282, 266], [278, 254], [245, 249], [251, 237], [278, 247], [286, 289]]}" + } + ], + "images": "RH20T_cfg2_task_0037_user_0007_scene_0006_cfg_0002_037522062165#514", + "gt": "[[275, 275], [272, 287], [281, 287], [267, 291], [282, 266], [278, 254], [245, 249], [251, 237], [278, 247], [286, 289]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "90404_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the marker in the cup', and now you are performing subtask 'put the marker in the cup.'\nStarting at [171.0, 51.5], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[171.0, 51.5], [158.0, 51.5], [149.0, 64.5], [147.0, 92.5], [155.0, 110.5], [146.0, 110.5], [140.0, 122.5], [159.0, 84.5], [176.0, 83.5], [167.0, 103.5]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/90404_exterior_image_1_left#0.jpg", + "gt": "[[171.0, 51.5], [158.0, 51.5], [149.0, 64.5], [147.0, 92.5], [155.0, 110.5], [146.0, 110.5], [140.0, 122.5], [159.0, 84.5], [176.0, 83.5], [167.0, 103.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0065_user_0014_scene_0003_cfg_0007_104122064161#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with small Lego blocks for the nth time with n blocks', and now you are performing subtask 'pick up the first Lego block from the right side of the workbench, transfer the first Lego block from the right side of the workbench to the center Lego baseplate, place the first Lego block on the Lego baseplate.'\nStart at [337, 115]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[337, 115], [415, 196], [425, 232], [421, 211], [395, 179], [382, 183], [379, 175], [389, 171], [411, 182], [411, 182]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg7_task_0065_user_0014_scene_0003_cfg_0007_104122064161#0.jpg", + "gt": "[[337, 115], [415, 196], [425, 232], [421, 211], [395, 179], [382, 183], [379, 175], [389, 171], [411, 182], [411, 182]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0072_user_0010_scene_0010_cfg_0001_819112070044#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'drop a coin into the piggy bank', and now you are performing subtask 'pick up the coin from the surface, transfer the coin from the surface to the top of the piggy bank, place the coin into the piggy bank.'\nFrom start point [428, 143], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[428, 143], [420, 127], [402, 153], [372, 145], [341, 173], [346, 187], [389, 148], [421, 139], [412, 149], [412, 149]]}" + } + ], + "images": "RH20T_cfg1_task_0072_user_0010_scene_0010_cfg_0001_819112070044#419", + "gt": "[[428, 143], [420, 127], [402, 153], [372, 145], [341, 173], [346, 187], [389, 148], [421, 139], [412, 149], [412, 149]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0037_user_0007_scene_0010_cfg_0005_104422070044#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'place the third block on top of the first block, pick up the fourth block on the table, transfer the fourth block from the table to the position above the third block, place the fourth block on top of the third block.'\nStarting at [437, 160], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[437, 160], [439, 147], [431, 133], [412, 134], [410, 155], [412, 158], [417, 129], [441, 136], [439, 145], [433, 141]]}" + } + ], + "images": "RH20T_cfg5_task_0037_user_0007_scene_0010_cfg_0005_104422070044#269", + "gt": "[[437, 160], [439, 147], [431, 133], [412, 134], [410, 155], [412, 158], [417, 129], [441, 136], [439, 145], [433, 141]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg3_task_0058_user_0010_scene_0001_cfg_0003_104122062823#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn off the power strips', and now you are performing subtask 'press the button on the first power strip to turn off the power, press the button on the second power strip to turn off the power.'\nBegin at [350, 204] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[350, 204], [350, 194], [355, 191], [381, 189], [378, 189], [383, 196], [375, 199], [375, 203], [382, 192], [400, 186]]}" + } + ], + "images": "RH20T_cfg3_task_0058_user_0010_scene_0001_cfg_0003_104122062823#240", + "gt": "[[350, 204], [350, 194], [355, 191], [381, 189], [378, 189], [383, 196], [375, 199], [375, 203], [382, 192], [400, 186]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0037_user_0007_scene_0010_cfg_0005_037522062165#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'pick up the fifth block on the table, transfer the fifth block from the table to the position of the fourth block, place the fifth block on top of the fourth block.'\nStarting at [255, 148], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[255, 148], [286, 225], [279, 202], [263, 190], [252, 107], [228, 98], [195, 113], [182, 128], [179, 95], [184, 93]]}" + } + ], + "images": "RH20T_cfg5_task_0037_user_0007_scene_0010_cfg_0005_037522062165#819", + "gt": "[[255, 148], [286, 225], [279, 202], [263, 190], [252, 107], [228, 98], [195, 113], [182, 128], [179, 95], [184, 93]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "72158_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the yellow cylinder inside the orange pot', and now you are performing subtask 'put the yellow cylinder inside the orange pot.'\nYour starting position is [225, 0]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[225, 0], [224, 42], [217, 61], [222, 75], [216, 57], [198, 43], [197, 67], [200, 48], [196, 54], [198, 47]]}" + } + ], + "images": "72158_exterior_image_2_left#0", + "gt": "[[225, 0], [224, 42], [217, 61], [222, 75], [216, 57], [198, 43], [197, 67], [200, 48], [196, 54], [198, 47]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "44868_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the yellow and brown bottle to the right and then move the water bottle backward', and now you are performing subtask 'push the water bottle backward.'\nYour starting position is [181, 109]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[181, 109], [178, 106], [160, 129], [179, 146], [184, 158], [179, 162], [179, 152], [175, 156], [170, 151], [171, 129]]}" + } + ], + "images": "44868_exterior_image_1_left#232", + "gt": "[[181, 109], [178, 106], [160, 129], [179, 146], [184, 158], [179, 162], [179, 152], [175, 156], [170, 151], [171, 129]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "89315_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the jumper on the armchair seat', and now you are performing subtask 'place the jumper on the seat of the armchair.'\nFrom start point [92, 84], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[92, 84], [151, 78], [159, 94], [150, 112], [164, 118], [161, 80], [183, 29], [182, 0], [197, 23], [177, 65]]}" + } + ], + "images": "89315_exterior_image_2_left#0", + "gt": "[[92, 84], [151, 78], [159, 94], [150, 112], [164, 118], [161, 80], [183, 29], [182, 0], [197, 23], [177, 65]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "265_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the bowl to the right and put the rubik's cube inside it', and now you are performing subtask 'place the rubik's cube in the bowl.'\nYour initial coordinate is [175, 89]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[175, 89], [174, 83], [183, 80], [173, 89], [180, 107], [171, 94], [179, 82], [185, 81], [186, 89], [176, 66]]}" + } + ], + "images": "265_exterior_image_1_left#364", + "gt": "[[175, 89], [174, 83], [183, 80], [173, 89], [180, 107], [171, 94], [179, 82], [185, 81], [186, 89], [176, 66]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "29621_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'the towel on the folding table', and now you are performing subtask 'the towel on the folding table.'\nFrom start point [205, 118], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[205, 118], [149, 97], [106, 120], [146, 101], [159, 77], [182, 92], [139, 113], [145, 100], [177, 107], [188, 94]]}" + } + ], + "images": "29621_exterior_image_2_left#0", + "gt": "[[205, 118], [149, 97], [106, 120], [146, 101], [159, 77], [182, 92], [139, 113], [145, 100], [177, 107], [188, 94]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "72606_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'slide the towel to the left', and now you are performing subtask 'slide the towel to the left.'\nYour initial coordinate is [147, 0]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[147, 0], [176, 32], [206, 81], [211, 105], [205, 108], [194, 103], [175, 84], [174, 68], [175, 62], [177, 63]]}" + } + ], + "images": "72606_exterior_image_1_left#0", + "gt": "[[147, 0], [176, 32], [206, 81], [211, 105], [205, 108], [194, 103], [175, 84], [174, 68], [175, 62], [177, 63]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "14782_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'uncover the lunch box, pour the sweets inside it into a mug and then put it back on the table', and now you are performing subtask 'place the lunch box back on the table.'\nStart at [182, 86]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[182, 86], [189, 85], [190, 74], [262, 83], [247, 59], [206, 66], [224, 76], [223, 80], [215, 72], [200, 76]]}" + } + ], + "images": "14782_exterior_image_1_left#207", + "gt": "[[182, 86], [189, 85], [190, 74], [262, 83], [247, 59], [206, 66], [224, 76], [223, 80], [215, 72], [200, 76]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "82985_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the lid on the small pot on the table', and now you are performing subtask 'put the lid on the small pot on the table.'\nBegin at [108.0, 59.5] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[108.0, 59.5], [127.0, 68.5], [130.0, 106.5], [165.0, 147.5], [160.0, 155.5], [155.0, 144.5], [136.0, 147.5], [143.0, 152.5], [142.0, 144.5], [142.0, 144.5]]}" + } + ], + "images": "82985_exterior_image_1_left#0", + "gt": "[[108.0, 59.5], [127.0, 68.5], [130.0, 106.5], [165.0, 147.5], [160.0, 155.5], [155.0, 144.5], [136.0, 147.5], [143.0, 152.5], [142.0, 144.5], [142.0, 144.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "89989_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'push the black lamp to the left', and now you are performing subtask 'push the black lamp to the left.'\nThe trajectory starts at [221, 86]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[221, 86], [177, 63], [209, 102], [187, 142], [211, 104], [185, 111], [199, 139], [220, 85], [203, 110], [203, 110]]}" + } + ], + "images": "89989_exterior_image_1_left#0", + "gt": "[[221, 86], [177, 63], [209, 102], [187, 142], [211, 104], [185, 111], [199, 139], [220, 85], [203, 110], [203, 110]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "15165_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'push in the first rod on the foosball table', and now you are performing subtask 'push in the first rod on the foosball table.'\nStart at [186.0, 69.0]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[186.0, 69.0], [199.0, 72.0], [197.0, 73.0], [206.0, 82.0], [208.0, 90.0], [213.0, 86.0], [232.0, 79.0], [224.0, 66.0], [213.0, 57.0], [213.0, 57.0]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/15165_exterior_image_1_left#0.jpg", + "gt": "[[186.0, 69.0], [199.0, 72.0], [197.0, 73.0], [206.0, 82.0], [208.0, 90.0], [213.0, 86.0], [232.0, 79.0], [224.0, 66.0], [213.0, 57.0], [213.0, 57.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0058_user_0007_scene_0004_cfg_0005_037522062165#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn off the power strips', and now you are performing subtask 'press the buttons on a row of four power strips to turn off the power strips.'\nStarting at [289, 152], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[289, 152], [265, 181], [253, 245], [245, 256], [250, 257], [251, 269], [267, 247], [268, 234], [279, 232], [289, 214]]}" + } + ], + "images": "RH20T_cfg5_task_0058_user_0007_scene_0004_cfg_0005_037522062165#0", + "gt": "[[289, 152], [265, 181], [253, 245], [245, 256], [250, 257], [251, 269], [267, 247], [268, 234], [279, 232], [289, 214]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg2_task_0104_user_0007_scene_0007_cfg_0002_104122061850#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'drag the plate back after holding it down', and now you are performing subtask 'drag the plate back after holding it down.'\nYour initial coordinate is [340, 106]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[340, 106], [337, 199], [345, 181], [333, 188], [365, 138], [362, 157], [370, 139], [366, 150], [385, 137], [357, 140]]}" + } + ], + "images": "RH20T_cfg2_task_0104_user_0007_scene_0007_cfg_0002_104122061850#0", + "gt": "[[340, 106], [337, 199], [345, 181], [333, 188], [365, 138], [362, 157], [370, 139], [366, 150], [385, 137], [357, 140]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg2_task_0037_user_0007_scene_0007_cfg_0002_105422061350#TrajectoryPrediction_Task#8", + "task": "TrajectoryPrediction_Task", + "p_index": 8, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'pick up the fifth block from the surface, transfer the fifth block from the surface to the top of the fourth block, place the fifth block on top of the fourth block.'\nYour initial coordinate is [267, 162]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[267, 162], [263, 169], [270, 177], [276, 162], [288, 158], [326, 165], [330, 173], [321, 172], [326, 157], [343, 150]]}" + } + ], + "images": "RH20T_cfg2_task_0037_user_0007_scene_0007_cfg_0002_105422061350#824", + "gt": "[[267, 162], [263, 169], [270, 177], [276, 162], [288, 158], [326, 165], [330, 173], [321, 172], [326, 157], [343, 150]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "20237_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stir the contents in the green bowl using a spatula', and now you are performing subtask 'stir the contents in the green bowl using a spatula.'\nYour initial coordinate is [308, 32]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[308, 32], [174, 107], [168, 120], [183, 104], [188, 114], [171, 103], [166, 109], [166, 97], [202, 90], [208, 76]]}" + } + ], + "images": "20237_exterior_image_1_left#0", + "gt": "[[308, 32], [174, 107], [168, 120], [183, 104], [188, 114], [171, 103], [166, 109], [166, 97], [202, 90], [208, 76]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "2362_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the wallet from the table and put it in the black bag', and now you are performing subtask 'pick up the wallet from the table.'\nStarting at [222.0, 132.5], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[222.0, 132.5], [222.0, 126.5], [223.0, 133.5], [196.0, 126.5], [192.0, 134.5], [226.0, 133.5], [223.0, 138.5], [211.0, 137.5], [216.0, 133.5], [210.0, 121.5]]}" + } + ], + "images": "2362_exterior_image_1_left#202", + "gt": "[[222.0, 132.5], [222.0, 126.5], [223.0, 133.5], [196.0, 126.5], [192.0, 134.5], [226.0, 133.5], [223.0, 138.5], [211.0, 137.5], [216.0, 133.5], [210.0, 121.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "43469_exterior_image_1_left#TrajectoryPrediction_Task#10", + "task": "TrajectoryPrediction_Task", + "p_index": 10, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'fold the sweatshirt twice', and now you are performing subtask 'fold the sweatshirt in half again.'\nWith start location [192, 47], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[192, 47], [204, 62], [202, 76], [205, 61], [221, 54], [213, 56], [205, 39], [170, 57], [181, 73], [179, 61]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/43469_exterior_image_1_left#371.jpg", + "gt": "[[192, 47], [204, 62], [202, 76], [205, 61], [221, 54], [213, 56], [205, 39], [170, 57], [181, 73], [179, 61]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "17544_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close the top drawer on the right', and now you are performing subtask 'close the top drawer on the right.'\nWith start location [132, 134], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[132, 134], [165, 104], [167, 98], [167, 89], [170, 84], [182, 85], [198, 81], [203, 82], [202, 83], [202, 83]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/17544_exterior_image_2_left#0.jpg", + "gt": "[[132, 134], [165, 104], [167, 98], [167, 89], [170, 84], [182, 85], [198, 81], [203, 82], [202, 83], [202, 83]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg3_task_0091_user_0010_scene_0004_cfg_0003_104122062823#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the green button, the basketball toy, and the football toy from the black box to the pink box', and now you are performing subtask 'transfer the basketball toy from the black box to above the pink box, place the basketball toy in the pink box, pick up the football toy from the black box.'\nYour initial coordinate is [194, 26]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[194, 26], [200, 35], [242, 20], [301, 20], [337, 44], [323, 89], [314, 87], [327, 80], [315, 103], [323, 83]]}" + } + ], + "images": "RH20T_cfg3_task_0091_user_0010_scene_0004_cfg_0003_104122062823#398", + "gt": "[[194, 26], [200, 35], [242, 20], [301, 20], [337, 44], [323, 89], [314, 87], [327, 80], [315, 103], [323, 83]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0029_user_0014_scene_0003_cfg_0006_104122064161#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'grasp the handle and open the drawer', and now you are performing subtask 'grasp the handle and open the drawer.'\nStarting at [338, 110], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[338, 110], [344, 103], [353, 73], [364, 68], [366, 62], [374, 86], [348, 119], [337, 144], [333, 146], [329, 136]]}" + } + ], + "images": "RH20T_cfg6_task_0029_user_0014_scene_0003_cfg_0006_104122064161#0", + "gt": "[[338, 110], [344, 103], [353, 73], [364, 68], [366, 62], [374, 86], [348, 119], [337, 144], [333, 146], [329, 136]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "63511_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unravel the charger', and now you are performing subtask 'grab the charger on the tabletop.'\nFrom start point [210, 3], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[210, 3], [239, 50], [219, 56], [174, 97], [171, 47], [167, 60], [184, 62], [186, 70], [182, 68], [181, 72]]}" + } + ], + "images": "63511_exterior_image_1_left#0", + "gt": "[[210, 3], [239, 50], [219, 56], [174, 97], [171, 47], [167, 60], [184, 62], [186, 70], [182, 68], [181, 72]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "25326_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close the lid on the clear container on the left then turn on the extension cable', and now you are performing subtask 'press the button on the extension cord to turn on the power.'\nStarting at [205, 99], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[205, 99], [205, 96], [206, 98], [210, 92], [214, 92], [208, 92], [207, 101], [201, 67], [206, 21], [209, 20]]}" + } + ], + "images": "25326_exterior_image_1_left#237", + "gt": "[[205, 99], [205, 96], [206, 98], [210, 92], [214, 92], [208, 92], [207, 101], [201, 67], [206, 21], [209, 20]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg2_task_0004_user_0006_scene_0003_cfg_0002_036422060215#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the small block on the left and move it to the right', and now you are performing subtask 'pick up the small block on the left and move it to the right.'\nYou start from [349, 254]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[349, 254], [402, 219], [424, 221], [444, 256], [420, 291], [435, 269], [407, 274], [391, 297], [409, 272], [403, 267]]}" + } + ], + "images": "RH20T_cfg2_task_0004_user_0006_scene_0003_cfg_0002_036422060215#0", + "gt": "[[349, 254], [402, 219], [424, 221], [444, 256], [420, 291], [435, 269], [407, 274], [391, 297], [409, 272], [403, 267]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "55742_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the white towel on the black object on top of the table', and now you are performing subtask 'place the white towel on the black object on the table.'\nStart at [145, 58]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[145, 58], [151, 53], [159, 61], [138, 72], [148, 84], [146, 89], [126, 27], [153, 43], [154, 48], [149, 40]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/55742_exterior_image_1_left#193.jpg", + "gt": "[[145, 58], [151, 53], [159, 61], [138, 72], [148, 84], [146, 89], [126, 27], [153, 43], [154, 48], [149, 40]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0038_user_0014_scene_0004_cfg_0001_750612070853#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the cup', and now you are performing subtask 'pick up the cup.'\nStart at [382, 78]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[382, 78], [413, 76], [536, 113], [601, 157], [611, 171], [603, 199], [592, 166], [516, 67], [496, 29], [493, 0]]}" + } + ], + "images": "RH20T_cfg1_task_0038_user_0014_scene_0004_cfg_0001_750612070853#0", + "gt": "[[382, 78], [413, 76], [536, 113], [601, 157], [611, 171], [603, 199], [592, 166], [516, 67], [496, 29], [493, 0]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0123_user_0010_scene_0004_cfg_0005_104422070044#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the knife on the knife rack', and now you are performing subtask 'pick up the knife on the table, transfer the knife from the table to the knife rack, place the knife on the knife rack.'\nWith start location [375, 134], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[375, 134], [372, 145], [380, 172], [392, 141], [401, 136], [413, 139], [421, 148], [422, 161], [427, 159], [414, 143]]}" + } + ], + "images": "RH20T_cfg5_task_0123_user_0010_scene_0004_cfg_0005_104422070044#0", + "gt": "[[375, 134], [372, 145], [380, 172], [392, 141], [401, 136], [413, 139], [421, 148], [422, 161], [427, 159], [414, 143]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "49121_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the marker on the table', and now you are performing subtask 'put the marker on the table.'\nYou start from [201, 43]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[201, 43], [170, 58], [173, 77], [171, 109], [174, 99], [169, 92], [163, 102], [136, 117], [132, 101], [141, 85]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/49121_exterior_image_2_left#0.jpg", + "gt": "[[201, 43], [170, 58], [173, 77], [171, 109], [174, 99], [169, 92], [163, 102], [136, 117], [132, 101], [141, 85]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0037_user_0007_scene_0004_cfg_0005_104122061850#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'pick up the first block from the surface, place the first block on the vertical stack on the surface, pick up the second block from the surface.'\nStart at [305, 50]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[305, 50], [308, 49], [317, 67], [318, 113], [328, 148], [318, 174], [323, 193], [321, 112], [331, 90], [341, 113]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0037_user_0007_scene_0004_cfg_0005_104122061850#0.jpg", + "gt": "[[305, 50], [308, 49], [317, 67], [318, 113], [328, 148], [318, 174], [323, 193], [321, 112], [331, 90], [341, 113]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0066_user_0014_scene_0008_cfg_0001_750612070851#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'putting a portion of the Lego blocks on the Lego baseplate', and now you are performing subtask 'insert the purple Lego brick into the Lego base, pick up the yellow Lego brick from the table, transfer the yellow Lego brick from the table to the Lego base, insert the yellow Lego brick into the Lego base.'\nWith start location [253, 207], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[253, 207], [238, 206], [208, 235], [217, 304], [226, 313], [208, 297], [244, 219], [291, 178], [301, 186], [301, 214]]}" + } + ], + "images": "RH20T_cfg1_task_0066_user_0014_scene_0008_cfg_0001_750612070851#251", + "gt": "[[253, 207], [238, 206], [208, 235], [217, 304], [226, 313], [208, 297], [244, 219], [291, 178], [301, 186], [301, 214]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0075_user_0007_scene_0004_cfg_0005_104122061850#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'finish setting up the starting position of the chessboard that is almost arranged', and now you are performing subtask 'place the black chess piece next to the black chess piece on the chessboard, pick up the white chess piece on the table, transfer the white chess piece from the table to the white chess piece on the chessboard, place the white chess piece next to the white chess piece on the chessboard.'\nYou begin at [336, 107]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[336, 107], [413, 128], [426, 135], [439, 155], [440, 149], [409, 142], [408, 138], [418, 129], [440, 133], [440, 133]]}" + } + ], + "images": "RH20T_cfg5_task_0075_user_0007_scene_0004_cfg_0005_104122061850#433", + "gt": "[[336, 107], [413, 128], [426, 135], [439, 155], [440, 149], [409, 142], [408, 138], [418, 129], [440, 133], [440, 133]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "20823_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the banana inside the first drawer from the right then close the drawer', and now you are performing subtask 'place the banana inside the first drawer on the right.'\nYour initial coordinate is [171, 9]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[171, 9], [150, 68], [197, 103], [214, 97], [212, 82], [206, 88], [215, 93], [189, 84], [185, 92], [197, 97]]}" + } + ], + "images": "20823_exterior_image_2_left#0", + "gt": "[[171, 9], [150, 68], [197, 103], [214, 97], [212, 82], [206, 88], [215, 93], [189, 84], [185, 92], [197, 97]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0132_user_0020_scene_0002_cfg_0006_104122064161#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks into a cross shape', and now you are performing subtask 'pick up the fourth block from the left side, place the fourth block on top of the first and second blocks to complete the cross shape.'\nThe trajectory starts at [424, 143]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[424, 143], [429, 138], [423, 155], [411, 175], [428, 155], [427, 133], [410, 131], [378, 138], [350, 133], [351, 141]]}" + } + ], + "images": "RH20T_cfg6_task_0132_user_0020_scene_0002_cfg_0006_104122064161#880", + "gt": "[[424, 143], [429, 138], [423, 155], [411, 175], [428, 155], [427, 133], [410, 131], [378, 138], [350, 133], [351, 141]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0066_user_0016_scene_0001_cfg_0004_104122062295#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with large megabloks for the nth time with n blocks', and now you are performing subtask 'place the large Megablok in the building area, press the large Megablok.'\nBegin at [133, 89] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[133, 89], [133, 102], [124, 109], [137, 69], [132, 84], [137, 89], [125, 75], [128, 59], [139, 50], [149, 60]]}" + } + ], + "images": "RH20T_cfg4_task_0066_user_0016_scene_0001_cfg_0004_104122062295#156", + "gt": "[[133, 89], [133, 102], [124, 109], [137, 69], [132, 84], [137, 89], [125, 75], [128, 59], [139, 50], [149, 60]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0041_user_0007_scene_0006_cfg_0005_104122063678#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'clean the tabletop with a sponge', and now you are performing subtask 'pick up the sponge on the tabletop, slide the sponge on the tabletop to clean the surface.'\nYour initial coordinate is [323, 132]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[323, 132], [317, 151], [346, 172], [345, 179], [337, 180], [341, 174], [346, 186], [345, 218], [332, 238], [326, 223]]}" + } + ], + "images": "RH20T_cfg5_task_0041_user_0007_scene_0006_cfg_0005_104122063678#0", + "gt": "[[323, 132], [317, 151], [346, 172], [345, 179], [337, 180], [341, 174], [346, 186], [345, 218], [332, 238], [326, 223]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "13967_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the lid and pick up the object from the pot and put it in the white bowl', and now you are performing subtask 'pick up the object from the pot.'\nBegin at [106.5, 62.5] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[106.5, 62.5], [112.5, 56.5], [162.5, 62.5], [172.5, 69.5], [174.5, 100.5], [177.5, 87.5], [187.5, 84.5], [217.5, 105.5], [177.5, 75.5], [177.5, 93.5]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/13967_exterior_image_1_left#0.jpg", + "gt": "[[106.5, 62.5], [112.5, 56.5], [162.5, 62.5], [172.5, 69.5], [174.5, 100.5], [177.5, 87.5], [187.5, 84.5], [217.5, 105.5], [177.5, 75.5], [177.5, 93.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0110_user_0007_scene_0009_cfg_0004_104122063550#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the pencil out from the pencil sharpener', and now you are performing subtask 'take the pencil out from the pencil sharpener.'\nStart at [275, 185]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[275, 185], [293, 184], [296, 167], [266, 158], [283, 172], [248, 204], [242, 215], [248, 228], [271, 218], [278, 190]]}" + } + ], + "images": "RH20T_cfg4_task_0110_user_0007_scene_0009_cfg_0004_104122063550#0", + "gt": "[[275, 185], [293, 184], [296, 167], [266, 158], [283, 172], [248, 204], [242, 215], [248, 228], [271, 218], [278, 190]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "90987_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put a black pen on top of the table, then move another black pen and place it into the white cup, then, open the grey towel on the table', and now you are performing subtask 'fold the grey towel underneath the table.'\nThe trajectory starts at [198, 68]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[198, 68], [190, 70], [187, 113], [209, 118], [227, 138], [228, 128], [193, 96], [183, 89], [163, 90], [161, 72]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/90987_exterior_image_1_left#241.jpg", + "gt": "[[198, 68], [190, 70], [187, 113], [209, 118], [227, 138], [228, 128], [193, 96], [183, 89], [163, 90], [161, 72]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "45833_exterior_image_2_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the door of the top shelf', and now you are performing subtask 'pull the handle of the top shelf door to open the top shelf door.'\nYour starting position is [195, 43]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[195, 43], [180, 55], [175, 51], [172, 60], [179, 56], [176, 52], [218, 52], [213, 51], [220, 23], [201, 22]]}" + } + ], + "images": "45833_exterior_image_2_left#221", + "gt": "[[195, 43], [180, 55], [175, 51], [172, 60], [179, 56], [176, 52], [218, 52], [213, 51], [220, 23], [201, 22]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0065_user_0010_scene_0005_cfg_0001_038522062547#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with small Lego blocks for the nth time with n blocks', and now you are performing subtask 'place the white small Lego block on the black small Lego block, press the white small Lego block, press the white small Lego block, did not pick up the blue small Lego block, pick up the blue small Lego block from the desktop, transfer the blue small Lego block from the desktop to the white small Lego block, place the blue small Lego block on the white small Lego block.'\nFrom start point [416, 185], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[416, 185], [401, 186], [405, 178], [415, 185], [434, 162], [459, 166], [439, 148], [447, 163], [464, 162], [416, 186]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0065_user_0010_scene_0005_cfg_0001_038522062547#1078.jpg", + "gt": "[[416, 185], [401, 186], [405, 178], [415, 185], [434, 162], [459, 166], [439, 148], [447, 163], [464, 162], [416, 186]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "48888_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'after opening and then closing the flask lid, and then opening it again', and now you are performing subtask 'press the flask lid open.'\nYou start from [234, 85]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[234, 85], [231, 89], [225, 75], [217, 72], [214, 82], [224, 92], [211, 80], [204, 65], [208, 65], [226, 80]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/48888_exterior_image_1_left#185.jpg", + "gt": "[[234, 85], [231, 89], [225, 75], [217, 72], [214, 82], [224, 92], [211, 80], [204, 65], [208, 65], [226, 80]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0016_user_0014_scene_0001_cfg_0001_035622060973#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'hit the pool ball', and now you are performing subtask 'pick up the pool ball from the surface.'\nYour starting position is [292, 297]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[292, 297], [290, 295], [289, 300], [297, 297], [306, 302], [311, 302], [315, 297], [304, 274], [301, 260], [298, 261]]}" + } + ], + "images": "RH20T_cfg1_task_0016_user_0014_scene_0001_cfg_0001_035622060973#288", + "gt": "[[292, 297], [290, 295], [289, 300], [297, 297], [306, 302], [311, 302], [315, 297], [304, 274], [301, 260], [298, 261]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "18069_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the carrot plush toy and put it on the counter', and now you are performing subtask 'place the carrot plush toy on the counter.'\nWith start location [120, 80], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[120, 80], [126, 83], [116, 75], [126, 80], [136, 91], [137, 97], [114, 83], [107, 75], [111, 75], [110, 78]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/18069_exterior_image_1_left#183.jpg", + "gt": "[[120, 80], [126, 83], [116, 75], [126, 80], [136, 91], [137, 97], [114, 83], [107, 75], [111, 75], [110, 78]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0061_user_0001_scene_0006_cfg_0001_038522063145#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take everything out of the gift box', and now you are performing subtask 'pick up the small block from the gift box, transfer the small block from the gift box to the table, place the small block on the table.'\nYou start from [444, 129]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[444, 129], [421, 131], [440, 122], [441, 134], [432, 139], [450, 115], [454, 84], [494, 114], [513, 151], [482, 107]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0061_user_0001_scene_0006_cfg_0001_038522063145#234.jpg", + "gt": "[[444, 129], [421, 131], [440, 122], [441, 134], [432, 139], [450, 115], [454, 84], [494, 114], [513, 151], [482, 107]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg2_task_0037_user_0007_scene_0006_cfg_0002_104122063678#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'pick up the first block on the table, transfer the first block from the table to the top of the second block, place the first block on the second block.'\nYour starting position is [289, 199]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[289, 199], [359, 229], [360, 237], [382, 232], [383, 246], [372, 263], [374, 242], [366, 229], [345, 213], [343, 221]]}" + } + ], + "images": "RH20T_cfg2_task_0037_user_0007_scene_0006_cfg_0002_104122063678#0", + "gt": "[[289, 199], [359, 229], [360, 237], [382, 232], [383, 246], [372, 263], [374, 242], [366, 229], [345, 213], [343, 221]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0037_user_0016_scene_0009_cfg_0001_035622060973#TrajectoryPrediction_Task#8", + "task": "TrajectoryPrediction_Task", + "p_index": 8, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'pick up the fourth block from the surface, transfer the fourth block from the desktop to the second position above the third block, place the fourth block on top of the third block.'\nStarting at [186, 184], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[186, 184], [185, 205], [199, 235], [191, 210], [225, 172], [223, 133], [218, 120], [211, 123], [215, 107], [215, 107]]}" + } + ], + "images": "RH20T_cfg1_task_0037_user_0016_scene_0009_cfg_0001_035622060973#584", + "gt": "[[186, 184], [185, 205], [199, 235], [191, 210], [225, 172], [223, 133], [218, 120], [211, 123], [215, 107], [215, 107]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "19018_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the pillow and lean it against the handle of the couch, pick up the second pillow and lean it against the first pillow', and now you are performing subtask 'pick up the second pillow from the couch.'\nYou begin at [215, 75]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[215, 75], [178, 108], [180, 120], [185, 101], [213, 96], [188, 114], [222, 107], [203, 123], [231, 90], [142, 132]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/19018_exterior_image_1_left#0.jpg", + "gt": "[[215, 75], [178, 108], [180, 120], [185, 101], [213, 96], [188, 114], [222, 107], [203, 123], [231, 90], [142, 132]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "66066_exterior_image_2_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the fabric', and now you are performing subtask 'slide the fabric on the tabletop.'\nWith start location [228, 91], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[228, 91], [217, 82], [206, 78], [200, 81], [208, 87], [212, 120], [221, 127], [232, 125], [240, 95], [240, 83]]}" + } + ], + "images": "66066_exterior_image_2_left#122", + "gt": "[[228, 91], [217, 82], [206, 78], [200, 81], [208, 87], [212, 120], [221, 127], [232, 125], [240, 95], [240, 83]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0032_user_0016_scene_0002_cfg_0004_038522062288#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'slide the outer casing onto the gift box', and now you are performing subtask 'pick up the outer casing from the table, slide the outer casing onto the gift box.'\nStart at [295, 243]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[295, 243], [298, 242], [299, 245], [295, 251], [279, 248], [272, 240], [245, 222], [240, 213], [244, 207], [244, 207]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg4_task_0032_user_0016_scene_0002_cfg_0004_038522062288#105.jpg", + "gt": "[[295, 243], [298, 242], [299, 245], [295, 251], [279, 248], [272, 240], [245, 222], [240, 213], [244, 207], [244, 207]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "70311_exterior_image_2_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the white mug on the red plate and then put it back on the table', and now you are performing subtask 'pick up the white mug on the red plate.'\nWith start location [134, 81], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[134, 81], [135, 68], [125, 85], [116, 75], [132, 73], [142, 77], [144, 74], [112, 77], [148, 93], [139, 77]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/70311_exterior_image_2_left#257.jpg", + "gt": "[[134, 81], [135, 68], [125, 85], [116, 75], [132, 73], [142, 77], [144, 74], [112, 77], [148, 93], [139, 77]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "13247_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'rotate the green bowl clockwise', and now you are performing subtask 'rotate the green bowl clockwise.'\nBegin at [238, 70] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[238, 70], [223, 86], [161, 91], [153, 145], [142, 141], [154, 134], [164, 143], [168, 131], [178, 145], [168, 145]]}" + } + ], + "images": "13247_exterior_image_1_left#0", + "gt": "[[238, 70], [223, 86], [161, 91], [153, 145], [142, 141], [154, 134], [164, 143], [168, 131], [178, 145], [168, 145]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "5673_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the cup and pour its contents into the white bowl', and now you are performing subtask 'pick up the cup and pour its contents into the white bowl.'\nThe trajectory starts at [198, 100]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[198, 100], [173, 103], [166, 106], [165, 113], [167, 104], [151, 117], [148, 116], [152, 109], [154, 107], [155, 109]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/5673_exterior_image_1_left#0.jpg", + "gt": "[[198, 100], [173, 103], [166, 106], [165, 113], [167, 104], [151, 117], [148, 116], [152, 109], [154, 107], [155, 109]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0034_user_0016_scene_0009_cfg_0004_104122062823#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the squares into a pyramid shape', and now you are performing subtask 'pick up the first block on the cardboard.'\nStarting at [290, 0], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[290, 0], [311, 0], [265, 9], [251, 23], [256, 31], [357, 30], [340, 43], [431, 71], [417, 137], [391, 95]]}" + } + ], + "images": "RH20T_cfg4_task_0034_user_0016_scene_0009_cfg_0004_104122062823#0", + "gt": "[[290, 0], [311, 0], [265, 9], [251, 23], [256, 31], [357, 30], [340, 43], [431, 71], [417, 137], [391, 95]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg3_task_0058_user_0010_scene_0006_cfg_0003_104122062823#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn off the power strips', and now you are performing subtask 'press the first button of the power strip, press the second button of the power strip.'\nYour initial coordinate is [149, 58]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[149, 58], [146, 56], [148, 59], [148, 63], [147, 63], [147, 64], [144, 55], [140, 49], [136, 46], [136, 46]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg3_task_0058_user_0010_scene_0006_cfg_0003_104122062823#168.jpg", + "gt": "[[149, 58], [146, 56], [148, 59], [148, 63], [147, 63], [147, 64], [144, 55], [140, 49], [136, 46], [136, 46]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "74887_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'throw the building block tower onto the table, then push the green building blocks in the tower to the edge of the table', and now you are performing subtask 'pick up the block tower on the right side of the table.'\nBegin at [93, 69] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[93, 69], [120, 69], [130, 75], [132, 89], [140, 94], [143, 87], [142, 91], [128, 102], [123, 97], [116, 100]]}" + } + ], + "images": "74887_exterior_image_2_left#0", + "gt": "[[93, 69], [120, 69], [130, 75], [132, 89], [140, 94], [143, 87], [142, 91], [128, 102], [123, 97], [116, 100]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "89978_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'arrange the water bottles in a straight line', and now you are performing subtask 'place the second bottle of water in the specified position in a straight line.'\nStarting at [163, 121], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[163, 121], [156, 122], [166, 126], [167, 151], [172, 145], [189, 149], [192, 157], [187, 159], [180, 150], [180, 150]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/89978_exterior_image_1_left#0.jpg", + "gt": "[[163, 121], [156, 122], [166, 126], [167, 151], [172, 145], [189, 149], [192, 157], [187, 159], [180, 150], [180, 150]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "74617_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the fries plush toy and put it on the plate', and now you are performing subtask 'place the fries toy on the plate.'\nYour initial coordinate is [243, 59]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[243, 59], [197, 51], [189, 54], [177, 67], [180, 79], [167, 105], [167, 115], [176, 108], [157, 122], [157, 103]]}" + } + ], + "images": "74617_exterior_image_1_left#0", + "gt": "[[243, 59], [197, 51], [189, 54], [177, 67], [180, 79], [167, 105], [167, 115], [176, 108], [157, 122], [157, 103]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "26768_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the cube in the sink', and now you are performing subtask 'put the cube in the sink.'\nStarting at [145, 7], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[145, 7], [171, 94], [178, 109], [185, 115], [189, 114], [158, 112], [144, 107], [143, 95], [147, 87], [153, 88]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/26768_exterior_image_1_left#0.jpg", + "gt": "[[145, 7], [171, 94], [178, 109], [185, 115], [189, 114], [158, 112], [144, 107], [143, 95], [147, 87], [153, 88]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "10503_exterior_image_2_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the white towel then set it down again', and now you are performing subtask 'press the white towel.'\nStart at [142, 94]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[142, 94], [151, 57], [139, 74], [133, 108], [129, 103], [137, 104], [134, 109], [140, 114], [133, 90], [129, 89]]}" + } + ], + "images": "10503_exterior_image_2_left#172", + "gt": "[[142, 94], [151, 57], [139, 74], [133, 108], [129, 103], [137, 104], [134, 109], [140, 114], [133, 90], [129, 89]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "27910_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the orange cube on the green cube', and now you are performing subtask 'put the orange cube on the green cube.'\nBegin at [212, 65] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[212, 65], [190, 68], [184, 71], [179, 81], [176, 93], [168, 104], [170, 96], [176, 85], [179, 84], [186, 90]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/27910_exterior_image_1_left#0.jpg", + "gt": "[[212, 65], [190, 68], [184, 71], [179, 81], [176, 93], [168, 104], [170, 96], [176, 85], [179, 84], [186, 90]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "55751_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the black ladle out of the glass jar', and now you are performing subtask 'take the black ladle out of the glass jar.'\nBegin at [223, 0] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[223, 0], [182, 38], [174, 68], [159, 9], [179, 14], [161, 93], [177, 87], [176, 120], [154, 106], [152, 76]]}" + } + ], + "images": "55751_exterior_image_1_left#0", + "gt": "[[223, 0], [182, 38], [174, 68], [159, 9], [179, 14], [161, 93], [177, 87], [176, 120], [154, 106], [152, 76]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "84561_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the brown block in the plate', and now you are performing subtask 'put the brown block in the plate.'\nThe trajectory starts at [74.5, 2.0]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[74.5, 2.0], [95.5, 19.0], [87.5, 17.0], [90.5, 21.0], [151.5, 90.0], [131.5, 81.0], [124.5, 89.0], [124.5, 99.0], [111.5, 81.0], [116.5, 84.0]]}" + } + ], + "images": "84561_exterior_image_1_left#0", + "gt": "[[74.5, 2.0], [95.5, 19.0], [87.5, 17.0], [90.5, 21.0], [151.5, 90.0], [131.5, 81.0], [124.5, 89.0], [124.5, 99.0], [111.5, 81.0], [116.5, 84.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0037_user_0014_scene_0009_cfg_0007_104122064161#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'pick up the fifth block from the desktop, transfer the block from the desktop to the fourth block, place the block on the fourth block.'\nStart at [332, 114]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[332, 114], [346, 85], [372, 72], [386, 83], [386, 96], [386, 90], [373, 75], [368, 89], [364, 85], [364, 85]]}" + } + ], + "images": "RH20T_cfg7_task_0037_user_0014_scene_0009_cfg_0007_104122064161#345", + "gt": "[[332, 114], [346, 85], [372, 72], [386, 83], [386, 96], [386, 90], [373, 75], [368, 89], [364, 85], [364, 85]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0038_user_0016_scene_0009_cfg_0001_035622060973#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the cup', and now you are performing subtask 'pick up the cup.'\nYour starting position is [247, 129]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[247, 129], [250, 129], [246, 127], [228, 131], [228, 137], [230, 139], [226, 146], [228, 149], [226, 127], [228, 115]]}" + } + ], + "images": "RH20T_cfg1_task_0038_user_0016_scene_0009_cfg_0001_035622060973#0", + "gt": "[[247, 129], [250, 129], [246, 127], [228, 131], [228, 137], [230, 139], [226, 146], [228, 149], [226, 127], [228, 115]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "57005_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the marker from beneath the table to above the table', and now you are performing subtask 'move the marker from beneath the table to above the table.'\nYou start from [221.5, 1.0]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[221.5, 1.0], [280.5, 39.0], [264.5, 38.0], [285.5, 69.0], [272.5, 75.0], [274.5, 86.0], [264.5, 92.0], [247.5, 76.0], [233.5, 77.0], [234.5, 61.0]]}" + } + ], + "images": "57005_exterior_image_1_left#0", + "gt": "[[221.5, 1.0], [280.5, 39.0], [264.5, 38.0], [285.5, 69.0], [272.5, 75.0], [274.5, 86.0], [264.5, 92.0], [247.5, 76.0], [233.5, 77.0], [234.5, 61.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0029_user_0016_scene_0009_cfg_0004_104122062823#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'grasp the handle and open the drawer', and now you are performing subtask 'grasp the handle and open the drawer.'\nThe trajectory starts at [290, 0]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[290, 0], [324, 2], [316, 6], [321, 8], [312, 32], [339, 85], [336, 90], [263, 49], [254, 0], [254, 0]]}" + } + ], + "images": "RH20T_cfg4_task_0029_user_0016_scene_0009_cfg_0004_104122062823#0", + "gt": "[[290, 0], [324, 2], [316, 6], [321, 8], [312, 32], [339, 85], [336, 90], [263, 49], [254, 0], [254, 0]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0058_user_0014_scene_0008_cfg_0004_038522062288#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn off the power strips', and now you are performing subtask 'press the second button of the power socket to turn it off, press the third button of the power socket to turn it off.'\nYou start from [316, 84]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[316, 84], [306, 82], [305, 83], [306, 86], [302, 81], [308, 86], [301, 76], [298, 74], [289, 74], [285, 72]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg4_task_0058_user_0014_scene_0008_cfg_0004_038522062288#144.jpg", + "gt": "[[316, 84], [306, 82], [305, 83], [306, 86], [302, 81], [308, 86], [301, 76], [298, 74], [289, 74], [285, 72]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg3_task_0057_user_0010_scene_0006_cfg_0003_104122062823#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn on the power strips', and now you are performing subtask 'press the button on the left power strip.'\nStart at [120, 52]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[120, 52], [126, 53], [124, 59], [108, 43], [90, 12], [91, 6], [102, 0], [181, 0], [195, 29], [186, 29]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg3_task_0057_user_0010_scene_0006_cfg_0003_104122062823#144.jpg", + "gt": "[[120, 52], [126, 53], [124, 59], [108, 43], [90, 12], [91, 6], [102, 0], [181, 0], [195, 29], [186, 29]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0050_user_0020_scene_0008_cfg_0007_104122060811#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the plate on the bowl rack', and now you are performing subtask 'put the plate on the bowl rack.'\nStarting at [387, 130], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[387, 130], [364, 133], [373, 126], [369, 117], [347, 107], [322, 106], [316, 118], [344, 105], [364, 122], [365, 116]]}" + } + ], + "images": "RH20T_cfg7_task_0050_user_0020_scene_0008_cfg_0007_104122060811#0", + "gt": "[[387, 130], [364, 133], [373, 126], [369, 117], [347, 107], [322, 106], [316, 118], [344, 105], [364, 122], [365, 116]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0066_user_0014_scene_0005_cfg_0007_104122061018#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with large Megabloks for the nth time with n blocks', and now you are performing subtask 'pick up the block on the flat surface, transfer the block from the flat surface to the block board, place the block on the block board.'\nStart at [244, 105]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[244, 105], [219, 123], [220, 126], [234, 101], [248, 89], [310, 86], [336, 104], [337, 122], [328, 108], [301, 95]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg7_task_0066_user_0014_scene_0005_cfg_0007_104122061018#234.jpg", + "gt": "[[244, 105], [219, 123], [220, 126], [234, 101], [248, 89], [310, 86], [336, 104], [337, 122], [328, 108], [301, 95]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "73153_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn on the main adapter switch', and now you are performing subtask 'press the switch on the main adapter.'\nFrom start point [198, 88], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[198, 88], [202, 93], [206, 93], [207, 95], [211, 92], [180, 91], [177, 87], [177, 84], [178, 83], [178, 86]]}" + } + ], + "images": "73153_exterior_image_1_left#152", + "gt": "[[198, 88], [202, 93], [206, 93], [207, 95], [211, 92], [180, 91], [177, 87], [177, 84], [178, 83], [178, 86]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0032_user_0016_scene_0006_cfg_0004_104422070011#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'slide the outer casing onto the gift box', and now you are performing subtask 'push the gift box lid on the desktop.'\nBegin at [329, 142] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[329, 142], [338, 154], [382, 120], [376, 83], [358, 92], [381, 134], [334, 130], [327, 160], [314, 148], [310, 159]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg4_task_0032_user_0016_scene_0006_cfg_0004_104422070011#138.jpg", + "gt": "[[329, 142], [338, 154], [382, 120], [376, 83], [358, 92], [381, 134], [334, 130], [327, 160], [314, 148], [310, 159]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "59865_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the cob of maize to the left', and now you are performing subtask 'move the cob of maize to the left.'\nWith start location [205, 3], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[205, 3], [233, 45], [227, 102], [223, 86], [207, 72], [181, 66], [173, 71], [171, 79], [167, 66], [167, 66]]}" + } + ], + "images": "59865_exterior_image_1_left#0", + "gt": "[[205, 3], [233, 45], [227, 102], [223, 86], [207, 72], [181, 66], [173, 71], [171, 79], [167, 66], [167, 66]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0020_user_0016_scene_0002_cfg_0004_104122062823#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn on the desk lamp by pressing the button', and now you are performing subtask 'press the button on the desk lamp to turn on the light.'\nYour starting position is [243, 0]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[243, 0], [190, 0], [203, 0], [184, 14], [191, 36], [181, 10], [194, 32], [190, 60], [158, 85], [160, 66]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg4_task_0020_user_0016_scene_0002_cfg_0004_104122062823#0.jpg", + "gt": "[[243, 0], [190, 0], [203, 0], [184, 14], [191, 36], [181, 10], [194, 32], [190, 60], [158, 85], [160, 66]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "68845_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the marker out of the pot and put it on the table', and now you are performing subtask 'take the marker out of the pot and put it on the table.'\nStarting at [166.0, 42.0], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[166.0, 42.0], [172.0, 67.0], [165.0, 87.0], [173.0, 64.0], [190.0, 53.0], [200.0, 54.0], [207.0, 66.0], [207.0, 105.0], [205.0, 83.0], [211.0, 84.0]]}" + } + ], + "images": "68845_exterior_image_1_left#0", + "gt": "[[166.0, 42.0], [172.0, 67.0], [165.0, 87.0], [173.0, 64.0], [190.0, 53.0], [200.0, 54.0], [207.0, 66.0], [207.0, 105.0], [205.0, 83.0], [211.0, 84.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "6770_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take out all the cloves of garlic in the bowl and put them on the table', and now you are performing subtask 'place the garlic on the table.'\nThe trajectory starts at [202, 142]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[202, 142], [206, 118], [221, 140], [207, 117], [195, 125], [193, 145], [204, 120], [211, 117], [210, 131], [211, 116]]}" + } + ], + "images": "6770_exterior_image_1_left#360", + "gt": "[[202, 142], [206, 118], [221, 140], [207, 117], [195, 125], [193, 145], [204, 120], [211, 117], [210, 131], [211, 116]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0064_user_0001_scene_0008_cfg_0001_039422060546#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the roll of paper down from the shelf', and now you are performing subtask 'take the roll of paper down from the shelf.'\nBegin at [261, 126] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[261, 126], [242, 141], [242, 204], [216, 216], [241, 213], [247, 251], [330, 166], [334, 179], [316, 139], [254, 120]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0064_user_0001_scene_0008_cfg_0001_039422060546#0.jpg", + "gt": "[[261, 126], [242, 141], [242, 204], [216, 216], [241, 213], [247, 251], [330, 166], [334, 179], [316, 139], [254, 120]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0018_user_0014_scene_0007_cfg_0006_104122061602#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'sliding the Lego blocks on the desktop', and now you are performing subtask 'sliding the Lego blocks on the desktop.'\nStart at [446, 106]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[446, 106], [439, 171], [418, 196], [423, 204], [432, 204], [441, 191], [442, 181], [452, 169], [444, 160], [427, 160]]}" + } + ], + "images": "RH20T_cfg6_task_0018_user_0014_scene_0007_cfg_0006_104122061602#0", + "gt": "[[446, 106], [439, 171], [418, 196], [423, 204], [432, 204], [441, 191], [442, 181], [452, 169], [444, 160], [427, 160]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0111_user_0010_scene_0006_cfg_0001_035622060973#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the object with the corresponding shape into the corresponding hole', and now you are performing subtask 'put the object with the corresponding shape into the corresponding hole.'\nThe trajectory starts at [242, 137]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[242, 137], [236, 152], [221, 163], [219, 196], [193, 217], [212, 221], [233, 245], [262, 240], [248, 191], [246, 142]]}" + } + ], + "images": "RH20T_cfg1_task_0111_user_0010_scene_0006_cfg_0001_035622060973#0", + "gt": "[[242, 137], [236, 152], [221, 163], [219, 196], [193, 217], [212, 221], [233, 245], [262, 240], [248, 191], [246, 142]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg3_task_0057_user_0010_scene_0007_cfg_0003_104122062295#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn on the power strips', and now you are performing subtask 'press the button of the power socket in the second position, press the button of the power socket in the third position.'\nYour starting position is [314, 231]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[314, 231], [313, 232], [314, 237], [313, 237], [319, 228], [320, 225], [319, 230], [319, 234], [317, 238], [311, 245]]}" + } + ], + "images": "RH20T_cfg3_task_0057_user_0010_scene_0007_cfg_0003_104122062295#170", + "gt": "[[314, 231], [313, 232], [314, 237], [313, 237], [319, 228], [320, 225], [319, 230], [319, 234], [317, 238], [311, 245]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg2_task_0037_user_0007_scene_0006_cfg_0002_105422061350#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'pick up the third block on the table, transfer the third block from the table to the top of the fourth block, place the third block on the fourth block, pick up the fourth block on the table.'\nThe trajectory starts at [292, 176]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[292, 176], [289, 183], [292, 179], [293, 185], [292, 177], [312, 136], [317, 145], [324, 139], [320, 149], [282, 187]]}" + } + ], + "images": "RH20T_cfg2_task_0037_user_0007_scene_0006_cfg_0002_105422061350#499", + "gt": "[[292, 176], [289, 183], [292, 179], [293, 185], [292, 177], [312, 136], [317, 145], [324, 139], [320, 149], [282, 187]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0003_user_0010_scene_0005_cfg_0005_104122063678#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press three buttons from left to right in sequence', and now you are performing subtask 'press the green button on the right.'\nStart at [323, 132]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[323, 132], [340, 165], [345, 208], [366, 219], [361, 222], [360, 210], [345, 213], [342, 224], [359, 230], [347, 244]]}" + } + ], + "images": "RH20T_cfg5_task_0003_user_0010_scene_0005_cfg_0005_104122063678#0", + "gt": "[[323, 132], [340, 165], [345, 208], [366, 219], [361, 222], [360, 210], [345, 213], [342, 224], [359, 230], [347, 244]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0055_user_0015_scene_0009_cfg_0001_038522062547#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'transfer liquid using a dropper', and now you are performing subtask 'pick up the dropper from the cup, transfer the dropper from the cup to the container with liquid, place the dropper in the container with liquid.'\nYour initial coordinate is [405, 132]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[405, 132], [383, 110], [354, 108], [359, 118], [381, 101], [390, 65], [457, 28], [470, 30], [463, 49], [458, 40]]}" + } + ], + "images": "RH20T_cfg1_task_0055_user_0015_scene_0009_cfg_0001_038522062547#0", + "gt": "[[405, 132], [383, 110], [354, 108], [359, 118], [381, 101], [390, 65], [457, 28], [470, 30], [463, 49], [458, 40]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "5154_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the marker from the center of the table to the bottom of the table', and now you are performing subtask 'move the marker from the center of the table to the bottom of the table.'\nStarting at [44, 85], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[44, 85], [73, 64], [92, 54], [101, 53], [125, 79], [124, 86], [118, 86], [103, 104], [98, 91], [103, 93]]}" + } + ], + "images": "5154_exterior_image_1_left#0", + "gt": "[[44, 85], [73, 64], [92, 54], [101, 53], [125, 79], [124, 86], [118, 86], [103, 104], [98, 91], [103, 93]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "59279_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'place the snack in the cabinet', and now you are performing subtask 'place the snack in the cabinet.'\nYour starting position is [142, 73]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[142, 73], [152, 137], [151, 117], [138, 88], [133, 0], [150, 21], [142, 1], [132, 4], [127, 14], [119, 95]]}" + } + ], + "images": "59279_exterior_image_1_left#0", + "gt": "[[142, 73], [152, 137], [151, 117], [138, 88], [133, 0], [150, 21], [142, 1], [132, 4], [127, 14], [119, 95]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "45919_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stir the contents of the bowl with a spoon', and now you are performing subtask 'stir the contents of the bowl with a spoon.'\nStarting at [228, 63], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[228, 63], [223, 98], [229, 79], [209, 71], [205, 83], [208, 66], [195, 78], [200, 66], [202, 86], [221, 65]]}" + } + ], + "images": "45919_exterior_image_1_left#0", + "gt": "[[228, 63], [223, 98], [229, 79], [209, 71], [205, 83], [208, 66], [195, 78], [200, 66], [202, 86], [221, 65]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0065_user_0014_scene_0003_cfg_0007_104122064161#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with small Lego blocks for the nth time with n blocks', and now you are performing subtask 'pick up the second Lego block from the right side of the workbench, transfer the second Lego block from the right side of the workbench to the center Lego baseplate, place the second Lego block on the Lego baseplate.'\nWith start location [411, 182], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[411, 182], [430, 204], [428, 218], [421, 187], [409, 173], [382, 162], [376, 173], [375, 164], [373, 169], [400, 169]]}" + } + ], + "images": "RH20T_cfg7_task_0065_user_0014_scene_0003_cfg_0007_104122064161#279", + "gt": "[[411, 182], [430, 204], [428, 218], [421, 187], [409, 173], [382, 162], [376, 173], [375, 164], [373, 169], [400, 169]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg2_task_0011_user_0013_scene_0001_cfg_0002_105422061350#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the watering can to the center of the table', and now you are performing subtask 'move the watering can to the center of the table.'\nStart at [319, 108]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[319, 108], [286, 138], [272, 140], [215, 215], [213, 192], [231, 143], [262, 110], [247, 117], [230, 143], [217, 205]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg2_task_0011_user_0013_scene_0001_cfg_0002_105422061350#0.jpg", + "gt": "[[319, 108], [286, 138], [272, 140], [215, 215], [213, 192], [231, 143], [262, 110], [247, 117], [230, 143], [217, 205]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0031_user_0020_scene_0007_cfg_0007_104122064161#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'cover the box', and now you are performing subtask 'cover the box.'\nYour starting position is [337, 115]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[337, 115], [344, 122], [360, 168], [373, 184], [372, 225], [383, 172], [375, 140], [376, 116], [380, 119], [364, 100]]}" + } + ], + "images": "RH20T_cfg7_task_0031_user_0020_scene_0007_cfg_0007_104122064161#0", + "gt": "[[337, 115], [344, 122], [360, 168], [373, 184], [372, 225], [383, 172], [375, 140], [376, 116], [380, 119], [364, 100]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0066_user_0014_scene_0005_cfg_0007_104122061602#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with large Megabloks for the nth time with n blocks', and now you are performing subtask 'pick up the block on the flat surface, transfer the block from the flat surface to the block board, place the block on the block board.'\nFrom start point [448, 116], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[448, 116], [490, 138], [516, 141], [545, 161], [553, 177], [540, 221], [543, 208], [526, 176], [480, 176], [469, 191]]}" + } + ], + "images": "RH20T_cfg7_task_0066_user_0014_scene_0005_cfg_0007_104122061602#0", + "gt": "[[448, 116], [490, 138], [516, 141], [545, 161], [553, 177], [540, 221], [543, 208], [526, 176], [480, 176], [469, 191]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0024_user_0014_scene_0003_cfg_0004_104122063550#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn off the power strip by pressing the button', and now you are performing subtask 'turn off the power strip by pressing the button.'\nThe trajectory starts at [275, 186]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[275, 186], [305, 220], [281, 213], [269, 251], [264, 196], [274, 200], [304, 253], [296, 259], [279, 210], [277, 182]]}" + } + ], + "images": "RH20T_cfg4_task_0024_user_0014_scene_0003_cfg_0004_104122063550#0", + "gt": "[[275, 186], [305, 220], [281, 213], [269, 251], [264, 196], [274, 200], [304, 253], [296, 259], [279, 210], [277, 182]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "17163_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick the marker and put it in the cup', and now you are performing subtask 'pick the marker and put it in the cup.'\nFrom start point [123, 153], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[123, 153], [141, 141], [149, 141], [170, 163], [155, 124], [130, 122], [140, 118], [152, 125], [141, 129], [141, 129]]}" + } + ], + "images": "17163_exterior_image_2_left#0", + "gt": "[[123, 153], [141, 141], [149, 141], [170, 163], [155, 124], [130, 122], [140, 118], [152, 125], [141, 129], [141, 129]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "88097_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the pen on the table', and now you are performing subtask 'put the pen on the table.'\nYour starting position is [148.0, 2.0]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[148.0, 2.0], [158.0, 22.0], [155.0, 62.0], [162.0, 66.0], [155.0, 47.0], [142.0, 43.0], [128.0, 55.0], [124.0, 74.0], [127.0, 81.0], [129.0, 74.0]]}" + } + ], + "images": "88097_exterior_image_1_left#0", + "gt": "[[148.0, 2.0], [158.0, 22.0], [155.0, 62.0], [162.0, 66.0], [155.0, 47.0], [142.0, 43.0], [128.0, 55.0], [124.0, 74.0], [127.0, 81.0], [129.0, 74.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0094_user_0014_scene_0010_cfg_0001_038522062547#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open a box', and now you are performing subtask 'fold the third lid on the box on the table, fold the fourth lid on the box on the table.'\nThe trajectory starts at [368, 196]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[368, 196], [381, 209], [418, 204], [414, 212], [483, 250], [462, 244], [471, 223], [456, 206], [408, 195], [408, 195]]}" + } + ], + "images": "RH20T_cfg1_task_0094_user_0014_scene_0010_cfg_0001_038522062547#213", + "gt": "[[368, 196], [381, 209], [418, 204], [414, 212], [483, 250], [462, 244], [471, 223], [456, 206], [408, 195], [408, 195]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "77960_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the marker inside the transparent cup', and now you are performing subtask 'put the marker inside the transparent cup.'\nBegin at [218, 49] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[218, 49], [197, 33], [180, 28], [167, 30], [167, 55], [158, 72], [160, 96], [149, 71], [141, 114], [129, 80]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/77960_exterior_image_2_left#0.jpg", + "gt": "[[218, 49], [197, 33], [180, 28], [167, 30], [167, 55], [158, 72], [160, 96], [149, 71], [141, 114], [129, 80]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg2_task_0016_user_0003_scene_0009_cfg_0002_037522062165#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'an action of hitting the pool ball', and now you are performing subtask 'strike the pool ball on the green pool table, transfer the cue from in front of the pool ball to the pool table, place the cue on the pool table.'\nThe trajectory starts at [295, 230]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[295, 230], [271, 245], [282, 239], [300, 213], [297, 218], [295, 212], [272, 213], [246, 199], [256, 208], [272, 156]]}" + } + ], + "images": "RH20T_cfg2_task_0016_user_0003_scene_0009_cfg_0002_037522062165#252", + "gt": "[[295, 230], [271, 245], [282, 239], [300, 213], [297, 218], [295, 212], [272, 213], [246, 199], [256, 208], [272, 156]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "81736_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close the middle drawer doors', and now you are performing subtask 'push the handle of the right-side middle cabinet door to close the cabinet door.'\nYou begin at [69, 70]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[69, 70], [131, 34], [179, 54], [180, 63], [163, 67], [159, 63], [168, 54], [189, 46], [172, 68], [136, 51]]}" + } + ], + "images": "81736_exterior_image_1_left#0", + "gt": "[[69, 70], [131, 34], [179, 54], [180, 63], [163, 67], [159, 63], [168, 54], [189, 46], [172, 68], [136, 51]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0003_user_0014_scene_0010_cfg_0005_104122063678#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press three buttons from left to right in sequence', and now you are performing subtask 'press the orange button on the vertical base, press the green button on the white base.'\nStarting at [417, 246], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[417, 246], [425, 215], [421, 198], [404, 189], [395, 196], [398, 192], [405, 202], [399, 203], [398, 209], [392, 202]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0003_user_0014_scene_0010_cfg_0005_104122063678#214.jpg", + "gt": "[[417, 246], [425, 215], [421, 198], [404, 189], [395, 196], [398, 192], [405, 202], [399, 203], [398, 209], [392, 202]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0091_user_0007_scene_0004_cfg_0005_104422070044#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move an object from one box to another', and now you are performing subtask 'throw the block onto the table, pick up the block from the table, move the block from the table to the blue box, place the object into the light blue box.'\nThe trajectory starts at [413, 120]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[413, 120], [400, 118], [376, 141], [374, 149], [378, 176], [367, 136], [367, 128], [359, 125], [354, 135], [354, 118]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0091_user_0007_scene_0004_cfg_0005_104422070044#141.jpg", + "gt": "[[413, 120], [400, 118], [376, 141], [374, 149], [378, 176], [367, 136], [367, 128], [359, 125], [354, 135], [354, 118]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "6070_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the white cup', and now you are performing subtask 'move the white cup.'\nYou start from [87.5, 12.5]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[87.5, 12.5], [122.5, 11.5], [163.5, 35.5], [176.5, 57.5], [166.5, 87.5], [155.5, 79.5], [131.5, 81.5], [154.5, 93.5], [155.5, 117.5], [148.5, 67.5]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/6070_exterior_image_1_left#0.jpg", + "gt": "[[87.5, 12.5], [122.5, 11.5], [163.5, 35.5], [176.5, 57.5], [166.5, 87.5], [155.5, 79.5], [131.5, 81.5], [154.5, 93.5], [155.5, 117.5], [148.5, 67.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "79681_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the towel and lay it flat on the countertop', and now you are performing subtask 'slide the towel up.'\nYour starting position is [245, 110]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[245, 110], [219, 87], [222, 88], [209, 92], [204, 101], [192, 109], [173, 103], [175, 100], [188, 102], [188, 102]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/79681_exterior_image_1_left#169.jpg", + "gt": "[[245, 110], [219, 87], [222, 88], [209, 92], [204, 101], [192, 109], [173, 103], [175, 100], [188, 102], [188, 102]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0003_user_0014_scene_0006_cfg_0005_037522062165#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press three buttons from left to right in sequence', and now you are performing subtask 'press the green button on the gray and white base, press the red button on the black and orange base.'\nYou begin at [212, 216]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[212, 216], [209, 203], [226, 210], [269, 247], [271, 254], [250, 266], [259, 267], [257, 275], [260, 264], [247, 209]]}" + } + ], + "images": "RH20T_cfg5_task_0003_user_0014_scene_0006_cfg_0005_037522062165#350", + "gt": "[[212, 216], [209, 203], [226, 210], [269, 247], [271, 254], [250, 266], [259, 267], [257, 275], [260, 264], [247, 209]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "26790_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'push the first small block to the left and use the second small block to push the third small block to the right', and now you are performing subtask 'pick up the second small object on the table.'\nBegin at [196.0, 39.0] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[196.0, 39.0], [165.0, 64.0], [148.0, 93.0], [144.0, 97.0], [138.0, 98.0], [137.0, 105.0], [148.0, 74.0], [144.0, 81.0], [135.0, 82.0], [134.0, 90.0]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/26790_exterior_image_1_left#0.jpg", + "gt": "[[196.0, 39.0], [165.0, 64.0], [148.0, 93.0], [144.0, 97.0], [138.0, 98.0], [137.0, 105.0], [148.0, 74.0], [144.0, 81.0], [135.0, 82.0], [134.0, 90.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "41140_exterior_image_2_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'spread the silver containers on the counter', and now you are performing subtask 'place the silver bowl in another location.'\nStart at [140, 130]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[140, 130], [129, 134], [123, 153], [143, 159], [148, 144], [134, 157], [133, 172], [143, 168], [147, 150], [144, 151]]}" + } + ], + "images": "41140_exterior_image_2_left#161", + "gt": "[[140, 130], [129, 134], [123, 153], [143, 159], [148, 144], [134, 157], [133, 172], [143, 168], [147, 150], [144, 151]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg2_task_0002_user_0013_scene_0006_cfg_0002_036422060215#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pull out a napkin, place the napkin on the table', and now you are performing subtask 'pull out a napkin, place the napkin on the table.'\nYour initial coordinate is [294, 162]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[294, 162], [301, 159], [295, 149], [297, 157], [310, 127], [325, 116], [330, 118], [334, 138], [326, 147], [318, 184]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg2_task_0002_user_0013_scene_0006_cfg_0002_036422060215#0.jpg", + "gt": "[[294, 162], [301, 159], [295, 149], [297, 157], [310, 127], [325, 116], [330, 118], [334, 138], [326, 147], [318, 184]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "26635_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the bottle to the right side of the table', and now you are performing subtask 'move the bottle to the right side of the table.'\nWith start location [159.0, 2.0], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[159.0, 2.0], [167.0, 0.0], [143.0, 75.0], [153.0, 52.0], [178.0, 30.0], [206.0, 34.0], [200.0, 33.0], [206.0, 51.0], [197.0, 66.0], [202.0, 42.0]]}" + } + ], + "images": "26635_exterior_image_1_left#0", + "gt": "[[159.0, 2.0], [167.0, 0.0], [143.0, 75.0], [153.0, 52.0], [178.0, 30.0], [206.0, 34.0], [200.0, 33.0], [206.0, 51.0], [197.0, 66.0], [202.0, 42.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "91717_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the orange cloth', and now you are performing subtask 'pick up the orange cloth from the tabletop.'\nStarting at [134, 80], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[134, 80], [150, 81], [171, 107], [165, 106], [167, 125], [187, 111], [220, 120], [227, 128], [226, 146], [198, 98]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/91717_exterior_image_2_left#0.jpg", + "gt": "[[134, 80], [150, 81], [171, 107], [165, 106], [167, 125], [187, 111], [220, 120], [227, 128], [226, 146], [198, 98]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0002_user_0014_scene_0004_cfg_0001_038522062547#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pull out a napkin', and now you are performing subtask 'pull out a napkin.'\nBegin at [406, 133] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[406, 133], [421, 98], [415, 122], [433, 174], [428, 176], [420, 144], [424, 86], [438, 78], [424, 13], [424, 13]]}" + } + ], + "images": "RH20T_cfg1_task_0002_user_0014_scene_0004_cfg_0001_038522062547#0", + "gt": "[[406, 133], [421, 98], [415, 122], [433, 174], [428, 176], [420, 144], [424, 86], [438, 78], [424, 13], [424, 13]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "61861_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the cloth and wipe the pot then place it on the table', and now you are performing subtask 'pick up the cloth and wipe the pot then place it on the table.'\nYour starting position is [142.5, 6.0]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[142.5, 6.0], [214.5, 117.0], [200.5, 90.0], [179.5, 94.0], [186.5, 105.0], [166.5, 101.0], [170.5, 86.0], [184.5, 83.0], [219.5, 117.0], [186.5, 100.0]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/61861_exterior_image_1_left#0.jpg", + "gt": "[[142.5, 6.0], [214.5, 117.0], [200.5, 90.0], [179.5, 94.0], [186.5, 105.0], [166.5, 101.0], [170.5, 86.0], [184.5, 83.0], [219.5, 117.0], [186.5, 100.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "83621_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the brown toy and place it on the stove', and now you are performing subtask 'pick up the brown toy and place it on the stove.'\nYou begin at [230, 29]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[230, 29], [186, 76], [141, 103], [142, 120], [142, 107], [158, 99], [188, 102], [216, 97], [226, 81], [238, 87]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/83621_exterior_image_2_left#0.jpg", + "gt": "[[230, 29], [186, 76], [141, 103], [142, 120], [142, 107], [158, 99], [188, 102], [216, 97], [226, 81], [238, 87]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "21358_exterior_image_1_left#TrajectoryPrediction_Task#8", + "task": "TrajectoryPrediction_Task", + "p_index": 8, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the two pillows', and now you are performing subtask 'pull the second cushion next to the first small cushion.'\nYou begin at [159, 94]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[159, 94], [165, 106], [163, 113], [162, 109], [171, 104], [181, 105], [199, 113], [218, 111], [215, 97], [199, 102]]}" + } + ], + "images": "21358_exterior_image_1_left#467", + "gt": "[[159, 94], [165, 106], [163, 113], [162, 109], [171, 104], [181, 105], [199, 113], [218, 111], [215, 97], [199, 102]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "59486_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the black masking tape on the cream plate', and now you are performing subtask 'put the black masking tape on the cream plate.'\nYour initial coordinate is [304, 1]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[304, 1], [296, 24], [201, 76], [214, 74], [177, 114], [183, 79], [214, 76], [223, 82], [220, 92], [216, 81]]}" + } + ], + "images": "59486_exterior_image_2_left#0", + "gt": "[[304, 1], [296, 24], [201, 76], [214, 74], [177, 114], [183, 79], [214, 76], [223, 82], [220, 92], [216, 81]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0096_user_0020_scene_0003_cfg_0006_104122060811#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take something out of a drawer', and now you are performing subtask 'pull the handle of the drawer, pick up the object from inside the drawer.'\nYou start from [385, 127]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[385, 127], [366, 124], [371, 113], [395, 129], [414, 121], [434, 134], [413, 143], [434, 126], [392, 136], [406, 141]]}" + } + ], + "images": "RH20T_cfg6_task_0096_user_0020_scene_0003_cfg_0006_104122060811#0", + "gt": "[[385, 127], [366, 124], [371, 113], [395, 129], [414, 121], [434, 134], [413, 143], [434, 126], [392, 136], [406, 141]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "26499_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the white cloth and place it on the clear screen', and now you are performing subtask 'take the white cloth and place it on the clear screen.'\nYou begin at [131, 63]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[131, 63], [116, 79], [126, 95], [118, 129], [108, 68], [116, 24], [127, 14], [145, 20], [167, 53], [155, 32]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/26499_exterior_image_2_left#0.jpg", + "gt": "[[131, 63], [116, 79], [126, 95], [118, 129], [108, 68], [116, 24], [127, 14], [145, 20], [167, 53], [155, 32]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0081_user_0007_scene_0003_cfg_0005_036422060215#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the leg of the glasses (with one hand)', and now you are performing subtask 'fold the legs of the glasses to unfold them.'\nFrom start point [219, 118], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[219, 118], [213, 127], [213, 138], [227, 153], [229, 166], [219, 172], [217, 170], [217, 151], [224, 136], [222, 114]]}" + } + ], + "images": "RH20T_cfg5_task_0081_user_0007_scene_0003_cfg_0005_036422060215#349", + "gt": "[[219, 118], [213, 127], [213, 138], [227, 153], [229, 166], [219, 172], [217, 170], [217, 151], [224, 136], [222, 114]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "52362_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'arrange the two small pillows against the right armrest of the sofa', and now you are performing subtask 'pick up the small pillow on the left side of the sofa.'\nYou start from [186, 111]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[186, 111], [188, 119], [189, 103], [202, 89], [204, 102], [202, 98], [199, 102], [210, 105], [213, 101], [207, 93]]}" + } + ], + "images": "52362_exterior_image_1_left#92", + "gt": "[[186, 111], [188, 119], [189, 103], [202, 89], [204, 102], [202, 98], [199, 102], [210, 105], [213, 101], [207, 93]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0058_user_0014_scene_0003_cfg_0004_036422060909#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn off the power strips', and now you are performing subtask 'press the button on the second power strip from the left.'\nStart at [367, 115]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[367, 115], [366, 117], [366, 119], [363, 125], [361, 127], [359, 132], [353, 127], [347, 124], [341, 122], [332, 121]]}" + } + ], + "images": "RH20T_cfg4_task_0058_user_0014_scene_0003_cfg_0004_036422060909#124", + "gt": "[[367, 115], [366, 117], [366, 119], [363, 125], [361, 127], [359, 132], [353, 127], [347, 124], [341, 122], [332, 121]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "13565_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the towel', and now you are performing subtask 'move the towel.'\nStart at [192, 2]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[192, 2], [217, 34], [237, 81], [229, 78], [234, 83], [230, 100], [222, 110], [212, 111], [170, 95], [172, 80]]}" + } + ], + "images": "13565_exterior_image_1_left#0", + "gt": "[[192, 2], [217, 34], [237, 81], [229, 78], [234, 83], [230, 100], [222, 110], [212, 111], [170, 95], [172, 80]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "31978_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'lay the bottle on its side then place it upside down', and now you are performing subtask 'pick up the bottle from the side.'\nYou begin at [221, 4]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[221, 4], [199, 45], [211, 72], [205, 52], [209, 32], [201, 77], [194, 49], [177, 46], [204, 62], [200, 67]]}" + } + ], + "images": "31978_exterior_image_1_left#0", + "gt": "[[221, 4], [199, 45], [211, 72], [205, 52], [209, 32], [201, 77], [194, 49], [177, 46], [204, 62], [200, 67]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "6473_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the marker from the table and place it in the glass container', and now you are performing subtask 'take the marker from the table and place it in the glass container.'\nStarting at [208, 20], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[208, 20], [211, 57], [218, 79], [198, 91], [195, 103], [198, 109], [193, 95], [187, 92], [201, 105], [202, 87]]}" + } + ], + "images": "6473_exterior_image_1_left#0", + "gt": "[[208, 20], [211, 57], [218, 79], [198, 91], [195, 103], [198, 109], [193, 95], [187, 92], [201, 105], [202, 87]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0039_user_0007_scene_0003_cfg_0005_036422060215#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pour the water from one cup into another empty cup', and now you are performing subtask 'pour the water from one cup into another empty cup.'\nBegin at [286, 108] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[286, 108], [256, 104], [237, 121], [230, 161], [237, 117], [284, 113], [271, 103], [241, 113], [226, 130], [225, 155]]}" + } + ], + "images": "RH20T_cfg5_task_0039_user_0007_scene_0003_cfg_0005_036422060215#0", + "gt": "[[286, 108], [256, 104], [237, 121], [230, 161], [237, 117], [284, 113], [271, 103], [241, 113], [226, 130], [225, 155]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "57247_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close the kitchen drawer', and now you are performing subtask 'close the kitchen drawer.'\nWith start location [146, 79], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[146, 79], [115, 82], [51, 103], [25, 130], [17, 151], [30, 162], [40, 166], [55, 161], [94, 134], [83, 119]]}" + } + ], + "images": "57247_exterior_image_1_left#0", + "gt": "[[146, 79], [115, 82], [51, 103], [25, 130], [17, 151], [30, 162], [40, 166], [55, 161], [94, 134], [83, 119]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "41945_exterior_image_2_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'throw the bottle cap on the table', and now you are performing subtask 'throw the bottle cap on the table.'\nYou begin at [131, 48]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[131, 48], [131, 46], [132, 47], [132, 46], [132, 48], [132, 43], [129, 42], [131, 45], [130, 44], [130, 44]]}" + } + ], + "images": "41945_exterior_image_2_left#74", + "gt": "[[131, 48], [131, 46], [132, 47], [132, 46], [132, 48], [132, 43], [129, 42], [131, 45], [130, 44], [130, 44]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "2437_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the tulip plush toy inside the sink', and now you are performing subtask 'put the tulip plush toy inside the sink.'\nStarting at [241, 2], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[241, 2], [166, 79], [154, 100], [164, 119], [201, 89], [221, 88], [222, 96], [209, 107], [199, 84], [244, 65]]}" + } + ], + "images": "2437_exterior_image_2_left#0", + "gt": "[[241, 2], [166, 79], [154, 100], [164, 119], [201, 89], [221, 88], [222, 96], [209, 107], [199, 84], [244, 65]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "19989_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close the box', and now you are performing subtask 'close the box.'\nYour initial coordinate is [277, 45]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[277, 45], [242, 78], [243, 90], [208, 108], [197, 98], [175, 103], [180, 71], [194, 94], [186, 104], [192, 80]]}" + } + ], + "images": "19989_exterior_image_1_left#0", + "gt": "[[277, 45], [242, 78], [243, 90], [208, 108], [197, 98], [175, 103], [180, 71], [194, 94], [186, 104], [192, 80]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0066_user_0014_scene_0005_cfg_0007_104122063633#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with large Megabloks for the nth time with n blocks', and now you are performing subtask 'pick up the block on the flat surface, transfer the block from the flat surface to the block board, place the block on the block board.'\nFrom start point [180, 154], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[180, 154], [151, 169], [146, 181], [157, 161], [176, 151], [219, 208], [217, 213], [200, 189], [181, 180], [181, 180]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg7_task_0066_user_0014_scene_0005_cfg_0007_104122063633#343.jpg", + "gt": "[[180, 154], [151, 169], [146, 181], [157, 161], [176, 151], [219, 208], [217, 213], [200, 189], [181, 180], [181, 180]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0001_user_0010_scene_0004_cfg_0004_104122062823#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the button from top to bottom', and now you are performing subtask 'press the button on the surface from top to bottom.'\nYour initial coordinate is [243, 0]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[243, 0], [384, 1], [389, 17], [359, 35], [352, 60], [353, 52], [366, 61], [373, 48], [362, 55], [362, 55]]}" + } + ], + "images": "RH20T_cfg4_task_0001_user_0010_scene_0004_cfg_0004_104122062823#0", + "gt": "[[243, 0], [384, 1], [389, 17], [359, 35], [352, 60], [353, 52], [366, 61], [373, 48], [362, 55], [362, 55]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "54851_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the marker out of the mug and put it on the table', and now you are performing subtask 'take the marker out of the mug and put it on the table.'\nYou start from [122, 82]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[122, 82], [158, 83], [147, 87], [145, 98], [133, 112], [133, 117], [141, 95], [149, 98], [152, 112], [154, 104]]}" + } + ], + "images": "54851_exterior_image_2_left#0", + "gt": "[[122, 82], [158, 83], [147, 87], [145, 98], [133, 112], [133, 117], [141, 95], [149, 98], [152, 112], [154, 104]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "76007_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up a bottle from the table and place it on the tray', and now you are performing subtask 'push the bottle to the left.'\nBegin at [189, 47] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[189, 47], [189, 45], [211, 40], [218, 50], [215, 56], [189, 59], [196, 48], [201, 47], [205, 50], [205, 50]]}" + } + ], + "images": "76007_exterior_image_1_left#150", + "gt": "[[189, 47], [189, 45], [211, 40], [218, 50], [215, 56], [189, 59], [196, 48], [201, 47], [205, 50], [205, 50]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0038_user_0014_scene_0006_cfg_0006_104122061330#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the cup', and now you are performing subtask 'pick up the cup.'\nThe trajectory starts at [265, 97]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[265, 97], [264, 73], [261, 79], [272, 89], [290, 121], [301, 152], [299, 177], [283, 143], [283, 93], [283, 93]]}" + } + ], + "images": "RH20T_cfg6_task_0038_user_0014_scene_0006_cfg_0006_104122061330#0", + "gt": "[[265, 97], [264, 73], [261, 79], [272, 89], [290, 121], [301, 152], [299, 177], [283, 143], [283, 93], [283, 93]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0012_user_0010_scene_0005_cfg_0004_104122062823#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'push the soccer ball into the goal', and now you are performing subtask 'push the soccer ball toward the goal.'\nThe trajectory starts at [216, 37]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[216, 37], [229, 54], [236, 43], [241, 39], [239, 38], [237, 39], [239, 40], [239, 38], [250, 45], [265, 59]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg4_task_0012_user_0010_scene_0005_cfg_0004_104122062823#166.jpg", + "gt": "[[216, 37], [229, 54], [236, 43], [241, 39], [239, 38], [237, 39], [239, 40], [239, 38], [250, 45], [265, 59]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0057_user_0014_scene_0008_cfg_0006_104122063633#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn on the power strips', and now you are performing subtask 'press the second button on the power strip.'\nThe trajectory starts at [230, 163]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[230, 163], [226, 164], [222, 167], [224, 173], [226, 170], [223, 164], [220, 160], [218, 160], [216, 162], [216, 162]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg6_task_0057_user_0014_scene_0008_cfg_0006_104122063633#155.jpg", + "gt": "[[230, 163], [226, 164], [222, 167], [224, 173], [226, 170], [223, 164], [220, 160], [218, 160], [216, 162], [216, 162]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "87077_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the glass lid from the black pot', and now you are performing subtask 'remove the glass lid from the black pot.'\nFrom start point [247, 24], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[247, 24], [199, 37], [189, 60], [191, 87], [189, 76], [184, 75], [180, 97], [169, 115], [171, 136], [180, 150]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/87077_exterior_image_2_left#0.jpg", + "gt": "[[247, 24], [199, 37], [189, 60], [191, 87], [189, 76], [184, 75], [180, 97], [169, 115], [171, 136], [180, 150]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg3_task_0038_user_0010_scene_0010_cfg_0003_104122063550#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the cup', and now you are performing subtask 'pick up the cup.'\nYour initial coordinate is [277, 192]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[277, 192], [254, 183], [253, 189], [276, 190], [359, 175], [402, 155], [408, 188], [367, 169], [338, 180], [336, 190]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg3_task_0038_user_0010_scene_0010_cfg_0003_104122063550#0.jpg", + "gt": "[[277, 192], [254, 183], [253, 189], [276, 190], [359, 175], [402, 155], [408, 188], [367, 169], [338, 180], [336, 190]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "1784_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'place the bowl in front of the table', and now you are performing subtask 'place the bowl in front of the table.'\nBegin at [123.0, 22.0] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[123.0, 22.0], [140.0, 33.0], [146.0, 48.0], [147.0, 71.0], [151.0, 90.0], [161.0, 94.0], [166.0, 108.0], [174.0, 112.0], [168.0, 107.0], [165.0, 62.0]]}" + } + ], + "images": "1784_exterior_image_1_left#0", + "gt": "[[123.0, 22.0], [140.0, 33.0], [146.0, 48.0], [147.0, 71.0], [151.0, 90.0], [161.0, 94.0], [166.0, 108.0], [174.0, 112.0], [168.0, 107.0], [165.0, 62.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg3_task_0073_user_0010_scene_0010_cfg_0003_038522062288#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the things in the drawer', and now you are performing subtask 'pick up the small square from the table, transfer the small square from the table to the open drawer, place the small square in the drawer.'\nBegin at [236, 126] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[236, 126], [173, 155], [105, 165], [125, 181], [136, 135], [178, 92], [192, 96], [183, 122], [213, 110], [221, 251]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg3_task_0073_user_0010_scene_0010_cfg_0003_038522062288#0.jpg", + "gt": "[[236, 126], [173, 155], [105, 165], [125, 181], [136, 135], [178, 92], [192, 96], [183, 122], [213, 110], [221, 251]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0118_user_0007_scene_0010_cfg_0005_104122063678#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn on the water tap', and now you are performing subtask 'turn on the water tap.'\nYou begin at [213, 120]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[213, 120], [240, 128], [249, 140], [280, 158], [295, 206], [299, 200], [291, 188], [296, 180], [261, 184], [225, 151]]}" + } + ], + "images": "RH20T_cfg5_task_0118_user_0007_scene_0010_cfg_0005_104122063678#0", + "gt": "[[213, 120], [240, 128], [249, 140], [280, 158], [295, 206], [299, 200], [291, 188], [296, 180], [261, 184], [225, 151]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "17995_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'transfer the marker from the bowl to the table', and now you are performing subtask 'place the marker on the tabletop.'\nYour starting position is [164, 80]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[164, 80], [166, 80], [164, 63], [155, 43], [152, 42], [148, 46], [144, 55], [149, 79], [152, 80], [148, 60]]}" + } + ], + "images": "17995_exterior_image_1_left#114", + "gt": "[[164, 80], [166, 80], [164, 63], [155, 43], [152, 42], [148, 46], [144, 55], [149, 79], [152, 80], [148, 60]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0016_user_0010_scene_0001_cfg_0005_036422060215#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'hit the pool ball', and now you are performing subtask 'hit the pool ball.'\nThe trajectory starts at [286, 108]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[286, 108], [299, 183], [292, 189], [295, 177], [278, 168], [273, 148], [269, 163], [278, 170], [273, 131], [280, 124]]}" + } + ], + "images": "RH20T_cfg5_task_0016_user_0010_scene_0001_cfg_0005_036422060215#0", + "gt": "[[286, 108], [299, 183], [292, 189], [295, 177], [278, 168], [273, 148], [269, 163], [278, 170], [273, 131], [280, 124]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0065_user_0014_scene_0002_cfg_0001_038522062547#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with small Lego blocks for the nth time with n blocks', and now you are performing subtask 'pick up the pink block on the desktop, transfer the pink block from the desktop to the building area, place the pink block in the building area.'\nYour initial coordinate is [405, 132]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[405, 132], [388, 138], [387, 165], [394, 190], [410, 216], [417, 213], [427, 239], [407, 209], [391, 203], [382, 210]]}" + } + ], + "images": "RH20T_cfg1_task_0065_user_0014_scene_0002_cfg_0001_038522062547#0", + "gt": "[[405, 132], [388, 138], [387, 165], [394, 190], [410, 216], [417, 213], [427, 239], [407, 209], [391, 203], [382, 210]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg2_task_0065_user_0007_scene_0010_cfg_0002_105422061350#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with small Lego blocks for the nth time with n blocks', and now you are performing subtask 'pick up the green Lego block from the table, transfer the green Lego block from the table to the building area, place the green Lego block in the building area, press the green Lego block in the building area, pick up the black Lego block from the table.'\nYou start from [304, 109]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[304, 109], [305, 135], [262, 97], [171, 79], [169, 93], [227, 108], [224, 126], [216, 111], [189, 112], [189, 112]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg2_task_0065_user_0007_scene_0010_cfg_0002_105422061350#0.jpg", + "gt": "[[304, 109], [305, 135], [262, 97], [171, 79], [169, 93], [227, 108], [224, 126], [216, 111], [189, 112], [189, 112]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg3_task_0003_user_0016_scene_0001_cfg_0003_104122063550#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press three buttons from left to right in sequence', and now you are performing subtask 'press the green button on the right.'\nStarting at [279, 185], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[279, 185], [282, 134], [286, 199], [279, 193], [295, 231], [296, 291], [282, 297], [299, 342], [311, 342], [303, 347]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg3_task_0003_user_0016_scene_0001_cfg_0003_104122063550#0.jpg", + "gt": "[[279, 185], [282, 134], [286, 199], [279, 193], [295, 231], [296, 291], [282, 297], [299, 342], [311, 342], [303, 347]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg3_task_0057_user_0010_scene_0007_cfg_0003_104122062823#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn on the power strips', and now you are performing subtask 'press the button of the power socket in the third position.'\nYour initial coordinate is [185, 114]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[185, 114], [185, 108], [188, 105], [195, 105], [197, 106], [195, 108], [198, 111], [197, 111], [194, 100], [194, 100]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg3_task_0057_user_0010_scene_0007_cfg_0003_104122062823#190.jpg", + "gt": "[[185, 114], [185, 108], [188, 105], [195, 105], [197, 106], [195, 108], [198, 111], [197, 111], [194, 100], [194, 100]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg3_task_0023_user_0010_scene_0004_cfg_0003_038522062288#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn on the power strip by pressing the button', and now you are performing subtask 'turn on the power strip by pressing the button.'\nStart at [235, 130]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[235, 130], [209, 140], [240, 149], [270, 137], [175, 154], [171, 167], [200, 142], [220, 146], [207, 149], [197, 177]]}" + } + ], + "images": "RH20T_cfg3_task_0023_user_0010_scene_0004_cfg_0003_038522062288#0", + "gt": "[[235, 130], [209, 140], [240, 149], [270, 137], [175, 154], [171, 167], [200, 142], [220, 146], [207, 149], [197, 177]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "20030_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the drawer', and now you are performing subtask 'open the drawer.'\nThe trajectory starts at [274, 3]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[274, 3], [262, 32], [260, 58], [236, 74], [218, 82], [212, 81], [221, 84], [231, 93], [244, 73], [238, 78]]}" + } + ], + "images": "20030_exterior_image_2_left#0", + "gt": "[[274, 3], [262, 32], [260, 58], [236, 74], [218, 82], [212, 81], [221, 84], [231, 93], [244, 73], [238, 78]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "50242_exterior_image_2_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the white cup and put it on the orange object, then pick up the black cup and put it on the green object', and now you are performing subtask 'place the black cup on the green object.'\nBegin at [120, 90] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[120, 90], [141, 111], [140, 115], [130, 111], [123, 120], [129, 119], [128, 121], [126, 112], [117, 108], [117, 108]]}" + } + ], + "images": "50242_exterior_image_2_left#202", + "gt": "[[120, 90], [141, 111], [140, 115], [130, 111], [123, 120], [129, 119], [128, 121], [126, 112], [117, 108], [117, 108]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0073_user_0001_scene_0003_cfg_0001_035622060973#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the things in the drawer', and now you are performing subtask 'push the drawer handle to close the drawer.'\nThe trajectory starts at [278, 119]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[278, 119], [282, 125], [294, 127], [293, 131], [299, 126], [297, 131], [283, 117], [266, 87], [265, 92], [243, 108]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0073_user_0001_scene_0003_cfg_0001_035622060973#316.jpg", + "gt": "[[278, 119], [282, 125], [294, 127], [293, 131], [299, 126], [297, 131], [283, 117], [266, 87], [265, 92], [243, 108]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0015_user_0014_scene_0008_cfg_0007_104122064161#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'play the drum', and now you are performing subtask 'play the drum.'\nThe trajectory starts at [337, 115]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[337, 115], [371, 152], [389, 195], [385, 245], [398, 141], [384, 117], [394, 125], [393, 142], [370, 186], [361, 130]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg7_task_0015_user_0014_scene_0008_cfg_0007_104122064161#0.jpg", + "gt": "[[337, 115], [371, 152], [389, 195], [385, 245], [398, 141], [384, 117], [394, 125], [393, 142], [370, 186], [361, 130]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0130_user_0020_scene_0002_cfg_0006_104122060811#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'plug in the bulb holder with a bulb to the socket and turn on the switch of the bulb', and now you are performing subtask 'press the switch on the socket to turn on the bulb, press the bulb switch to turn on the light.'\nStart at [347, 118]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[347, 118], [355, 110], [352, 107], [359, 107], [355, 110], [363, 122], [368, 126], [370, 121], [363, 130], [363, 130]]}" + } + ], + "images": "RH20T_cfg6_task_0130_user_0020_scene_0002_cfg_0006_104122060811#584", + "gt": "[[347, 118], [355, 110], [352, 107], [359, 107], [355, 110], [363, 122], [368, 126], [370, 121], [363, 130], [363, 130]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0013_user_0014_scene_0007_cfg_0006_104122061330#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'place the block on the scale', and now you are performing subtask 'place the block on the scale.'\nYou start from [266, 97]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[266, 97], [251, 124], [255, 151], [254, 140], [270, 108], [293, 110], [285, 103], [230, 106], [224, 101], [230, 97]]}" + } + ], + "images": "RH20T_cfg6_task_0013_user_0014_scene_0007_cfg_0006_104122061330#0", + "gt": "[[266, 97], [251, 124], [255, 151], [254, 140], [270, 108], [293, 110], [285, 103], [230, 106], [224, 101], [230, 97]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0082_user_0007_scene_0002_cfg_0005_104422070044#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'scoop water with a large spoon from one bowl to another', and now you are performing subtask 'scoop water with a large spoon from one bowl to another.'\nBegin at [374, 132] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[374, 132], [391, 133], [398, 177], [403, 96], [392, 91], [384, 108], [403, 115], [403, 153], [384, 124], [384, 124]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0082_user_0007_scene_0002_cfg_0005_104422070044#0.jpg", + "gt": "[[374, 132], [391, 133], [398, 177], [403, 96], [392, 91], [384, 108], [403, 115], [403, 153], [384, 124], [384, 124]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "56862_exterior_image_1_left#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the bottle of water, the black bag, the dark blue bag, the top plastic and the remaining snack pack in the box respectively', and now you are performing subtask 'place the transparent bag in the box.'\nYou begin at [186, 98]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[186, 98], [172, 97], [152, 101], [150, 109], [166, 82], [178, 100], [177, 117], [175, 118], [170, 107], [155, 103]]}" + } + ], + "images": "56862_exterior_image_1_left#639", + "gt": "[[186, 98], [172, 97], [152, 101], [150, 109], [166, 82], [178, 100], [177, 117], [175, 118], [170, 107], [155, 103]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "65467_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the bottle from the table and put it inside the clear bowl, turn off the white extension cable, take out one bottle from the clear bowl and place it on the left side of the table', and now you are performing subtask 'place the bottle on the left side of the table.'\nStart at [253, 110]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[253, 110], [224, 107], [229, 88], [207, 93], [190, 109], [172, 84], [157, 110], [147, 118], [148, 108], [148, 108]]}" + } + ], + "images": "65467_exterior_image_1_left#265", + "gt": "[[253, 110], [224, 107], [229, 88], [207, 93], [190, 109], [172, 84], [157, 110], [147, 118], [148, 108], [148, 108]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0081_user_0007_scene_0003_cfg_0005_036422060215#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the leg of the glasses (with one hand)', and now you are performing subtask 'pick up the glasses on the table, fold the legs of the glasses to unfold them.'\nFrom start point [286, 108], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[286, 108], [268, 134], [253, 142], [243, 173], [239, 165], [230, 170], [227, 111], [225, 107], [219, 118], [219, 118]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0081_user_0007_scene_0003_cfg_0005_036422060215#0.jpg", + "gt": "[[286, 108], [268, 134], [253, 142], [243, 173], [239, 165], [230, 170], [227, 111], [225, 107], [219, 118], [219, 118]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0073_user_0007_scene_0001_cfg_0005_104122063678#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the things in the drawer', and now you are performing subtask 'place the cube in the drawer, push the handle of the drawer to close the drawer.'\nYou begin at [328, 213]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[328, 213], [322, 199], [325, 174], [321, 164], [311, 179], [314, 192], [323, 203], [320, 193], [322, 151], [330, 143]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0073_user_0007_scene_0001_cfg_0005_104122063678#870.jpg", + "gt": "[[328, 213], [322, 199], [325, 174], [321, 164], [311, 179], [314, 192], [323, 203], [320, 193], [322, 151], [330, 143]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0006_user_0010_scene_0009_cfg_0005_104122063678#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'push the small block from below the table to above the table', and now you are performing subtask 'push the small block from below the table to above the table.'\nStarting at [323, 132], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[323, 132], [313, 293], [291, 315], [284, 308], [260, 208], [276, 207], [274, 193], [284, 214], [270, 191], [303, 168]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0006_user_0010_scene_0009_cfg_0005_104122063678#0.jpg", + "gt": "[[323, 132], [313, 293], [291, 315], [284, 308], [260, 208], [276, 207], [274, 193], [284, 214], [270, 191], [303, 168]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0059_user_0007_scene_0003_cfg_0005_104122063678#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn the knob to increase the volume of the speaker', and now you are performing subtask 'turn the knob to increase the volume of the speaker.'\nYour initial coordinate is [323, 132]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[323, 132], [320, 139], [327, 155], [319, 184], [322, 132], [326, 164], [276, 177], [270, 185], [270, 203], [274, 202]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0059_user_0007_scene_0003_cfg_0005_104122063678#0.jpg", + "gt": "[[323, 132], [320, 139], [327, 155], [319, 184], [322, 132], [326, 164], [276, 177], [270, 185], [270, 203], [274, 202]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0066_user_0014_scene_0005_cfg_0007_104122061602#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with large Megabloks for the nth time with n blocks', and now you are performing subtask 'place the block on the block board, pick up the block on the flat surface, transfer the block from the flat surface to the block board, place the block on the block board.'\nThe trajectory starts at [434, 177]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[434, 177], [456, 166], [498, 165], [505, 172], [504, 181], [503, 163], [479, 147], [440, 142], [425, 143], [414, 156]]}" + } + ], + "images": "RH20T_cfg7_task_0066_user_0014_scene_0005_cfg_0007_104122061602#337", + "gt": "[[434, 177], [456, 166], [498, 165], [505, 172], [504, 181], [503, 163], [479, 147], [440, 142], [425, 143], [414, 156]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "31421_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the blue object on the dish rack', and now you are performing subtask 'put the blue object on the dish rack.'\nBegin at [231, 34] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[231, 34], [217, 40], [223, 100], [210, 95], [218, 108], [227, 87], [234, 107], [213, 58], [165, 69], [211, 46]]}" + } + ], + "images": "31421_exterior_image_1_left#0", + "gt": "[[231, 34], [217, 40], [223, 100], [210, 95], [218, 108], [227, 87], [234, 107], [213, 58], [165, 69], [211, 46]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0104_user_0020_scene_0004_cfg_0006_104122064161#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'drag the plate back after holding it down', and now you are performing subtask 'drag the plate back after holding it down.'\nYou begin at [338, 111]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[338, 111], [351, 107], [355, 116], [369, 121], [373, 226], [379, 188], [362, 156], [329, 126], [322, 106], [327, 105]]}" + } + ], + "images": "RH20T_cfg6_task_0104_user_0020_scene_0004_cfg_0006_104122064161#0", + "gt": "[[338, 111], [351, 107], [355, 116], [369, 121], [373, 226], [379, 188], [362, 156], [329, 126], [322, 106], [327, 105]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "66771_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the yellow item and put it on the right side of the table', and now you are performing subtask 'pick up the yellow item and put it on the right side of the table.'\nWith start location [287, 1], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[287, 1], [222, 104], [212, 108], [221, 67], [232, 53], [244, 60], [242, 76], [241, 54], [221, 37], [257, 38]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/66771_exterior_image_2_left#0.jpg", + "gt": "[[287, 1], [222, 104], [212, 108], [221, 67], [232, 53], [244, 60], [242, 76], [241, 54], [221, 37], [257, 38]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "72609_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the marker in the cup', and now you are performing subtask 'put the marker in the cup.'\nStarting at [168.0, 5.5], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[168.0, 5.5], [169.0, 31.5], [186.0, 48.5], [187.0, 97.5], [197.0, 33.5], [256.0, 53.5], [242.0, 60.5], [230.0, 86.5], [212.0, 95.5], [236.0, 62.5]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/72609_exterior_image_1_left#0.jpg", + "gt": "[[168.0, 5.5], [169.0, 31.5], [186.0, 48.5], [187.0, 97.5], [197.0, 33.5], [256.0, 53.5], [242.0, 60.5], [230.0, 86.5], [212.0, 95.5], [236.0, 62.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "19146_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the blue towel from the left to the right', and now you are performing subtask 'move the blue towel from the left to the right.'\nBegin at [148, 1] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[148, 1], [131, 49], [134, 63], [131, 62], [133, 66], [129, 68], [131, 76], [144, 83], [164, 87], [148, 75]]}" + } + ], + "images": "19146_exterior_image_1_left#0", + "gt": "[[148, 1], [131, 49], [134, 63], [131, 62], [133, 66], [129, 68], [131, 76], [144, 83], [164, 87], [148, 75]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "51625_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn on the second switch from the main switch on the adapter', and now you are performing subtask 'turn on the second switch from the main switch on the adapter.'\nYou begin at [151, 25]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[151, 25], [164, 24], [173, 32], [176, 52], [170, 59], [174, 61], [174, 74], [179, 72], [182, 80], [176, 53]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/51625_exterior_image_2_left#0.jpg", + "gt": "[[151, 25], [164, 24], [173, 32], [176, 52], [170, 59], [174, 61], [174, 74], [179, 72], [182, 80], [176, 53]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0005_user_0008_scene_0006_cfg_0001_750612070851#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'approach and touch the side of the small block', and now you are performing subtask 'approach and touch the side of the small block.'\nThe trajectory starts at [329, 155]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[329, 155], [335, 158], [320, 212], [307, 231], [267, 245], [246, 272], [222, 264], [228, 287], [216, 279], [292, 246]]}" + } + ], + "images": "RH20T_cfg1_task_0005_user_0008_scene_0006_cfg_0001_750612070851#0", + "gt": "[[329, 155], [335, 158], [320, 212], [307, 231], [267, 245], [246, 272], [222, 264], [228, 287], [216, 279], [292, 246]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "60714_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the green sachet in the bag', and now you are performing subtask 'put the green sachet in the bag.'\nYour initial coordinate is [165, 122]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[165, 122], [142, 160], [163, 151], [170, 158], [166, 180], [143, 115], [105, 97], [96, 84], [104, 94], [100, 99]]}" + } + ], + "images": "60714_exterior_image_2_left#0", + "gt": "[[165, 122], [142, 160], [163, 151], [170, 158], [166, 180], [143, 115], [105, 97], [96, 84], [104, 94], [100, 99]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0013_user_0014_scene_0007_cfg_0006_037522061512#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'place the block on the scale', and now you are performing subtask 'place the block on the scale.'\nYour initial coordinate is [257, 83]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[257, 83], [284, 117], [296, 151], [307, 163], [291, 152], [274, 151], [262, 167], [262, 186], [268, 132], [288, 81]]}" + } + ], + "images": "RH20T_cfg6_task_0013_user_0014_scene_0007_cfg_0006_037522061512#0", + "gt": "[[257, 83], [284, 117], [296, 151], [307, 163], [291, 152], [274, 151], [262, 167], [262, 186], [268, 132], [288, 81]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0029_user_0020_scene_0009_cfg_0007_104122064161#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the drawer', and now you are performing subtask 'open the drawer.'\nBegin at [337, 115] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[337, 115], [373, 107], [369, 115], [388, 127], [381, 132], [406, 153], [393, 97], [384, 92], [369, 107], [369, 107]]}" + } + ], + "images": "RH20T_cfg7_task_0029_user_0020_scene_0009_cfg_0007_104122064161#0", + "gt": "[[337, 115], [373, 107], [369, 115], [388, 127], [381, 132], [406, 153], [393, 97], [384, 92], [369, 107], [369, 107]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "12567_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the bottle on the left side of the table', and now you are performing subtask 'put the bottle on the left side of the table.'\nStarting at [230, 0], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[230, 0], [163, 30], [163, 69], [167, 39], [154, 40], [123, 73], [145, 81], [148, 59], [141, 64], [141, 64]]}" + } + ], + "images": "12567_exterior_image_1_left#0", + "gt": "[[230, 0], [163, 30], [163, 69], [167, 39], [154, 40], [123, 73], [145, 81], [148, 59], [141, 64], [141, 64]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "34116_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the black spoon from the cutlery box', and now you are performing subtask 'remove the black spoon from the cutlery box.'\nYou start from [110.5, 66.5]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[110.5, 66.5], [153.5, 52.5], [191.5, 73.5], [206.5, 91.5], [188.5, 73.5], [187.5, 58.5], [208.5, 49.5], [237.5, 66.5], [248.5, 86.5], [195.5, 55.5]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/34116_exterior_image_1_left#0.jpg", + "gt": "[[110.5, 66.5], [153.5, 52.5], [191.5, 73.5], [206.5, 91.5], [188.5, 73.5], [187.5, 58.5], [208.5, 49.5], [237.5, 66.5], [248.5, 86.5], [195.5, 55.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0032_user_0016_scene_0006_cfg_0004_104122062295#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'slide the outer casing onto the gift box', and now you are performing subtask 'push the gift box lid on the desktop.'\nYou begin at [351, 244]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[351, 244], [404, 201], [372, 195], [351, 255], [357, 302], [311, 240], [255, 243], [251, 198], [233, 201], [233, 201]]}" + } + ], + "images": "RH20T_cfg4_task_0032_user_0016_scene_0006_cfg_0004_104122062295#221", + "gt": "[[351, 244], [404, 201], [372, 195], [351, 255], [357, 302], [311, 240], [255, 243], [251, 198], [233, 201], [233, 201]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0003_user_0014_scene_0010_cfg_0006_037522061512#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press three buttons from left to right in sequence', and now you are performing subtask 'press the green button in the middle, press the yellow button at the top.'\nBegin at [249, 95] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[249, 95], [239, 94], [227, 102], [219, 124], [220, 127], [221, 124], [218, 121], [217, 115], [219, 108], [219, 108]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg6_task_0003_user_0014_scene_0010_cfg_0006_037522061512#157.jpg", + "gt": "[[249, 95], [239, 94], [227, 102], [219, 124], [220, 127], [221, 124], [218, 121], [217, 115], [219, 108], [219, 108]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "84821_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the drawer', and now you are performing subtask 'open the drawer.'\nYou begin at [137, 71]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[137, 71], [143, 64], [144, 91], [160, 93], [158, 99], [169, 100], [157, 95], [124, 106], [112, 54], [118, 49]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/84821_exterior_image_1_left#0.jpg", + "gt": "[[137, 71], [143, 64], [144, 91], [160, 93], [158, 99], [169, 100], [157, 95], [124, 106], [112, 54], [118, 49]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0132_user_0020_scene_0004_cfg_0006_104122064161#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks into a cross shape', and now you are performing subtask 'pick up the first block from the table, twist the block counterclockwise, place the first block to the left of the second block.'\nFrom start point [338, 111], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[338, 111], [356, 143], [370, 139], [380, 144], [424, 184], [427, 196], [443, 190], [444, 205], [430, 211], [425, 228]]}" + } + ], + "images": "RH20T_cfg6_task_0132_user_0020_scene_0004_cfg_0006_104122064161#0", + "gt": "[[338, 111], [356, 143], [370, 139], [380, 144], [424, 184], [427, 196], [443, 190], [444, 205], [430, 211], [425, 228]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg2_task_0054_user_0007_scene_0009_cfg_0002_036422060215#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'grasp the moving object', and now you are performing subtask 'grasp the moving object.'\nBegin at [282, 177] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[282, 177], [265, 186], [259, 180], [238, 180], [257, 155], [254, 146], [251, 160], [248, 152], [270, 178], [278, 178]]}" + } + ], + "images": "RH20T_cfg2_task_0054_user_0007_scene_0009_cfg_0002_036422060215#0", + "gt": "[[282, 177], [265, 186], [259, 180], [238, 180], [257, 155], [254, 146], [251, 160], [248, 152], [270, 178], [278, 178]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0066_user_0016_scene_0003_cfg_0004_104122062823#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'building blocks', and now you are performing subtask 'place the red block on the block board, pick up the blue block from the table, transfer the blue block from the table to the block board, place the blue block on the block board.'\nYou start from [361, 62]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[361, 62], [345, 40], [351, 66], [353, 47], [345, 47], [317, 101], [307, 105], [311, 115], [332, 59], [325, 53]]}" + } + ], + "images": "RH20T_cfg4_task_0066_user_0016_scene_0003_cfg_0004_104122062823#297", + "gt": "[[361, 62], [345, 40], [351, 66], [353, 47], [345, 47], [317, 101], [307, 105], [311, 115], [332, 59], [325, 53]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "42894_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pull the white bowl to the left, take out the fork and the spoon from the bowl, then place them on the table, move the white cup to the left', and now you are performing subtask 'pick up the fork from the white bowl.'\nYour starting position is [130, 78]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[130, 78], [134, 128], [137, 129], [138, 135], [132, 122], [125, 115], [124, 117], [127, 110], [127, 99], [121, 90]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/42894_exterior_image_1_left#0.jpg", + "gt": "[[130, 78], [134, 128], [137, 129], [138, 135], [132, 122], [125, 115], [124, 117], [127, 110], [127, 99], [121, 90]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "45040_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the drawer and put some of the plush toys in the drawer and close it', and now you are performing subtask 'place the watermelon plush toy in the drawer.'\nYou start from [150.5, 41.5]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[150.5, 41.5], [123.5, 38.5], [96.5, 43.5], [89.5, 51.5], [91.5, 58.5], [103.5, 43.5], [130.5, 52.5], [128.5, 48.5], [136.5, 47.5], [134.5, 55.5]]}" + } + ], + "images": "45040_exterior_image_1_left#455", + "gt": "[[150.5, 41.5], [123.5, 38.5], [96.5, 43.5], [89.5, 51.5], [91.5, 58.5], [103.5, 43.5], [130.5, 52.5], [128.5, 48.5], [136.5, 47.5], [134.5, 55.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "13458_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the white pot from the right side of the stove to the left', and now you are performing subtask 'move the white pot from the right side of the stove to the left.'\nThe trajectory starts at [140, 116]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[140, 116], [137, 109], [155, 107], [158, 110], [154, 111], [145, 107], [128, 106], [131, 105], [132, 101], [131, 83]]}" + } + ], + "images": "13458_exterior_image_1_left#0", + "gt": "[[140, 116], [137, 109], [155, 107], [158, 110], [154, 111], [145, 107], [128, 106], [131, 105], [132, 101], [131, 83]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "54621_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'rotate the faucet counterclockwise, press the button on the faucet', and now you are performing subtask 'press the button on the faucet.'\nYou start from [134.0, 80.5]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[134.0, 80.5], [104.0, 104.5], [108.0, 111.5], [125.0, 111.5], [118.0, 87.5], [132.0, 64.5], [167.0, 60.5], [193.0, 67.5], [187.0, 72.5], [187.0, 72.5]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/54621_exterior_image_1_left#236.jpg", + "gt": "[[134.0, 80.5], [104.0, 104.5], [108.0, 111.5], [125.0, 111.5], [118.0, 87.5], [132.0, 64.5], [167.0, 60.5], [193.0, 67.5], [187.0, 72.5], [187.0, 72.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "592_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the drawer then place the green pear inside the drawer', and now you are performing subtask 'pick up the green pear from the box on the countertop.'\nWith start location [91, 95], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[91, 95], [104, 48], [97, 56], [102, 51], [193, 125], [198, 144], [157, 172], [202, 106], [215, 71], [208, 63]]}" + } + ], + "images": "592_exterior_image_2_left#0", + "gt": "[[91, 95], [104, 48], [97, 56], [102, 51], [193, 125], [198, 144], [157, 172], [202, 106], [215, 71], [208, 63]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "49729_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'place the glass lid on the black pot', and now you are performing subtask 'place the glass lid on the black pot.'\nYou begin at [312, 56]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[312, 56], [266, 85], [222, 154], [224, 129], [243, 108], [254, 106], [255, 113], [250, 115], [254, 106], [254, 106]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/49729_exterior_image_2_left#0.jpg", + "gt": "[[312, 56], [266, 85], [222, 154], [224, 129], [243, 108], [254, 106], [255, 113], [250, 115], [254, 106], [254, 106]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "78997_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the purple object from the counter and put it on top of the shelf', and now you are performing subtask 'pick up the purple object from the counter and put it on top of the shelf.'\nStart at [109.5, 93.5]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[109.5, 93.5], [124.5, 130.5], [117.5, 145.5], [105.5, 132.5], [104.5, 69.5], [116.5, 45.5], [133.5, 53.5], [125.5, 48.5], [106.5, 71.5], [101.5, 97.5]]}" + } + ], + "images": "78997_exterior_image_1_left#0", + "gt": "[[109.5, 93.5], [124.5, 130.5], [117.5, 145.5], [105.5, 132.5], [104.5, 69.5], [116.5, 45.5], [133.5, 53.5], [125.5, 48.5], [106.5, 71.5], [101.5, 97.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "57764_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the black object to the bottom right corner of the countertop', and now you are performing subtask 'move the black object to the bottom right corner of the countertop.'\nWith start location [101.5, 1.5], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[101.5, 1.5], [158.5, 15.5], [150.5, 18.5], [150.5, 32.5], [155.5, 14.5], [175.5, 3.5], [248.5, 1.5], [259.5, 16.5], [242.5, 41.5], [224.5, 0.0]]}" + } + ], + "images": "57764_exterior_image_1_left#0", + "gt": "[[101.5, 1.5], [158.5, 15.5], [150.5, 18.5], [150.5, 32.5], [155.5, 14.5], [175.5, 3.5], [248.5, 1.5], [259.5, 16.5], [242.5, 41.5], [224.5, 0.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0047_user_0007_scene_0009_cfg_0005_036422060215#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the cup off the cup rack', and now you are performing subtask 'take the cup off the cup rack.'\nThe trajectory starts at [286, 108]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[286, 108], [264, 101], [252, 111], [167, 127], [171, 105], [181, 93], [202, 82], [240, 81], [254, 99], [245, 130]]}" + } + ], + "images": "RH20T_cfg5_task_0047_user_0007_scene_0009_cfg_0005_036422060215#0", + "gt": "[[286, 108], [264, 101], [252, 111], [167, 127], [171, 105], [181, 93], [202, 82], [240, 81], [254, 99], [245, 130]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0053_user_0014_scene_0003_cfg_0001_039422060546#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'use a clamp', and now you are performing subtask 'use a clamp.'\nFrom start point [265, 123], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[265, 123], [286, 117], [300, 61], [336, 26], [316, 61], [324, 81], [316, 92], [309, 80], [320, 99], [348, 36]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0053_user_0014_scene_0003_cfg_0001_039422060546#0.jpg", + "gt": "[[265, 123], [286, 117], [300, 61], [336, 26], [316, 61], [324, 81], [316, 92], [309, 80], [320, 99], [348, 36]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0037_user_0020_scene_0009_cfg_0006_104122061602#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'place the first block on the second block, pick up the third block from the table, transfer the third block from the table to the first block, place the third block on the first block, pick up the fourth block from the table.'\nYou start from [416, 126]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[416, 126], [408, 91], [399, 124], [406, 100], [427, 100], [443, 116], [448, 147], [458, 90], [481, 95], [489, 119]]}" + } + ], + "images": "RH20T_cfg6_task_0037_user_0020_scene_0009_cfg_0006_104122061602#553", + "gt": "[[416, 126], [408, 91], [399, 124], [406, 100], [427, 100], [443, 116], [448, 147], [458, 90], [481, 95], [489, 119]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "48957_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the right drawer', and now you are performing subtask 'open the right drawer.'\nThe trajectory starts at [149.5, 41.0]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[149.5, 41.0], [110.5, 73.0], [126.5, 96.0], [128.5, 93.0], [139.5, 94.0], [145.5, 89.0], [129.5, 104.0], [119.5, 100.0], [120.5, 89.0], [117.5, 80.0]]}" + } + ], + "images": "48957_exterior_image_1_left#0", + "gt": "[[149.5, 41.0], [110.5, 73.0], [126.5, 96.0], [128.5, 93.0], [139.5, 94.0], [145.5, 89.0], [129.5, 104.0], [119.5, 100.0], [120.5, 89.0], [117.5, 80.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "51525_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close the microwave door, move the pink jar on the counter', and now you are performing subtask 'close the microwave door.'\nYou begin at [31, 53]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[31, 53], [36, 49], [51, 46], [94, 29], [84, 33], [91, 32], [127, 50], [136, 73], [166, 68], [166, 68]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/51525_exterior_image_2_left#0.jpg", + "gt": "[[31, 53], [36, 49], [51, 46], [94, 29], [84, 33], [91, 32], [127, 50], [136, 73], [166, 68], [166, 68]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0037_user_0014_scene_0009_cfg_0007_104122061330#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'pick up the first block from the desktop, transfer the block from the desktop to the second block, place the block on the second block.'\nBegin at [266, 103] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[266, 103], [314, 103], [320, 101], [325, 86], [347, 77], [361, 100], [357, 109], [359, 98], [364, 102], [365, 110]]}" + } + ], + "images": "RH20T_cfg7_task_0037_user_0014_scene_0009_cfg_0007_104122061330#0", + "gt": "[[266, 103], [314, 103], [320, 101], [325, 86], [347, 77], [361, 100], [357, 109], [359, 98], [364, 102], [365, 110]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "1087_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the purple and orange plushies from the box', and now you are performing subtask 'throw the purple plush toy in the plate.'\nThe trajectory starts at [133, 47]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[133, 47], [138, 73], [161, 108], [160, 118], [158, 111], [164, 104], [197, 110], [211, 109], [212, 104], [204, 104]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/1087_exterior_image_2_left#0.jpg", + "gt": "[[133, 47], [138, 73], [161, 108], [160, 118], [158, 111], [164, 104], [197, 110], [211, 109], [212, 104], [204, 104]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "69016_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn on the second switch from the left', and now you are performing subtask 'turn on the second switch from the left.'\nStarting at [125, 39], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[125, 39], [151, 27], [167, 34], [172, 40], [170, 68], [176, 70], [173, 73], [177, 79], [179, 74], [174, 54]]}" + } + ], + "images": "69016_exterior_image_2_left#0", + "gt": "[[125, 39], [151, 27], [167, 34], [172, 40], [170, 68], [176, 70], [173, 73], [177, 79], [179, 74], [174, 54]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0037_user_0020_scene_0009_cfg_0006_104122061330#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'place the fourth block on the third block, pick up the fifth block from the table, transfer the fifth block from the table to the fourth block, place the fifth block on the fourth block.'\nFrom start point [294, 123], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[294, 123], [284, 211], [257, 241], [272, 186], [259, 188], [270, 167], [258, 149], [261, 129], [287, 104], [261, 105]]}" + } + ], + "images": "RH20T_cfg6_task_0037_user_0020_scene_0009_cfg_0006_104122061330#1169", + "gt": "[[294, 123], [284, 211], [257, 241], [272, 186], [259, 188], [270, 167], [258, 149], [261, 129], [287, 104], [261, 105]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg3_task_0058_user_0010_scene_0006_cfg_0003_104122062823#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn off the power strips', and now you are performing subtask 'press the third button of the power strip, press the fourth button of the power strip.'\nYou start from [129, 50]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[129, 50], [113, 36], [129, 41], [123, 44], [115, 27], [121, 15], [176, 0], [187, 0], [182, 9], [177, 8]]}" + } + ], + "images": "RH20T_cfg3_task_0058_user_0010_scene_0006_cfg_0003_104122062823#221", + "gt": "[[129, 50], [113, 36], [129, 41], [123, 44], [115, 27], [121, 15], [176, 0], [187, 0], [182, 9], [177, 8]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0029_user_0010_scene_0006_cfg_0005_036422060215#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'grasp the handle and open the drawer', and now you are performing subtask 'grab the handle of the drawer.'\nYou begin at [286, 108]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[286, 108], [290, 106], [295, 93], [286, 100], [261, 112], [261, 108], [264, 104], [269, 113], [257, 121], [256, 124]]}" + } + ], + "images": "RH20T_cfg5_task_0029_user_0010_scene_0006_cfg_0005_036422060215#0", + "gt": "[[286, 108], [290, 106], [295, 93], [286, 100], [261, 112], [261, 108], [264, 104], [269, 113], [257, 121], [256, 124]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0094_user_0007_scene_0002_cfg_0005_104122063678#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open a box', and now you are performing subtask 'push the third box lid, push the fourth box lid.'\nFrom start point [345, 138], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[345, 138], [334, 131], [329, 133], [317, 132], [323, 118], [327, 116], [323, 94], [322, 100], [323, 87], [325, 108]]}" + } + ], + "images": "RH20T_cfg5_task_0094_user_0007_scene_0002_cfg_0005_104122063678#403", + "gt": "[[345, 138], [334, 131], [329, 133], [317, 132], [323, 118], [327, 116], [323, 94], [322, 100], [323, 87], [325, 108]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0038_user_0015_scene_0010_cfg_0001_750612070851#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the cup', and now you are performing subtask 'pick up the cup.'\nYour starting position is [315, 161]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[315, 161], [338, 206], [329, 183], [353, 188], [361, 208], [364, 201], [330, 62], [337, 29], [330, 16], [352, 17]]}" + } + ], + "images": "RH20T_cfg1_task_0038_user_0015_scene_0010_cfg_0001_750612070851#0", + "gt": "[[315, 161], [338, 206], [329, 183], [353, 188], [361, 208], [364, 201], [330, 62], [337, 29], [330, 16], [352, 17]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "9303_exterior_image_1_left#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the cloth', and now you are performing subtask 'fold the cloth again on the table.'\nFrom start point [221, 122], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[221, 122], [227, 107], [224, 99], [206, 97], [183, 106], [197, 117], [183, 143], [191, 115], [187, 102], [187, 113]]}" + } + ], + "images": "9303_exterior_image_1_left#467", + "gt": "[[221, 122], [227, 107], [224, 99], [206, 97], [183, 106], [197, 117], [183, 143], [191, 115], [187, 102], [187, 113]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "46244_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the can from the sink and put it on the counter', and now you are performing subtask 'pick up the can from the sink and put it on the counter.'\nYou begin at [235, 97]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[235, 97], [233, 100], [244, 109], [250, 129], [248, 131], [241, 109], [217, 115], [218, 127], [220, 113], [228, 107]]}" + } + ], + "images": "46244_exterior_image_2_left#0", + "gt": "[[235, 97], [233, 100], [244, 109], [250, 129], [248, 131], [241, 109], [217, 115], [218, 127], [220, 113], [228, 107]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0028_user_0020_scene_0003_cfg_0007_104122064161#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'grasp the handle and close the drawer', and now you are performing subtask 'grasp the handle and close the drawer.'\nYour starting position is [337, 115]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[337, 115], [355, 145], [370, 144], [380, 152], [399, 150], [366, 111], [377, 113], [373, 95], [368, 93], [361, 107]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg7_task_0028_user_0020_scene_0003_cfg_0007_104122064161#0.jpg", + "gt": "[[337, 115], [355, 145], [370, 144], [380, 152], [399, 150], [366, 111], [377, 113], [373, 95], [368, 93], [361, 107]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0010_user_0010_scene_0007_cfg_0005_104422070044#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'place the handset of the telephone on the corresponding phone cradle', and now you are performing subtask 'place the handset of the telephone on the corresponding phone cradle.'\nYou start from [374, 132]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[374, 132], [383, 142], [385, 163], [414, 172], [409, 221], [419, 237], [412, 219], [377, 194], [378, 185], [375, 190]]}" + } + ], + "images": "RH20T_cfg5_task_0010_user_0010_scene_0007_cfg_0005_104422070044#0", + "gt": "[[374, 132], [383, 142], [385, 163], [414, 172], [409, 221], [419, 237], [412, 219], [377, 194], [378, 185], [375, 190]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0046_user_0020_scene_0010_cfg_0006_104122063633#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the cup on the cup rack', and now you are performing subtask 'put the cup on the cup rack.'\nBegin at [234, 121] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[234, 121], [198, 138], [170, 129], [168, 159], [157, 141], [159, 156], [161, 146], [177, 165], [182, 138], [190, 143]]}" + } + ], + "images": "RH20T_cfg6_task_0046_user_0020_scene_0010_cfg_0006_104122063633#0", + "gt": "[[234, 121], [198, 138], [170, 129], [168, 159], [157, 141], [159, 156], [161, 146], [177, 165], [182, 138], [190, 143]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0105_user_0020_scene_0001_cfg_0006_104122063633#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the object on the shelf', and now you are performing subtask 'pick up the cup on the table, transfer the cup from the table to the shelf, place the cup on the shelf.'\nYour starting position is [172, 82]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[172, 82], [166, 103], [170, 111], [130, 164], [138, 169], [130, 134], [143, 69], [136, 38], [137, 0], [155, 0]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg6_task_0105_user_0020_scene_0001_cfg_0006_104122063633#353.jpg", + "gt": "[[172, 82], [166, 103], [170, 111], [130, 164], [138, 169], [130, 134], [143, 69], [136, 38], [137, 0], [155, 0]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0096_user_0014_scene_0001_cfg_0001_038522063145#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take something out of a drawer', and now you are performing subtask 'pull the drawer handle to the outside of the table, pick up the object from the drawer, transfer the object from the drawer to the top of the table, place the object on the table.'\nYour starting position is [394, 65]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[394, 65], [377, 39], [356, 71], [354, 58], [375, 29], [418, 41], [430, 83], [413, 119], [420, 85], [413, 56]]}" + } + ], + "images": "RH20T_cfg1_task_0096_user_0014_scene_0001_cfg_0001_038522063145#164", + "gt": "[[394, 65], [377, 39], [356, 71], [354, 58], [375, 29], [418, 41], [430, 83], [413, 119], [420, 85], [413, 56]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "19986_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the green object in the bowl', and now you are performing subtask 'put the green object in the bowl.'\nFrom start point [201, 0], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[201, 0], [205, 18], [218, 43], [214, 62], [206, 71], [212, 51], [225, 54], [231, 66], [217, 106], [215, 71]]}" + } + ], + "images": "19986_exterior_image_1_left#0", + "gt": "[[201, 0], [205, 18], [218, 43], [214, 62], [206, 71], [212, 51], [225, 54], [231, 66], [217, 106], [215, 71]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "51525_exterior_image_2_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close the microwave door, move the pink jar on the counter', and now you are performing subtask 'pick up the pink jar on the microwave.'\nFrom start point [156, 22], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[156, 22], [179, 13], [161, 21], [164, 21], [164, 23], [178, 19], [207, 32], [210, 46], [214, 49], [212, 54]]}" + } + ], + "images": "51525_exterior_image_2_left#96", + "gt": "[[156, 22], [179, 13], [161, 21], [164, 21], [164, 23], [178, 19], [207, 32], [210, 46], [214, 49], [212, 54]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "20753_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'wipe the inside of the pan with a white towel', and now you are performing subtask 'wipe the inside of the pan with a white towel.'\nYour initial coordinate is [146.5, 19.0]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[146.5, 19.0], [155.5, 29.0], [146.5, 53.0], [130.5, 54.0], [120.5, 65.0], [139.5, 48.0], [134.5, 76.0], [167.5, 83.0], [169.5, 52.0], [122.5, 59.0]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/20753_exterior_image_1_left#0.jpg", + "gt": "[[146.5, 19.0], [155.5, 29.0], [146.5, 53.0], [130.5, 54.0], [120.5, 65.0], [139.5, 48.0], [134.5, 76.0], [167.5, 83.0], [169.5, 52.0], [122.5, 59.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0037_user_0007_scene_0004_cfg_0005_105422061350#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'pick up the first block from the surface, place the first block on the vertical stack on the surface, pick up the second block from the surface.'\nYou begin at [276, 47]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[276, 47], [257, 14], [258, 36], [252, 49], [263, 52], [263, 59], [260, 75], [261, 62], [246, 91], [245, 107]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0037_user_0007_scene_0004_cfg_0005_105422061350#0.jpg", + "gt": "[[276, 47], [257, 14], [258, 36], [252, 49], [263, 52], [263, 59], [260, 75], [261, 62], [246, 91], [245, 107]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "30469_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the drawer, then take out a plush toy from the drawer, then close the drawer', and now you are performing subtask 'pull the handle of the drawer to open the drawer.'\nStart at [247, 79]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[247, 79], [214, 65], [185, 93], [196, 99], [199, 87], [179, 96], [209, 86], [190, 93], [215, 103], [220, 82]]}" + } + ], + "images": "30469_exterior_image_1_left#0", + "gt": "[[247, 79], [214, 65], [185, 93], [196, 99], [199, 87], [179, 96], [209, 86], [190, 93], [215, 103], [220, 82]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "24404_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the blue can's bottom drawer and remove the green object', and now you are performing subtask 'pull the drawer completely open.'\nThe trajectory starts at [191, 71]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[191, 71], [188, 75], [188, 85], [185, 87], [192, 92], [210, 92], [218, 89], [217, 81], [212, 75], [201, 70]]}" + } + ], + "images": "24404_exterior_image_1_left#143", + "gt": "[[191, 71], [188, 75], [188, 85], [185, 87], [192, 92], [210, 92], [218, 89], [217, 81], [212, 75], [201, 70]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "65596_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'use a cloth to wipe the counter', and now you are performing subtask 'use a cloth to wipe the counter.'\nYour starting position is [191, 62]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[191, 62], [188, 94], [201, 102], [202, 117], [233, 115], [235, 125], [212, 115], [239, 133], [182, 95], [182, 95]]}" + } + ], + "images": "65596_exterior_image_2_left#0", + "gt": "[[191, 62], [188, 94], [201, 102], [202, 117], [233, 115], [235, 125], [212, 115], [239, 133], [182, 95], [182, 95]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0121_user_0010_scene_0002_cfg_0001_819112070044#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'taking out the light bulb by rotating it', and now you are performing subtask 'twist the light bulb counterclockwise to loosen it.'\nFrom start point [396, 133], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[396, 133], [397, 128], [400, 126], [399, 131], [396, 133], [399, 134], [398, 133], [396, 134], [395, 132], [395, 132]]}" + } + ], + "images": "RH20T_cfg1_task_0121_user_0010_scene_0002_cfg_0001_819112070044#203", + "gt": "[[396, 133], [397, 128], [400, 126], [399, 131], [396, 133], [399, 134], [398, 133], [396, 134], [395, 132], [395, 132]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0044_user_0014_scene_0005_cfg_0007_104122061602#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up a bag of things', and now you are performing subtask 'pick up a bag of things.'\nYour initial coordinate is [448, 116]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[448, 116], [474, 149], [508, 173], [518, 217], [511, 217], [508, 197], [501, 186], [495, 165], [468, 114], [472, 90]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg7_task_0044_user_0014_scene_0005_cfg_0007_104122061602#0.jpg", + "gt": "[[448, 116], [474, 149], [508, 173], [518, 217], [511, 217], [508, 197], [501, 186], [495, 165], [468, 114], [472, 90]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "32646_exterior_image_2_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the cloth on the table', and now you are performing subtask 'again unfold the cloth on the table.'\nFrom start point [201, 105], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[201, 105], [203, 108], [201, 115], [201, 112], [189, 107], [174, 94], [168, 93], [204, 93], [205, 91], [206, 93]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/32646_exterior_image_2_left#143.jpg", + "gt": "[[201, 105], [203, 108], [201, 115], [201, 112], [189, 107], [174, 94], [168, 93], [204, 93], [205, 91], [206, 93]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0029_user_0020_scene_0010_cfg_0007_104122063633#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'grasp the handle and open the drawer', and now you are performing subtask 'grasp the handle and open the drawer.'\nThe trajectory starts at [234, 121]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[234, 121], [210, 150], [217, 173], [209, 188], [161, 210], [153, 232], [181, 178], [190, 146], [189, 129], [203, 116]]}" + } + ], + "images": "RH20T_cfg7_task_0029_user_0020_scene_0010_cfg_0007_104122063633#0", + "gt": "[[234, 121], [210, 150], [217, 173], [209, 188], [161, 210], [153, 232], [181, 178], [190, 146], [189, 129], [203, 116]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "88528_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the glue stick inside the mug cup', and now you are performing subtask 'put the glue stick inside the mug cup.'\nYour starting position is [267.0, 0.0]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[267.0, 0.0], [228.0, 42.0], [212.0, 69.0], [216.0, 73.0], [197.0, 82.0], [195.0, 97.0], [169.0, 67.0], [150.0, 71.0], [146.0, 88.0], [146.0, 72.0]]}" + } + ], + "images": "88528_exterior_image_1_left#0", + "gt": "[[267.0, 0.0], [228.0, 42.0], [212.0, 69.0], [216.0, 73.0], [197.0, 82.0], [195.0, 97.0], [169.0, 67.0], [150.0, 71.0], [146.0, 88.0], [146.0, 72.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "33949_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the colourless bowl', and now you are performing subtask 'open the colourless bowl.'\nThe trajectory starts at [43, 54]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[43, 54], [56, 50], [83, 54], [90, 63], [95, 89], [100, 88], [105, 96], [101, 73], [108, 50], [81, 43]]}" + } + ], + "images": "33949_exterior_image_2_left#0", + "gt": "[[43, 54], [56, 50], [83, 54], [90, 63], [95, 89], [100, 88], [105, 96], [101, 73], [108, 50], [81, 43]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0020_user_0016_scene_0002_cfg_0004_038522062288#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn on the desk lamp by pressing the button', and now you are performing subtask 'press the button on the desk lamp to turn on the light.'\nWith start location [317, 176], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[317, 176], [322, 189], [320, 194], [328, 199], [321, 208], [328, 208], [318, 195], [296, 189], [259, 191], [259, 198]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg4_task_0020_user_0016_scene_0002_cfg_0004_038522062288#131.jpg", + "gt": "[[317, 176], [322, 189], [320, 194], [328, 199], [321, 208], [328, 208], [318, 195], [296, 189], [259, 191], [259, 198]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "15475_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the can on the counter from the sink', and now you are performing subtask 'put the can on the counter from the sink.'\nYour initial coordinate is [80, 77]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[80, 77], [151, 88], [167, 131], [187, 138], [187, 157], [177, 129], [143, 120], [134, 132], [133, 115], [124, 106]]}" + } + ], + "images": "15475_exterior_image_1_left#0", + "gt": "[[80, 77], [151, 88], [167, 131], [187, 138], [187, 157], [177, 129], [143, 120], [134, 132], [133, 115], [124, 106]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "20992_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the candy bar in the sink', and now you are performing subtask 'put the candy bar in the sink.'\nYou start from [242, 73]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[242, 73], [198, 109], [178, 149], [180, 156], [182, 132], [195, 117], [205, 119], [218, 145], [218, 134], [231, 123]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/20992_exterior_image_2_left#0.jpg", + "gt": "[[242, 73], [198, 109], [178, 149], [180, 156], [182, 132], [195, 117], [205, 119], [218, 145], [218, 134], [231, 123]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0081_user_0020_scene_0004_cfg_0006_104122060811#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the leg of the glasses (with one hand)', and now you are performing subtask 'fold the leg of the glasses out.'\nStart at [342, 141]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[342, 141], [344, 150], [357, 126], [361, 132], [359, 136], [340, 130], [329, 138], [340, 130], [352, 132], [357, 138]]}" + } + ], + "images": "RH20T_cfg6_task_0081_user_0020_scene_0004_cfg_0006_104122060811#237", + "gt": "[[342, 141], [344, 150], [357, 126], [361, 132], [359, 136], [340, 130], [329, 138], [340, 130], [352, 132], [357, 138]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg2_task_0077_user_0014_scene_0006_cfg_0002_037522062165#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stacking blocks (small Lego) randomly one at a time', and now you are performing subtask 'place the yellow block on the red block, pick up the purple block on the table, transfer the purple block from the table to the yellow block, place the purple block on the yellow block, pick up the green block on the table, transfer the green block from the table to the purple block, place the green block on the purple block.'\nYour starting position is [192, 307]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[192, 307], [189, 298], [173, 322], [182, 350], [169, 339], [190, 296], [179, 350], [200, 360], [198, 300], [211, 294]]}" + } + ], + "images": "RH20T_cfg2_task_0077_user_0014_scene_0006_cfg_0002_037522062165#713", + "gt": "[[192, 307], [189, 298], [173, 322], [182, 350], [169, 339], [190, 296], [179, 350], [200, 360], [198, 300], [211, 294]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0037_user_0014_scene_0001_cfg_0007_037522061512#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line', and now you are performing subtask 'pick up the first block from the table, transfer the first block from the table to the stacking position.'\nYou begin at [261, 86]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[261, 86], [263, 87], [258, 91], [261, 108], [277, 120], [274, 119], [276, 125], [278, 124], [274, 113], [289, 115]]}" + } + ], + "images": "RH20T_cfg7_task_0037_user_0014_scene_0001_cfg_0007_037522061512#0", + "gt": "[[261, 86], [263, 87], [258, 91], [261, 108], [277, 120], [274, 119], [276, 125], [278, 124], [274, 113], [289, 115]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0075_user_0007_scene_0001_cfg_0005_104122063678#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'place the black chess pieces on the chessboard', and now you are performing subtask 'pick up the black piece on the table, transfer the black piece from the table to the chessboard, place the black piece on the chessboard, pick up the white piece on the table.'\nStart at [323, 132]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[323, 132], [348, 125], [356, 139], [374, 145], [373, 123], [368, 156], [372, 147], [383, 159], [367, 186], [376, 152]]}" + } + ], + "images": "RH20T_cfg5_task_0075_user_0007_scene_0001_cfg_0005_104122063678#0", + "gt": "[[323, 132], [348, 125], [356, 139], [374, 145], [373, 123], [368, 156], [372, 147], [383, 159], [367, 186], [376, 152]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "65832_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'push the drawer to close it', and now you are performing subtask 'push the drawer to close it.'\nYour starting position is [134, 122]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[134, 122], [135, 121], [134, 116], [139, 102], [139, 96], [140, 96], [139, 92], [141, 90], [146, 91], [151, 90]]}" + } + ], + "images": "65832_exterior_image_2_left#0", + "gt": "[[134, 122], [135, 121], [134, 116], [139, 102], [139, 96], [140, 96], [139, 92], [141, 90], [146, 91], [151, 90]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "92163_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the towel', and now you are performing subtask 'unfold the towel on the table.'\nThe trajectory starts at [119, 10]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[119, 10], [169, 37], [171, 67], [146, 72], [176, 78], [161, 98], [173, 110], [189, 97], [119, 85], [145, 118]]}" + } + ], + "images": "92163_exterior_image_1_left#0", + "gt": "[[119, 10], [169, 37], [171, 67], [146, 72], [176, 78], [161, 98], [173, 110], [189, 97], [119, 85], [145, 118]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "46244_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the can from the sink and put it on the counter', and now you are performing subtask 'pick up the can from the sink and put it on the counter.'\nThe trajectory starts at [121, 103]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[121, 103], [177, 117], [189, 124], [202, 139], [208, 168], [205, 136], [145, 125], [140, 132], [142, 137], [138, 115]]}" + } + ], + "images": "46244_exterior_image_1_left#0", + "gt": "[[121, 103], [177, 117], [189, 124], [202, 139], [208, 168], [205, 136], [145, 125], [140, 132], [142, 137], [138, 115]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "24724_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close the open drawer', and now you are performing subtask 'close the open drawer.'\nBegin at [147.5, 180.0] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[147.5, 180.0], [142.5, 179.0], [134.5, 175.0], [128.5, 174.0], [114.5, 165.0], [109.5, 165.0], [105.5, 164.0], [97.5, 160.0], [94.5, 156.0], [93.5, 157.0]]}" + } + ], + "images": "24724_exterior_image_1_left#0", + "gt": "[[147.5, 180.0], [142.5, 179.0], [134.5, 175.0], [128.5, 174.0], [114.5, 165.0], [109.5, 165.0], [105.5, 164.0], [97.5, 160.0], [94.5, 156.0], [93.5, 157.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "38730_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'use the towel to wipe on the table', and now you are performing subtask 'slide the towel to wipe the surface on the table.'\nStarting at [217, 114], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[217, 114], [210, 116], [194, 115], [193, 108], [179, 95], [178, 90], [173, 81], [170, 81], [176, 83], [173, 83]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/38730_exterior_image_1_left#166.jpg", + "gt": "[[217, 114], [210, 116], [194, 115], [193, 108], [179, 95], [178, 90], [173, 81], [170, 81], [176, 83], [173, 83]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0034_user_0016_scene_0001_cfg_0004_104122062823#TrajectoryPrediction_Task#8", + "task": "TrajectoryPrediction_Task", + "p_index": 8, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the squares into a pyramid shape', and now you are performing subtask 'place the square on top of the square pile in the right center position, pick up the third square, transfer the square from the square pile to the top, place the third square in the center position of the square pile.'\nYour initial coordinate is [366, 39]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[366, 39], [335, 0], [300, 0], [280, 16], [271, 40], [264, 45], [271, 53], [274, 28], [304, 0], [349, 0]]}" + } + ], + "images": "RH20T_cfg4_task_0034_user_0016_scene_0001_cfg_0004_104122062823#392", + "gt": "[[366, 39], [335, 0], [300, 0], [280, 16], [271, 40], [264, 45], [271, 53], [274, 28], [304, 0], [349, 0]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "42384_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the pen from the table and put it in the bowl', and now you are performing subtask 'pick up the pen from the table and put it in the bowl.'\nBegin at [250, 22] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[250, 22], [232, 32], [193, 63], [182, 77], [180, 51], [185, 24], [187, 19], [189, 20], [187, 27], [181, 34]]}" + } + ], + "images": "42384_exterior_image_2_left#0", + "gt": "[[250, 22], [232, 32], [193, 63], [182, 77], [180, 51], [185, 24], [187, 19], [189, 20], [187, 27], [181, 34]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0020_user_0016_scene_0002_cfg_0004_104122062823#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn on the desk lamp by pressing the button', and now you are performing subtask 'press the button on the desk lamp to turn on the light.'\nFrom start point [160, 66], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[160, 66], [162, 75], [155, 81], [153, 77], [162, 69], [154, 77], [159, 82], [168, 68], [213, 56], [229, 58]]}" + } + ], + "images": "RH20T_cfg4_task_0020_user_0016_scene_0002_cfg_0004_104122062823#142", + "gt": "[[160, 66], [162, 75], [155, 81], [153, 77], [162, 69], [154, 77], [159, 82], [168, 68], [213, 56], [229, 58]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0013_user_0010_scene_0002_cfg_0004_104422070011#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'place the block on the scale', and now you are performing subtask 'place the block on the scale.'\nStart at [340, 104]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[340, 104], [329, 109], [339, 118], [423, 156], [432, 175], [393, 134], [325, 120], [319, 138], [375, 125], [358, 120]]}" + } + ], + "images": "RH20T_cfg4_task_0013_user_0010_scene_0002_cfg_0004_104422070011#0", + "gt": "[[340, 104], [329, 109], [339, 118], [423, 156], [432, 175], [393, 134], [325, 120], [319, 138], [375, 125], [358, 120]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0037_user_0020_scene_0004_cfg_0006_104122061018#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'place the block on the other block, pick up the block on the surface, transfer the block from the surface to the other block, place the block on the other block.'\nWith start location [380, 110], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[380, 110], [357, 87], [326, 90], [275, 120], [369, 83], [381, 82], [384, 98], [366, 66], [330, 62], [330, 62]]}" + } + ], + "images": "RH20T_cfg6_task_0037_user_0020_scene_0004_cfg_0006_104122061018#1008", + "gt": "[[380, 110], [357, 87], [326, 90], [275, 120], [369, 83], [381, 82], [384, 98], [366, 66], [330, 62], [330, 62]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "865_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'use the wooden spoon to stir the contents of the pot', and now you are performing subtask 'use the wooden spoon to stir the contents of the pot.'\nBegin at [131.0, 59.5] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[131.0, 59.5], [160.0, 56.5], [178.0, 73.5], [191.0, 57.5], [171.0, 57.5], [193.0, 58.5], [171.0, 55.5], [194.0, 60.5], [175.0, 66.5], [174.0, 57.5]]}" + } + ], + "images": "865_exterior_image_1_left#0", + "gt": "[[131.0, 59.5], [160.0, 56.5], [178.0, 73.5], [191.0, 57.5], [171.0, 57.5], [193.0, 58.5], [171.0, 55.5], [194.0, 60.5], [175.0, 66.5], [174.0, 57.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "62551_exterior_image_1_left#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close the faucet, open the faucet, close the faucet', and now you are performing subtask 'press the faucet down.'\nWith start location [82, 76], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[82, 76], [84, 88], [79, 83], [72, 84], [77, 81], [92, 84], [94, 78], [94, 84], [91, 77], [81, 73]]}" + } + ], + "images": "62551_exterior_image_1_left#350", + "gt": "[[82, 76], [84, 88], [79, 83], [72, 84], [77, 81], [92, 84], [94, 78], [94, 84], [91, 77], [81, 73]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "39560_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the topmost drawer, take out the towel and place it on the counter then close the drawer', and now you are performing subtask 'pull the handle of the top drawer to the outside of the countertop.'\nYour starting position is [27.0, 80.5]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[27.0, 80.5], [77.0, 96.5], [100.0, 138.5], [111.0, 140.5], [106.0, 141.5], [118.0, 153.5], [144.0, 153.5], [144.0, 149.5], [86.0, 151.5], [72.0, 145.5]]}" + } + ], + "images": "39560_exterior_image_1_left#0", + "gt": "[[27.0, 80.5], [77.0, 96.5], [100.0, 138.5], [111.0, 140.5], [106.0, 141.5], [118.0, 153.5], [144.0, 153.5], [144.0, 149.5], [86.0, 151.5], [72.0, 145.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0091_user_0014_scene_0007_cfg_0004_038522062288#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move an object from one box to another', and now you are performing subtask 'move an object from one box to another.'\nStarting at [235, 120], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[235, 120], [250, 109], [225, 50], [247, 56], [265, 97], [249, 50], [274, 11], [287, 19], [266, 35], [279, 95]]}" + } + ], + "images": "RH20T_cfg4_task_0091_user_0014_scene_0007_cfg_0004_038522062288#0", + "gt": "[[235, 120], [250, 109], [225, 50], [247, 56], [265, 97], [249, 50], [274, 11], [287, 19], [266, 35], [279, 95]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0094_user_0014_scene_0010_cfg_0001_819112070044#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open a box', and now you are performing subtask 'fold the first lid on the box on the table, fold the second lid on the box on the table, fold the third lid on the box on the table.'\nStarting at [464, 168], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[464, 168], [448, 166], [430, 154], [414, 154], [409, 157], [406, 169], [418, 154], [430, 152], [447, 174], [449, 188]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0094_user_0014_scene_0010_cfg_0001_819112070044#118.jpg", + "gt": "[[464, 168], [448, 166], [430, 154], [414, 154], [409, 157], [406, 169], [418, 154], [430, 152], [447, 174], [449, 188]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0031_user_0020_scene_0007_cfg_0007_037522061512#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'cover the box', and now you are performing subtask 'cover the box.'\nFrom start point [261, 86], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[261, 86], [255, 112], [257, 101], [266, 117], [260, 95], [243, 88], [208, 127], [193, 163], [207, 120], [223, 99]]}" + } + ], + "images": "RH20T_cfg7_task_0031_user_0020_scene_0007_cfg_0007_037522061512#0", + "gt": "[[261, 86], [255, 112], [257, 101], [266, 117], [260, 95], [243, 88], [208, 127], [193, 163], [207, 120], [223, 99]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0058_user_0015_scene_0003_cfg_0001_035622060973#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn off the power strips', and now you are performing subtask 'press the third button on the power socket, press the fourth button on the power socket.'\nThe trajectory starts at [227, 98]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[227, 98], [226, 94], [220, 101], [221, 112], [224, 111], [224, 101], [223, 99], [222, 101], [227, 134], [224, 142]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0058_user_0015_scene_0003_cfg_0001_035622060973#236.jpg", + "gt": "[[227, 98], [226, 94], [220, 101], [221, 112], [224, 111], [224, 101], [223, 99], [222, 101], [227, 134], [224, 142]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "79681_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the towel and lay it flat on the countertop', and now you are performing subtask 'pull a corner of the towel to unfold the towel.'\nYour starting position is [314, 44]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[314, 44], [243, 52], [262, 54], [219, 61], [186, 77], [192, 79], [174, 101], [181, 92], [203, 94], [245, 110]]}" + } + ], + "images": "79681_exterior_image_1_left#0", + "gt": "[[314, 44], [243, 52], [262, 54], [219, 61], [186, 77], [192, 79], [174, 101], [181, 92], [203, 94], [245, 110]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0081_user_0010_scene_0001_cfg_0001_819112070044#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the leg of the glasses (with one hand)', and now you are performing subtask 'pull the leg of the glasses outward.'\nYour initial coordinate is [400, 169]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[400, 169], [394, 171], [385, 181], [383, 194], [386, 202], [379, 219], [378, 216], [369, 221], [373, 226], [372, 231]]}" + } + ], + "images": "RH20T_cfg1_task_0081_user_0010_scene_0001_cfg_0001_819112070044#0", + "gt": "[[400, 169], [394, 171], [385, 181], [383, 194], [386, 202], [379, 219], [378, 216], [369, 221], [373, 226], [372, 231]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "9510_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pour the water out of the mug on the right side and move the mug to the left side of the sink', and now you are performing subtask 'pour the water out of the mug on the right side and move the mug to the left side of the sink.'\nStart at [206, 57]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[206, 57], [173, 84], [160, 57], [155, 77], [95, 103], [76, 102], [44, 131], [31, 167], [45, 128], [78, 92]]}" + } + ], + "images": "9510_exterior_image_1_left#0", + "gt": "[[206, 57], [173, 84], [160, 57], [155, 77], [95, 103], [76, 102], [44, 131], [31, 167], [45, 128], [78, 92]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "29734_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'slide the towel to the right on the table', and now you are performing subtask 'slide the towel to the right on the table.'\nYou begin at [170, 4]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[170, 4], [152, 57], [146, 90], [146, 108], [150, 110], [169, 108], [217, 123], [232, 119], [236, 113], [233, 105]]}" + } + ], + "images": "29734_exterior_image_1_left#0", + "gt": "[[170, 4], [152, 57], [146, 90], [146, 108], [150, 110], [169, 108], [217, 123], [232, 119], [236, 113], [233, 105]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "22217_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close the lid of the bowl', and now you are performing subtask 'pull the packaging box to the closed position.'\nStarting at [179, 16], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[179, 16], [141, 62], [121, 74], [120, 67], [132, 63], [114, 102], [109, 98], [115, 108], [110, 116], [104, 109]]}" + } + ], + "images": "22217_exterior_image_2_left#0", + "gt": "[[179, 16], [141, 62], [121, 74], [120, 67], [132, 63], [114, 102], [109, 98], [115, 108], [110, 116], [104, 109]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0037_user_0007_scene_0010_cfg_0005_037522062165#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'pick up the fourth block on the table, transfer the fourth block from the table to the position above the third block, place the fourth block on top of the third block, pick up the fifth block on the table.'\nYou begin at [222, 231]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[222, 231], [208, 165], [195, 151], [181, 148], [189, 160], [195, 141], [223, 126], [237, 130], [255, 148], [255, 148]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0037_user_0007_scene_0010_cfg_0005_037522062165#557.jpg", + "gt": "[[222, 231], [208, 165], [195, 151], [181, 148], [189, 160], [195, 141], [223, 126], [237, 130], [255, 148], [255, 148]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0020_user_0014_scene_0010_cfg_0007_104122064161#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'waving the flag up and down', and now you are performing subtask 'waving the flag up and down.'\nStarting at [337, 115], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[337, 115], [373, 134], [376, 151], [364, 175], [363, 113], [344, 84], [343, 50], [349, 50], [349, 60], [341, 38]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg7_task_0020_user_0014_scene_0010_cfg_0007_104122064161#0.jpg", + "gt": "[[337, 115], [373, 134], [376, 151], [364, 175], [363, 113], [344, 84], [343, 50], [349, 50], [349, 60], [341, 38]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "6823_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the glue stick on the countertop', and now you are performing subtask 'put the glue stick on the countertop.'\nFrom start point [120.5, 28.5], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[120.5, 28.5], [105.5, 33.5], [107.5, 49.5], [119.5, 58.5], [106.5, 35.5], [108.5, 38.5], [113.5, 13.5], [126.5, 16.5], [129.5, 22.5], [123.5, 15.5]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/6823_exterior_image_1_left#0.jpg", + "gt": "[[120.5, 28.5], [105.5, 33.5], [107.5, 49.5], [119.5, 58.5], [106.5, 35.5], [108.5, 38.5], [113.5, 13.5], [126.5, 16.5], [129.5, 22.5], [123.5, 15.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0032_user_0016_scene_0002_cfg_0004_104122062295#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'slide the outer casing onto the gift box', and now you are performing subtask 'pick up the outer casing from the table.'\nYour initial coordinate is [260, 66]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[260, 66], [233, 85], [294, 108], [345, 147], [355, 170], [350, 203], [304, 267], [291, 271], [310, 271], [298, 285]]}" + } + ], + "images": "RH20T_cfg4_task_0032_user_0016_scene_0002_cfg_0004_104122062295#0", + "gt": "[[260, 66], [233, 85], [294, 108], [345, 147], [355, 170], [350, 203], [304, 267], [291, 271], [310, 271], [298, 285]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "44385_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the egg toy into the cup', and now you are performing subtask 'pick up the egg toy from the tray.'\nYour starting position is [119, 27]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[119, 27], [120, 36], [138, 23], [120, 32], [125, 43], [116, 27], [143, 42], [144, 85], [153, 98], [146, 127]]}" + } + ], + "images": "44385_exterior_image_1_left#0", + "gt": "[[119, 27], [120, 36], [138, 23], [120, 32], [125, 43], [116, 27], [143, 42], [144, 85], [153, 98], [146, 127]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0057_user_0015_scene_0009_cfg_0001_035622060973#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn them on', and now you are performing subtask 'press the first button on the right side of the power strip, press the second button on the right side of the power strip.'\nStart at [246, 130]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[246, 130], [250, 128], [231, 98], [236, 86], [232, 61], [238, 76], [234, 69], [235, 58], [224, 75], [227, 84]]}" + } + ], + "images": "RH20T_cfg1_task_0057_user_0015_scene_0009_cfg_0001_035622060973#0", + "gt": "[[246, 130], [250, 128], [231, 98], [236, 86], [232, 61], [238, 76], [234, 69], [235, 58], [224, 75], [227, 84]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg2_task_0054_user_0007_scene_0009_cfg_0002_104122061850#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'grasp the moving object', and now you are performing subtask 'pick up the moving object directly under the robotic arm, transfer the object from the robotic arm to the center of the table, place the object at the center of the table.'\nWith start location [421, 164], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[421, 164], [425, 175], [422, 179], [424, 170], [416, 147], [408, 134], [395, 123], [378, 117], [355, 114], [354, 121]]}" + } + ], + "images": "RH20T_cfg2_task_0054_user_0007_scene_0009_cfg_0002_104122061850#66", + "gt": "[[421, 164], [425, 175], [422, 179], [424, 170], [416, 147], [408, 134], [395, 123], [378, 117], [355, 114], [354, 121]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0051_user_0014_scene_0002_cfg_0006_104122063633#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the dish off the dish rack', and now you are performing subtask 'take the dish off the dish rack.'\nYou start from [233, 118]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[233, 118], [193, 95], [187, 43], [191, 74], [169, 100], [166, 149], [146, 174], [144, 164], [171, 124], [166, 142]]}" + } + ], + "images": "RH20T_cfg6_task_0051_user_0014_scene_0002_cfg_0006_104122063633#0", + "gt": "[[233, 118], [193, 95], [187, 43], [191, 74], [169, 100], [166, 149], [146, 174], [144, 164], [171, 124], [166, 142]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0016_user_0014_scene_0008_cfg_0001_039422060546#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'hit the pool ball', and now you are performing subtask 'pick up the pool cue on the wooden table, strike the pool ball with a tool.'\nStarting at [265, 125], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[265, 125], [273, 124], [288, 140], [320, 189], [332, 187], [340, 195], [340, 207], [322, 205], [325, 210], [335, 184]]}" + } + ], + "images": "RH20T_cfg1_task_0016_user_0014_scene_0008_cfg_0001_039422060546#0", + "gt": "[[265, 125], [273, 124], [288, 140], [320, 189], [332, 187], [340, 195], [340, 207], [322, 205], [325, 210], [335, 184]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0073_user_0020_scene_0003_cfg_0006_037522061512#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the things in the drawer', and now you are performing subtask 'pull the drawer to the open position, pick up the cube on the table, transfer the cube from the table to the drawer, place the cube in the drawer.'\nYour initial coordinate is [250, 75]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[250, 75], [254, 65], [261, 68], [274, 114], [276, 55], [251, 63], [225, 111], [224, 133], [228, 107], [228, 107]]}" + } + ], + "images": "RH20T_cfg6_task_0073_user_0020_scene_0003_cfg_0006_037522061512#451", + "gt": "[[250, 75], [254, 65], [261, 68], [274, 114], [276, 55], [251, 63], [225, 111], [224, 133], [228, 107], [228, 107]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "37401_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'folding the towel on the table', and now you are performing subtask 'pick up the top right corner of the towel on the counter.'\nThe trajectory starts at [290, 73]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[290, 73], [257, 91], [234, 95], [225, 105], [228, 117], [221, 125], [226, 122], [222, 116], [190, 113], [209, 114]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/37401_exterior_image_1_left#0.jpg", + "gt": "[[290, 73], [257, 91], [234, 95], [225, 105], [228, 117], [221, 125], [226, 122], [222, 116], [190, 113], [209, 114]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "55054_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn off the switch on the kettle', and now you are performing subtask 'turn off the switch on the kettle.'\nStarting at [120, 1], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[120, 1], [134, 23], [178, 44], [184, 60], [179, 41], [173, 62], [191, 81], [173, 86], [198, 93], [167, 95]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/55054_exterior_image_1_left#0.jpg", + "gt": "[[120, 1], [134, 23], [178, 44], [184, 60], [179, 41], [173, 62], [191, 81], [173, 86], [198, 93], [167, 95]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0008_user_0007_scene_0001_cfg_0005_104122061850#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'grab the block and place it at the designated location', and now you are performing subtask 'grab the block and place it at the designated location.'\nYour starting position is [311, 50]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[311, 50], [313, 70], [272, 129], [177, 217], [229, 249], [217, 235], [249, 204], [315, 170], [344, 175], [303, 121]]}" + } + ], + "images": "RH20T_cfg5_task_0008_user_0007_scene_0001_cfg_0005_104122061850#0", + "gt": "[[311, 50], [313, 70], [272, 129], [177, 217], [229, 249], [217, 235], [249, 204], [315, 170], [344, 175], [303, 121]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "81663_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the cup and put it on top of the table, then pick up the cloth and put it in the bowl and close the drawer', and now you are performing subtask 'pick up the cloth from the drawer.'\nWith start location [235, 5], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[235, 5], [198, 32], [184, 50], [187, 60], [189, 17], [186, 28], [162, 19], [146, 33], [158, 5], [186, 11]]}" + } + ], + "images": "81663_exterior_image_1_left#0", + "gt": "[[235, 5], [198, 32], [184, 50], [187, 60], [189, 17], [186, 28], [162, 19], [146, 33], [158, 5], [186, 11]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "43389_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the top drawer, pick up the watermelon plush toy from the countertop and put it in the basket. pick up the banana plush toy from the basket in the drawer and put it on the countertop. close the top drawer', and now you are performing subtask 'pick up the watermelon plush toy from the countertop.'\nStart at [219, 145]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[219, 145], [204, 135], [197, 135], [194, 136], [191, 144], [193, 148], [198, 152], [211, 155], [232, 150], [211, 141]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/43389_exterior_image_1_left#161.jpg", + "gt": "[[219, 145], [204, 135], [197, 135], [194, 136], [191, 144], [193, 148], [198, 152], [211, 155], [232, 150], [211, 141]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0004_user_0010_scene_0001_cfg_0005_037522062165#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the small block on the left and move it to the right', and now you are performing subtask 'pick up the small block on the left and move it to the right.'\nYour starting position is [289, 152]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[289, 152], [269, 160], [159, 155], [137, 137], [136, 171], [201, 214], [290, 219], [310, 243], [309, 260], [309, 260]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0004_user_0010_scene_0001_cfg_0005_037522062165#0.jpg", + "gt": "[[289, 152], [269, 160], [159, 155], [137, 137], [136, 171], [201, 214], [290, 219], [310, 243], [309, 260], [309, 260]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0081_user_0010_scene_0001_cfg_0001_039422060546#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the leg of the glasses (with one hand)', and now you are performing subtask 'pull the leg of the glasses outward.'\nYou start from [271, 104]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[271, 104], [255, 107], [267, 108], [290, 99], [302, 101], [300, 98], [302, 100], [310, 93], [328, 86], [328, 86]]}" + } + ], + "images": "RH20T_cfg1_task_0081_user_0010_scene_0001_cfg_0001_039422060546#169", + "gt": "[[271, 104], [255, 107], [267, 108], [290, 99], [302, 101], [300, 98], [302, 100], [310, 93], [328, 86], [328, 86]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0103_user_0007_scene_0002_cfg_0005_037522062165#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'slide the plate into the goal post', and now you are performing subtask 'slide the plate into the goal post.'\nWith start location [289, 152], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[289, 152], [264, 198], [259, 271], [159, 254], [174, 253], [186, 275], [167, 262], [196, 247], [212, 213], [207, 180]]}" + } + ], + "images": "RH20T_cfg5_task_0103_user_0007_scene_0002_cfg_0005_037522062165#0", + "gt": "[[289, 152], [264, 198], [259, 271], [159, 254], [174, 253], [186, 275], [167, 262], [196, 247], [212, 213], [207, 180]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "52032_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the clear lid from the top of the black object to the top of the cup and press on the lid', and now you are performing subtask 'move the clear lid from the top of the black object to the top of the cup and press on the lid.'\nYou begin at [174, 90]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[174, 90], [158, 110], [164, 133], [166, 104], [170, 109], [175, 97], [174, 112], [173, 101], [174, 110], [189, 88]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/52032_exterior_image_1_left#0.jpg", + "gt": "[[174, 90], [158, 110], [164, 133], [166, 104], [170, 109], [175, 97], [174, 112], [173, 101], [174, 110], [189, 88]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg2_task_0037_user_0007_scene_0007_cfg_0002_037522062165#TrajectoryPrediction_Task#8", + "task": "TrajectoryPrediction_Task", + "p_index": 8, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'pick up the fifth block from the surface, transfer the fifth block from the surface to the top of the fourth block, place the fifth block on top of the fourth block.'\nWith start location [253, 286], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[253, 286], [244, 301], [252, 324], [245, 324], [242, 304], [269, 267], [269, 240], [275, 243], [268, 251], [259, 221]]}" + } + ], + "images": "RH20T_cfg2_task_0037_user_0007_scene_0007_cfg_0002_037522062165#801", + "gt": "[[253, 286], [244, 301], [252, 324], [245, 324], [242, 304], [269, 267], [269, 240], [275, 243], [268, 251], [259, 221]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "18069_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the carrot plush toy and put it on the counter', and now you are performing subtask 'pick up the carrot plush toy and put it on the counter.'\nYour starting position is [319, 11]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[319, 11], [238, 71], [166, 106], [178, 106], [176, 119], [165, 108], [192, 97], [201, 104], [198, 112], [179, 104]]}" + } + ], + "images": "18069_exterior_image_2_left#0", + "gt": "[[319, 11], [238, 71], [166, 106], [178, 106], [176, 119], [165, 108], [192, 97], [201, 104], [198, 112], [179, 104]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "26173_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the slice of bread in the toaster, push the lever on the toaster down', and now you are performing subtask 'place the slice of bread in the toaster.'\nYour initial coordinate is [168.0, 139.0]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[168.0, 139.0], [194.0, 119.0], [186.0, 125.0], [188.0, 134.0], [204.0, 152.0], [205.0, 118.0], [213.0, 104.0], [224.0, 104.0], [237.0, 118.0], [233.0, 108.0]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/26173_exterior_image_1_left#0.jpg", + "gt": "[[168.0, 139.0], [194.0, 119.0], [186.0, 125.0], [188.0, 134.0], [204.0, 152.0], [205.0, 118.0], [213.0, 104.0], [224.0, 104.0], [237.0, 118.0], [233.0, 108.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "89028_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'place the rectangular yellow block on the rectangular green block', and now you are performing subtask 'place the rectangular yellow block on the rectangular green block.'\nStarting at [27.0, 5.0], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[27.0, 5.0], [76.0, 98.0], [114.0, 113.0], [118.0, 68.0], [131.0, 91.0], [151.0, 86.0], [141.0, 91.0], [141.0, 59.0], [133.0, 52.0], [91.0, 52.0]]}" + } + ], + "images": "89028_exterior_image_1_left#0", + "gt": "[[27.0, 5.0], [76.0, 98.0], [114.0, 113.0], [118.0, 68.0], [131.0, 91.0], [151.0, 86.0], [141.0, 91.0], [141.0, 59.0], [133.0, 52.0], [91.0, 52.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "60471_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the orange toy and put it in the silver teacup', and now you are performing subtask 'pick up the orange toy and put it in the silver teacup.'\nYour initial coordinate is [242, 0]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[242, 0], [217, 33], [206, 62], [210, 77], [202, 80], [191, 60], [173, 64], [174, 75], [191, 51], [183, 56]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/60471_exterior_image_2_left#0.jpg", + "gt": "[[242, 0], [217, 33], [206, 62], [210, 77], [202, 80], [191, 60], [173, 64], [174, 75], [191, 51], [183, 56]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0003_user_0014_scene_0006_cfg_0005_036422060215#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press three buttons from left to right in sequence', and now you are performing subtask 'press the green button on the gray and white base, press the red button on the black and orange base.'\nStart at [288, 132]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[288, 132], [292, 117], [285, 116], [248, 131], [238, 132], [239, 127], [234, 137], [239, 136], [257, 113], [268, 108]]}" + } + ], + "images": "RH20T_cfg5_task_0003_user_0014_scene_0006_cfg_0005_036422060215#389", + "gt": "[[288, 132], [292, 117], [285, 116], [248, 131], [238, 132], [239, 127], [234, 137], [239, 136], [257, 113], [268, 108]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0034_user_0014_scene_0004_cfg_0001_035622060973#TrajectoryPrediction_Task#10", + "task": "TrajectoryPrediction_Task", + "p_index": 10, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the squares into a pyramid shape', and now you are performing subtask 'place the fourth square on top of the first square, pick up the fifth square from the right side of the table, transfer the fifth square from the right side of the table to the top of the second square, place the fifth square on top of the second square.'\nWith start location [249, 140], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[249, 140], [217, 166], [212, 174], [211, 188], [209, 186], [206, 191], [206, 178], [220, 162], [254, 148], [254, 148]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0034_user_0014_scene_0004_cfg_0001_035622060973#704.jpg", + "gt": "[[249, 140], [217, 166], [212, 174], [211, 188], [209, 186], [206, 191], [206, 178], [220, 162], [254, 148], [254, 148]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "42289_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'slide the bowl to the left then put the pen inside the bowl', and now you are performing subtask 'slide the bowl on the table to the left.'\nThe trajectory starts at [104.0, 1.5]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[104.0, 1.5], [106.0, 4.5], [113.0, 32.5], [115.0, 36.5], [120.0, 39.5], [117.0, 40.5], [127.0, 47.5], [116.0, 47.5], [117.0, 30.5], [117.0, 30.5]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/42289_exterior_image_1_left#0.jpg", + "gt": "[[104.0, 1.5], [106.0, 4.5], [113.0, 32.5], [115.0, 36.5], [120.0, 39.5], [117.0, 40.5], [127.0, 47.5], [116.0, 47.5], [117.0, 30.5], [117.0, 30.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "70471_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the white and black mugs from the drawer, push the drawer closed, close the open bottom cabinet', and now you are performing subtask 'place the black cup on the countertop.'\nYou start from [168, 107]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[168, 107], [175, 102], [194, 112], [196, 123], [178, 125], [187, 130], [181, 135], [202, 127], [195, 102], [173, 101]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/70471_exterior_image_1_left#280.jpg", + "gt": "[[168, 107], [175, 102], [194, 112], [196, 123], [178, 125], [187, 130], [181, 135], [202, 127], [195, 102], [173, 101]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "35702_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close the left side of the drawer', and now you are performing subtask 'close the left side of the drawer.'\nYour initial coordinate is [163.5, 75.0]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[163.5, 75.0], [146.5, 83.0], [139.5, 91.0], [151.5, 84.0], [148.5, 90.0], [151.5, 90.0], [156.5, 100.0], [169.5, 100.0], [178.5, 96.0], [150.5, 85.0]]}" + } + ], + "images": "35702_exterior_image_1_left#0", + "gt": "[[163.5, 75.0], [146.5, 83.0], [139.5, 91.0], [151.5, 84.0], [148.5, 90.0], [151.5, 90.0], [156.5, 100.0], [169.5, 100.0], [178.5, 96.0], [150.5, 85.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "83847_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick the lid from the pot and put it on the table', and now you are performing subtask 'pick the lid from the pot and put it on the table.'\nWith start location [250, 35], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[250, 35], [221, 20], [207, 31], [202, 70], [194, 49], [182, 53], [176, 71], [186, 96], [179, 100], [184, 107]]}" + } + ], + "images": "83847_exterior_image_2_left#0", + "gt": "[[250, 35], [221, 20], [207, 31], [202, 70], [194, 49], [182, 53], [176, 71], [186, 96], [179, 100], [184, 107]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "70745_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the measuring tape', and now you are performing subtask 'move the measuring tape.'\nWith start location [262, 23], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[262, 23], [188, 41], [160, 56], [166, 56], [162, 59], [159, 89], [170, 78], [182, 82], [188, 93], [189, 85]]}" + } + ], + "images": "70745_exterior_image_1_left#0", + "gt": "[[262, 23], [188, 41], [160, 56], [166, 56], [162, 59], [159, 89], [170, 78], [182, 82], [188, 93], [189, 85]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0111_user_0007_scene_0001_cfg_0004_036422060909#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the object with the corresponding shape into the corresponding hole', and now you are performing subtask 'put the object with the corresponding shape into the corresponding hole.'\nYou begin at [341, 79]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[341, 79], [357, 81], [349, 70], [336, 88], [304, 78], [333, 73], [355, 90], [310, 67], [310, 58], [323, 64]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg4_task_0111_user_0007_scene_0001_cfg_0004_036422060909#0.jpg", + "gt": "[[341, 79], [357, 81], [349, 70], [336, 88], [304, 78], [333, 73], [355, 90], [310, 67], [310, 58], [323, 64]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "89090_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the black lid from the table and put it on the small cup', and now you are performing subtask 'pick up the black lid from the table and put it on the small cup.'\nThe trajectory starts at [213, 5]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[213, 5], [199, 34], [198, 43], [203, 51], [183, 91], [151, 81], [147, 93], [149, 52], [154, 45], [150, 48]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/89090_exterior_image_2_left#0.jpg", + "gt": "[[213, 5], [199, 34], [198, 43], [203, 51], [183, 91], [151, 81], [147, 93], [149, 52], [154, 45], [150, 48]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0010_user_0007_scene_0003_cfg_0005_037522062165#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'place the handset of the telephone on the corresponding phone cradle', and now you are performing subtask 'pick up the handset from the table, transfer the handset from the table to the phone cradle, place the handset on the phone cradle.'\nBegin at [298, 143] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[298, 143], [366, 165], [388, 184], [374, 271], [360, 290], [359, 300], [360, 280], [262, 237], [246, 219], [248, 210]]}" + } + ], + "images": "RH20T_cfg5_task_0010_user_0007_scene_0003_cfg_0005_037522062165#0", + "gt": "[[298, 143], [366, 165], [388, 184], [374, 271], [360, 290], [359, 300], [360, 280], [262, 237], [246, 219], [248, 210]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg3_task_0008_user_0016_scene_0005_cfg_0003_104122062823#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'grab the block and place it at the designated location', and now you are performing subtask 'pick up the block from the right side of the cardboard.'\nYour initial coordinate is [383, 67]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[383, 67], [396, 61], [384, 59], [384, 51], [375, 52], [378, 43], [385, 38], [371, 55], [372, 62], [391, 61]]}" + } + ], + "images": "RH20T_cfg3_task_0008_user_0016_scene_0005_cfg_0003_104122062823#57", + "gt": "[[383, 67], [396, 61], [384, 59], [384, 51], [375, 52], [378, 43], [385, 38], [371, 55], [372, 62], [391, 61]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "45188_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'fold the white towel once', and now you are performing subtask 'fold the white towel once.'\nYou begin at [275, 21]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[275, 21], [234, 48], [232, 74], [210, 76], [196, 107], [197, 87], [212, 112], [206, 98], [202, 116], [204, 97]]}" + } + ], + "images": "45188_exterior_image_2_left#0", + "gt": "[[275, 21], [234, 48], [232, 74], [210, 76], [196, 107], [197, 87], [212, 112], [206, 98], [202, 116], [204, 97]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "17981_exterior_image_2_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the orange cloth', and now you are performing subtask 'fold the cloth on the table.'\nThe trajectory starts at [221, 153]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[221, 153], [212, 146], [224, 136], [248, 138], [264, 154], [258, 155], [259, 141], [254, 131], [239, 119], [204, 114]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/17981_exterior_image_2_left#125.jpg", + "gt": "[[221, 153], [212, 146], [224, 136], [248, 138], [264, 154], [258, 155], [259, 141], [254, 131], [239, 119], [204, 114]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0066_user_0014_scene_0005_cfg_0007_104122061018#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with large Megabloks for the nth time with n blocks', and now you are performing subtask 'place the block on the block board, pick up the block on the flat surface, transfer the block from the flat surface to the other blocks, place the block on the other blocks.'\nYou begin at [356, 151]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[356, 151], [338, 132], [304, 129], [263, 148], [239, 168], [264, 115], [304, 75], [303, 67], [321, 64], [319, 82]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg7_task_0066_user_0014_scene_0005_cfg_0007_104122061018#438.jpg", + "gt": "[[356, 151], [338, 132], [304, 129], [263, 148], [239, 168], [264, 115], [304, 75], [303, 67], [321, 64], [319, 82]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0081_user_0015_scene_0008_cfg_0004_036422060909#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the leg of the glasses with one hand', and now you are performing subtask 'fold the left leg of the glasses on the table, fold the right leg of the glasses on the table.'\nWith start location [334, 80], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[334, 80], [312, 67], [354, 101], [355, 125], [361, 106], [409, 70], [389, 86], [392, 80], [381, 78], [363, 96]]}" + } + ], + "images": "RH20T_cfg4_task_0081_user_0015_scene_0008_cfg_0004_036422060909#0", + "gt": "[[334, 80], [312, 67], [354, 101], [355, 125], [361, 106], [409, 70], [389, 86], [392, 80], [381, 78], [363, 96]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0061_user_0020_scene_0003_cfg_0007_104122061330#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take everything out of the gift box', and now you are performing subtask 'place the lid on the table, pick up the object in the container, transfer the object from the container to the surface, place the object on the surface.'\nYou begin at [369, 68]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[369, 68], [365, 56], [353, 106], [371, 145], [371, 130], [364, 119], [339, 143], [328, 202], [340, 217], [334, 206]]}" + } + ], + "images": "RH20T_cfg7_task_0061_user_0020_scene_0003_cfg_0007_104122061330#186", + "gt": "[[369, 68], [365, 56], [353, 106], [371, 145], [371, 130], [364, 119], [339, 143], [328, 202], [340, 217], [334, 206]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "47788_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close the tap', and now you are performing subtask 'press the handle of the tap to close the tap.'\nStart at [84, 44]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[84, 44], [79, 43], [76, 45], [76, 48], [83, 50], [85, 55], [90, 59], [96, 46], [99, 45], [116, 49]]}" + } + ], + "images": "47788_exterior_image_1_left#156", + "gt": "[[84, 44], [79, 43], [76, 45], [76, 48], [83, 50], [85, 55], [90, 59], [96, 46], [99, 45], [116, 49]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "16095_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pour the contents in the red bowl into the silver bowl', and now you are performing subtask 'pour the contents in the red bowl into the silver bowl.'\nFrom start point [222, 114], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[222, 114], [184, 97], [128, 106], [158, 82], [173, 87], [168, 74], [175, 81], [135, 105], [135, 94], [186, 91]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/16095_exterior_image_2_left#0.jpg", + "gt": "[[222, 114], [184, 97], [128, 106], [158, 82], [173, 87], [168, 74], [175, 81], [135, 105], [135, 94], [186, 91]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "53935_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'push the chair, press the box', and now you are performing subtask 'push the chair.'\nYour initial coordinate is [230, 92]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[230, 92], [230, 93], [230, 92], [232, 92], [231, 94], [227, 94], [225, 92], [209, 65], [205, 57], [209, 60]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/53935_exterior_image_1_left#192.jpg", + "gt": "[[230, 92], [230, 93], [230, 92], [232, 92], [231, 94], [227, 94], [225, 92], [209, 65], [205, 57], [209, 60]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0068_user_0015_scene_0006_cfg_0004_104122062823#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press a button horizontally with obstacles', and now you are performing subtask 'press a button horizontally with obstacles.'\nBegin at [291, 0] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[291, 0], [326, 0], [339, 9], [328, 15], [392, 53], [481, 82], [494, 119], [529, 135], [370, 83], [273, 72]]}" + } + ], + "images": "RH20T_cfg4_task_0068_user_0015_scene_0006_cfg_0004_104122062823#0", + "gt": "[[291, 0], [326, 0], [339, 9], [328, 15], [392, 53], [481, 82], [494, 119], [529, 135], [370, 83], [273, 72]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "42384_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the pen from the table and put it in the bowl', and now you are performing subtask 'pick up the pen from the table and put it in the bowl.'\nStarting at [66, 67], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[66, 67], [92, 74], [125, 93], [130, 101], [138, 80], [144, 75], [156, 74], [161, 77], [175, 101], [175, 101]]}" + } + ], + "images": "42384_exterior_image_1_left#0", + "gt": "[[66, 67], [92, 74], [125, 93], [130, 101], [138, 80], [144, 75], [156, 74], [161, 77], [175, 101], [175, 101]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "21213_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the two paper bags out of the wooden crate', and now you are performing subtask 'place the second paper bag on the table.'\nFrom start point [203, 96], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[203, 96], [206, 102], [200, 108], [201, 114], [200, 94], [191, 100], [193, 124], [192, 111], [196, 100], [201, 98]]}" + } + ], + "images": "21213_exterior_image_1_left#365", + "gt": "[[203, 96], [206, 102], [200, 108], [201, 114], [200, 94], [191, 100], [193, 124], [192, 111], [196, 100], [201, 98]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "90712_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the soda can from the cabinet to the countertop', and now you are performing subtask 'move the soda can from the cabinet to the countertop.'\nFrom start point [206, 94], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[206, 94], [174, 28], [161, 25], [146, 31], [157, 21], [172, 28], [184, 41], [188, 116], [182, 133], [187, 100]]}" + } + ], + "images": "90712_exterior_image_2_left#0", + "gt": "[[206, 94], [174, 28], [161, 25], [146, 31], [157, 21], [172, 28], [184, 41], [188, 116], [182, 133], [187, 100]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "23851_exterior_image_1_left#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the apple and lemons inside the glass bowl', and now you are performing subtask 'pick up the fourth lemon on the table.'\nWith start location [215, 91], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[215, 91], [205, 94], [193, 110], [193, 117], [215, 89], [223, 89], [238, 102], [230, 94], [214, 93], [183, 110]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/23851_exterior_image_1_left#444.jpg", + "gt": "[[215, 91], [205, 94], [193, 110], [193, 117], [215, 89], [223, 89], [238, 102], [230, 94], [214, 93], [183, 110]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0012_user_0010_scene_0005_cfg_0004_104122062823#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'push the soccer ball into the goal', and now you are performing subtask 'push the soccer ball toward the goal.'\nThe trajectory starts at [220, 111]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[220, 111], [230, 118], [237, 133], [221, 128], [216, 134], [223, 138], [225, 135], [221, 126], [237, 127], [248, 141]]}" + } + ], + "images": "RH20T_cfg4_task_0012_user_0010_scene_0005_cfg_0004_104122062823#214", + "gt": "[[220, 111], [230, 118], [237, 133], [221, 128], [216, 134], [223, 138], [225, 135], [221, 126], [237, 127], [248, 141]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0094_user_0014_scene_0003_cfg_0004_104122062823#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open a box', and now you are performing subtask 'push the lid on the top of the box, push the lid on the bottom of the box.'\nYou start from [413, 0]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[413, 0], [408, 9], [410, 16], [421, 0], [436, 0], [429, 0], [426, 6], [430, 0], [403, 0], [398, 13]]}" + } + ], + "images": "RH20T_cfg4_task_0094_user_0014_scene_0003_cfg_0004_104122062823#311", + "gt": "[[413, 0], [408, 9], [410, 16], [421, 0], [436, 0], [429, 0], [426, 6], [430, 0], [403, 0], [398, 13]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "42121_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the blue pen from the red and black mug', and now you are performing subtask 'remove the blue pen from the red and black mug.'\nYour initial coordinate is [112.0, 5.5]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[112.0, 5.5], [147.0, 54.5], [195.0, 86.5], [205.0, 63.5], [203.0, 52.5], [186.0, 44.5], [161.0, 54.5], [139.0, 80.5], [157.0, 91.5], [161.0, 83.5]]}" + } + ], + "images": "42121_exterior_image_1_left#0", + "gt": "[[112.0, 5.5], [147.0, 54.5], [195.0, 86.5], [205.0, 63.5], [203.0, 52.5], [186.0, 44.5], [161.0, 54.5], [139.0, 80.5], [157.0, 91.5], [161.0, 83.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "47071_exterior_image_2_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the wooden spatula and mix the contents in the silver bowl', and now you are performing subtask 'place the spoon in the pot.'\nYou start from [107, 76]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[107, 76], [119, 33], [132, 32], [145, 58], [132, 67], [141, 65], [112, 41], [120, 29], [100, 59], [134, 69]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/47071_exterior_image_2_left#79.jpg", + "gt": "[[107, 76], [119, 33], [132, 32], [145, 58], [132, 67], [141, 65], [112, 41], [120, 29], [100, 59], [134, 69]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0020_user_0014_scene_0001_cfg_0006_104122060811#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn on the desk lamp by pressing the button', and now you are performing subtask 'turn on the desk lamp by pressing the button.'\nYou start from [385, 127]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[385, 127], [385, 121], [353, 146], [318, 163], [308, 180], [291, 196], [299, 188], [310, 185], [330, 163], [344, 155]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg6_task_0020_user_0014_scene_0001_cfg_0006_104122060811#0.jpg", + "gt": "[[385, 127], [385, 121], [353, 146], [318, 163], [308, 180], [291, 196], [299, 188], [310, 185], [330, 163], [344, 155]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0043_user_0020_scene_0009_cfg_0007_104122064161#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unscrew the lid from the jar', and now you are performing subtask 'twist the lid counterclockwise, pick up the lid on top of the jar, transfer the lid from above the jar to above the table, place the lid on the tabletop.'\nYour starting position is [375, 159]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[375, 159], [378, 150], [373, 161], [375, 152], [379, 154], [381, 170], [365, 222], [379, 168], [371, 134], [377, 130]]}" + } + ], + "images": "RH20T_cfg7_task_0043_user_0020_scene_0009_cfg_0007_104122064161#258", + "gt": "[[375, 159], [378, 150], [373, 161], [375, 152], [379, 154], [381, 170], [365, 222], [379, 168], [371, 134], [377, 130]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "21869_exterior_image_2_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the microwave door', and now you are performing subtask 'push the microwave to completely open.'\nThe trajectory starts at [140, 134]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[140, 134], [139, 134], [140, 134], [142, 131], [142, 132], [135, 138], [116, 151], [110, 157], [111, 157], [110, 157]]}" + } + ], + "images": "21869_exterior_image_2_left#179", + "gt": "[[140, 134], [139, 134], [140, 134], [142, 131], [142, 132], [135, 138], [116, 151], [110, 157], [111, 157], [110, 157]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0066_user_0014_scene_0005_cfg_0007_037522061512#TrajectoryPrediction_Task#8", + "task": "TrajectoryPrediction_Task", + "p_index": 8, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with large Megabloks for the nth time with n blocks', and now you are performing subtask 'place the block on the other blocks, pick up the block on the flat surface, transfer the block from the flat surface to the other blocks, place the block on the other blocks.'\nBegin at [241, 119] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[241, 119], [194, 136], [184, 154], [186, 139], [221, 118], [233, 117], [246, 125], [256, 143], [244, 138], [231, 122]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg7_task_0066_user_0014_scene_0005_cfg_0007_037522061512#606.jpg", + "gt": "[[241, 119], [194, 136], [184, 154], [186, 139], [221, 118], [233, 117], [246, 125], [256, 143], [244, 138], [231, 122]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "28024_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'swap the places of the cup and the cutlery', and now you are performing subtask 'place the cup on the side of the table where the cutlery is.'\nBegin at [101, 48] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[101, 48], [117, 61], [109, 93], [114, 102], [121, 103], [119, 117], [124, 117], [139, 97], [149, 102], [150, 95]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/28024_exterior_image_1_left#0.jpg", + "gt": "[[101, 48], [117, 61], [109, 93], [114, 102], [121, 103], [119, 117], [124, 117], [139, 97], [149, 102], [150, 95]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "10601_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the mug cup to the left', and now you are performing subtask 'move the mug cup to the left.'\nStart at [210.0, 3.5]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[210.0, 3.5], [192.0, 21.5], [195.0, 20.5], [192.0, 28.5], [181.0, 45.5], [177.0, 58.5], [179.0, 78.5], [174.0, 80.5], [167.0, 73.5], [162.0, 79.5]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/10601_exterior_image_1_left#0.jpg", + "gt": "[[210.0, 3.5], [192.0, 21.5], [195.0, 20.5], [192.0, 28.5], [181.0, 45.5], [177.0, 58.5], [179.0, 78.5], [174.0, 80.5], [167.0, 73.5], [162.0, 79.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "88436_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close the book on the table', and now you are performing subtask 'close the book on the table.'\nYou begin at [224, 79]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[224, 79], [212, 96], [209, 115], [198, 116], [198, 102], [217, 92], [191, 108], [201, 111], [208, 94], [224, 91]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/88436_exterior_image_1_left#0.jpg", + "gt": "[[224, 79], [212, 96], [209, 115], [198, 116], [198, 102], [217, 92], [191, 108], [201, 111], [208, 94], [224, 91]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0094_user_0001_scene_0009_cfg_0001_038522062547#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open a box', and now you are performing subtask 'pull the lid of the box upwards to open the box.'\nThe trajectory starts at [394, 215]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[394, 215], [375, 234], [373, 261], [401, 268], [425, 313], [438, 323], [439, 318], [428, 318], [433, 310], [423, 296]]}" + } + ], + "images": "RH20T_cfg1_task_0094_user_0001_scene_0009_cfg_0001_038522062547#303", + "gt": "[[394, 215], [375, 234], [373, 261], [401, 268], [425, 313], [438, 323], [439, 318], [428, 318], [433, 310], [423, 296]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0079_user_0015_scene_0003_cfg_0001_038522062547#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the microwave door', and now you are performing subtask 'pull the handle of the microwave door to open the door.'\nStarting at [405, 132], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[405, 132], [450, 161], [458, 178], [420, 142], [411, 123], [430, 141], [398, 110], [391, 39], [364, 42], [394, 39]]}" + } + ], + "images": "RH20T_cfg1_task_0079_user_0015_scene_0003_cfg_0001_038522062547#0", + "gt": "[[405, 132], [450, 161], [458, 178], [420, 142], [411, 123], [430, 141], [398, 110], [391, 39], [364, 42], [394, 39]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "21996_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the bottle from the top part of the segment tray and put it on the transparent box', and now you are performing subtask 'take the bottle from the top part of the segment tray and put it on the transparent box.'\nStarting at [85, 157], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[85, 157], [124, 120], [158, 103], [159, 110], [184, 88], [212, 99], [192, 107], [191, 116], [202, 125], [182, 114]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/21996_exterior_image_2_left#0.jpg", + "gt": "[[85, 157], [124, 120], [158, 103], [159, 110], [184, 88], [212, 99], [192, 107], [191, 116], [202, 125], [182, 114]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0130_user_0014_scene_0004_cfg_0006_037522061512#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'plug in the bulb holder with a bulb to the socket and turn on the switch of the bulb', and now you are performing subtask 'insert the lamp holder into the socket, press the lamp holder button to turn on the light.'\nStarting at [248, 110], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[248, 110], [259, 108], [259, 113], [241, 104], [216, 108], [206, 115], [201, 123], [205, 125], [205, 134], [201, 135]]}" + } + ], + "images": "RH20T_cfg6_task_0130_user_0014_scene_0004_cfg_0006_037522061512#325", + "gt": "[[248, 110], [259, 108], [259, 113], [241, 104], [216, 108], [206, 115], [201, 123], [205, 125], [205, 134], [201, 135]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "35069_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the towel and put it on the couch', and now you are performing subtask 'fold the towel together.'\nWith start location [197, 109], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[197, 109], [179, 105], [166, 129], [163, 122], [170, 88], [191, 69], [216, 70], [232, 98], [218, 104], [202, 80]]}" + } + ], + "images": "35069_exterior_image_1_left#374", + "gt": "[[197, 109], [179, 105], [166, 129], [163, 122], [170, 88], [191, 69], [216, 70], [232, 98], [218, 104], [202, 80]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0094_user_0014_scene_0003_cfg_0004_104422070011#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open a box', and now you are performing subtask 'push the lid on the right side of the box, push the lid on the left side of the box.'\nFrom start point [336, 102], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[336, 102], [332, 71], [296, 79], [305, 97], [288, 109], [309, 117], [284, 170], [215, 179], [221, 188], [254, 173]]}" + } + ], + "images": "RH20T_cfg4_task_0094_user_0014_scene_0003_cfg_0004_104422070011#0", + "gt": "[[336, 102], [332, 71], [296, 79], [305, 97], [288, 109], [309, 117], [284, 170], [215, 179], [221, 188], [254, 173]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "15833_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close the top drawer at the left of the oven', and now you are performing subtask 'close the top drawer at the left of the oven.'\nStart at [131, 4]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[131, 4], [179, 35], [190, 53], [217, 63], [234, 84], [214, 92], [187, 71], [189, 75], [175, 79], [162, 72]]}" + } + ], + "images": "15833_exterior_image_1_left#0", + "gt": "[[131, 4], [179, 35], [190, 53], [217, 63], [234, 84], [214, 92], [187, 71], [189, 75], [175, 79], [162, 72]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "591_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn off the switch of the extension cord', and now you are performing subtask 'turn off the switch of the extension cord.'\nThe trajectory starts at [192, 0]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[192, 0], [207, 28], [204, 29], [201, 38], [201, 63], [188, 84], [187, 97], [180, 88], [187, 53], [202, 31]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/591_exterior_image_1_left#0.jpg", + "gt": "[[192, 0], [207, 28], [204, 29], [201, 38], [201, 63], [188, 84], [187, 97], [180, 88], [187, 53], [202, 31]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg3_task_0003_user_0016_scene_0001_cfg_0003_104122063550#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press three buttons from left to right in sequence', and now you are performing subtask 'press the green button on the right, press the green button in the middle.'\nStart at [303, 347]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[303, 347], [296, 342], [296, 316], [284, 272], [287, 276], [292, 274], [296, 265], [295, 226], [298, 224], [305, 228]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg3_task_0003_user_0016_scene_0001_cfg_0003_104122063550#160.jpg", + "gt": "[[303, 347], [296, 342], [296, 316], [284, 272], [287, 276], [292, 274], [296, 265], [295, 226], [298, 224], [305, 228]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0094_user_0007_scene_0009_cfg_0005_036422060215#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open a box', and now you are performing subtask 'press the cardboard box on the side, press the cardboard box on the side.'\nFrom start point [290, 119], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[290, 119], [285, 123], [272, 125], [256, 123], [248, 136], [253, 125], [272, 120], [275, 122], [276, 137], [274, 122]]}" + } + ], + "images": "RH20T_cfg5_task_0094_user_0007_scene_0009_cfg_0005_036422060215#188", + "gt": "[[290, 119], [285, 123], [272, 125], [256, 123], [248, 136], [253, 125], [272, 120], [275, 122], [276, 137], [274, 122]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0035_user_0017_scene_0005_cfg_0004_104122062823#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up a small block', and now you are performing subtask 'pick up a small block.'\nYour initial coordinate is [289, 0]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[289, 0], [262, 0], [282, 0], [276, 0], [253, 76], [270, 114], [270, 120], [263, 117], [291, 17], [296, 18]]}" + } + ], + "images": "RH20T_cfg4_task_0035_user_0017_scene_0005_cfg_0004_104122062823#0", + "gt": "[[289, 0], [262, 0], [282, 0], [276, 0], [253, 76], [270, 114], [270, 120], [263, 117], [291, 17], [296, 18]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "71065_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'push the lid', and now you are performing subtask 'push the lid.'\nYou start from [167, 0]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[167, 0], [187, 35], [181, 34], [179, 56], [174, 66], [167, 67], [183, 48], [189, 27], [188, 16], [186, 19]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/71065_exterior_image_2_left#0.jpg", + "gt": "[[167, 0], [187, 35], [181, 34], [179, 56], [174, 66], [167, 67], [183, 48], [189, 27], [188, 16], [186, 19]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0094_user_0007_scene_0006_cfg_0005_104422070044#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open a box', and now you are performing subtask 'press the part of the box.'\nYou begin at [422, 142]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[422, 142], [424, 141], [443, 151], [442, 161], [440, 157], [436, 153], [430, 150], [427, 147], [422, 145], [420, 149]]}" + } + ], + "images": "RH20T_cfg5_task_0094_user_0007_scene_0006_cfg_0005_104422070044#97", + "gt": "[[422, 142], [424, 141], [443, 151], [442, 161], [440, 157], [436, 153], [430, 150], [427, 147], [422, 145], [420, 149]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0020_user_0014_scene_0001_cfg_0006_104122064161#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn on the desk lamp by pressing the button', and now you are performing subtask 'turn on the desk lamp by pressing the button.'\nBegin at [338, 110] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[338, 110], [341, 103], [330, 92], [334, 87], [326, 96], [312, 86], [316, 97], [328, 105], [330, 103], [330, 103]]}" + } + ], + "images": "RH20T_cfg6_task_0020_user_0014_scene_0001_cfg_0006_104122064161#0", + "gt": "[[338, 110], [341, 103], [330, 92], [334, 87], [326, 96], [312, 86], [316, 97], [328, 105], [330, 103], [330, 103]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg2_task_0042_user_0007_scene_0002_cfg_0002_037522062165#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'screw the lid onto the jar (needs to be rotated)', and now you are performing subtask 'twist the lid clockwise to the jar.'\nYour starting position is [251, 249]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[251, 249], [248, 254], [247, 252], [243, 253], [245, 255], [244, 257], [246, 257], [244, 260], [253, 260], [249, 264]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg2_task_0042_user_0007_scene_0002_cfg_0002_037522062165#796.jpg", + "gt": "[[251, 249], [248, 254], [247, 252], [243, 253], [245, 255], [244, 257], [246, 257], [244, 260], [253, 260], [249, 264]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "275_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the white mug on the left side of the counter, put it under the running faucet then place it down on the right side of the counter', and now you are performing subtask 'pick up the white mug on the left side of the counter.'\nYou begin at [37, 144]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[37, 144], [37, 135], [38, 136], [38, 138], [41, 138], [39, 138], [39, 139], [35, 139], [34, 138], [31, 137]]}" + } + ], + "images": "275_exterior_image_1_left#138", + "gt": "[[37, 144], [37, 135], [38, 136], [38, 138], [41, 138], [39, 138], [39, 139], [35, 139], [34, 138], [31, 137]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0029_user_0020_scene_0010_cfg_0007_104122061018#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'grasp the handle and open the drawer', and now you are performing subtask 'grasp the handle and open the drawer.'\nThe trajectory starts at [363, 31]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[363, 31], [339, 79], [354, 98], [356, 128], [311, 176], [305, 205], [275, 135], [275, 111], [293, 68], [337, 36]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg7_task_0029_user_0020_scene_0010_cfg_0007_104122061018#0.jpg", + "gt": "[[363, 31], [339, 79], [354, 98], [356, 128], [311, 176], [305, 205], [275, 135], [275, 111], [293, 68], [337, 36]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg3_task_0057_user_0010_scene_0002_cfg_0003_104122062823#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn on the power strips', and now you are performing subtask 'press the second button on the power strip, press the third button on the power strip.'\nYour initial coordinate is [288, 114]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[288, 114], [287, 109], [288, 107], [290, 107], [286, 111], [287, 115], [287, 112], [284, 107], [290, 108], [290, 106]]}" + } + ], + "images": "RH20T_cfg3_task_0057_user_0010_scene_0002_cfg_0003_104122062823#207", + "gt": "[[288, 114], [287, 109], [288, 107], [290, 107], [286, 111], [287, 115], [287, 112], [284, 107], [290, 108], [290, 106]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0075_user_0007_scene_0004_cfg_0005_105422061350#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'finish setting up the starting position of the chessboard that is almost arranged', and now you are performing subtask 'pick up the black chess piece on the table, transfer the black chess piece from the table to the chessboard, place the black chess piece next to the black chess piece on the chessboard.'\nStarting at [276, 47], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[276, 47], [268, 75], [294, 130], [296, 152], [304, 166], [288, 140], [280, 136], [261, 145], [251, 124], [251, 124]]}" + } + ], + "images": "RH20T_cfg5_task_0075_user_0007_scene_0004_cfg_0005_105422061350#0", + "gt": "[[276, 47], [268, 75], [294, 130], [296, 152], [304, 166], [288, 140], [280, 136], [261, 145], [251, 124], [251, 124]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "61454_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the spoon and ladle from the rack, put them on the table, and then move the rack to the right', and now you are performing subtask 'push the rack to the right.'\nYour initial coordinate is [276.0, 53.5]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[276.0, 53.5], [256.0, 37.5], [208.0, 43.5], [213.0, 51.5], [212.0, 29.5], [250.0, 16.5], [276.0, 31.5], [281.0, 45.5], [252.0, 10.5], [252.0, 10.5]]}" + } + ], + "images": "61454_exterior_image_1_left#380", + "gt": "[[276.0, 53.5], [256.0, 37.5], [208.0, 43.5], [213.0, 51.5], [212.0, 29.5], [250.0, 16.5], [276.0, 31.5], [281.0, 45.5], [252.0, 10.5], [252.0, 10.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0085_user_0007_scene_0006_cfg_0005_105422061350#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the bubble ring from the assembled bubble ring and ball and place it on the table', and now you are performing subtask 'remove the bubble ring from the assembled bubble ring and ball and place it on the table.'\nStart at [276, 47]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[276, 47], [270, 56], [225, 61], [204, 128], [207, 189], [216, 190], [210, 186], [210, 195], [215, 147], [215, 147]]}" + } + ], + "images": "RH20T_cfg5_task_0085_user_0007_scene_0006_cfg_0005_105422061350#0", + "gt": "[[276, 47], [270, 56], [225, 61], [204, 128], [207, 189], [216, 190], [210, 186], [210, 195], [215, 147], [215, 147]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "10503_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the white towel then set it down again', and now you are performing subtask 'press the white towel.'\nThe trajectory starts at [169, 13]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[169, 13], [182, 40], [186, 66], [179, 68], [191, 81], [186, 107], [194, 54], [201, 49], [177, 104], [192, 58]]}" + } + ], + "images": "10503_exterior_image_1_left#0", + "gt": "[[169, 13], [182, 40], [186, 66], [179, 68], [191, 81], [186, 107], [194, 54], [201, 49], [177, 104], [192, 58]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "73618_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the white doll in the silver pot', and now you are performing subtask 'put the white doll in the silver pot.'\nWith start location [81.0, 44.5], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[81.0, 44.5], [112.0, 69.5], [141.0, 100.5], [148.0, 112.5], [150.0, 135.5], [157.0, 141.5], [142.0, 104.5], [132.0, 99.5], [130.0, 105.5], [123.0, 95.5]]}" + } + ], + "images": "73618_exterior_image_1_left#0", + "gt": "[[81.0, 44.5], [112.0, 69.5], [141.0, 100.5], [148.0, 112.5], [150.0, 135.5], [157.0, 141.5], [142.0, 104.5], [132.0, 99.5], [130.0, 105.5], [123.0, 95.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "7930_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'use the towel to wipe the table', and now you are performing subtask 'push the fabric on the table to the left.'\nStart at [94, 0]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[94, 0], [131, 0], [173, 15], [191, 34], [214, 89], [213, 93], [199, 93], [175, 80], [172, 77], [174, 57]]}" + } + ], + "images": "7930_exterior_image_1_left#0", + "gt": "[[94, 0], [131, 0], [173, 15], [191, 34], [214, 89], [213, 93], [199, 93], [175, 80], [172, 77], [174, 57]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "70557_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put a corner of the green towel on the brown teddy bear toy', and now you are performing subtask 'put a corner of the green towel on the brown teddy bear toy.'\nYour initial coordinate is [159, 5]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[159, 5], [188, 63], [188, 79], [198, 88], [188, 74], [180, 71], [166, 74], [156, 85], [155, 69], [162, 59]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/70557_exterior_image_1_left#0.jpg", + "gt": "[[159, 5], [188, 63], [188, 79], [198, 88], [188, 74], [180, 71], [166, 74], [156, 85], [155, 69], [162, 59]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "85934_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the marker in the bowl', and now you are performing subtask 'put the marker in the bowl.'\nStarting at [315, 1], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[315, 1], [270, 16], [233, 52], [216, 57], [222, 58], [210, 58], [189, 76], [185, 62], [189, 31], [181, 37]]}" + } + ], + "images": "85934_exterior_image_2_left#0", + "gt": "[[315, 1], [270, 16], [233, 52], [216, 57], [222, 58], [210, 58], [189, 76], [185, 62], [189, 31], [181, 37]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "83937_exterior_image_2_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the rectangle block from the table and put it on top of the toy tower blocks', and now you are performing subtask 'place the rectangular block on the top of the tower toy blocks.'\nYou begin at [163, 105]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[163, 105], [167, 108], [166, 97], [159, 88], [147, 87], [146, 90], [144, 91], [145, 91], [146, 80], [149, 70]]}" + } + ], + "images": "83937_exterior_image_2_left#170", + "gt": "[[163, 105], [167, 108], [166, 97], [159, 88], [147, 87], [146, 90], [144, 91], [145, 91], [146, 80], [149, 70]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0094_user_0007_scene_0009_cfg_0005_104122061850#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open a box', and now you are performing subtask 'press the cardboard box on the side, press the cardboard box on the side.'\nYour initial coordinate is [343, 145]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[343, 145], [357, 99], [364, 107], [360, 99], [355, 98], [345, 120], [344, 133], [339, 129], [338, 124], [350, 129]]}" + } + ], + "images": "RH20T_cfg5_task_0094_user_0007_scene_0009_cfg_0005_104122061850#235", + "gt": "[[343, 145], [357, 99], [364, 107], [360, 99], [355, 98], [345, 120], [344, 133], [339, 129], [338, 124], [350, 129]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0064_user_0015_scene_0010_cfg_0001_819112070044#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the roll of paper from the desk and place it on the shelf', and now you are performing subtask 'pick up the roll of paper from the desk and place it on the shelf.'\nBegin at [400, 167] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[400, 167], [375, 150], [321, 188], [344, 244], [331, 247], [319, 228], [319, 295], [305, 228], [384, 180], [388, 190]]}" + } + ], + "images": "RH20T_cfg1_task_0064_user_0015_scene_0010_cfg_0001_819112070044#0", + "gt": "[[400, 167], [375, 150], [321, 188], [344, 244], [331, 247], [319, 228], [319, 295], [305, 228], [384, 180], [388, 190]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "16021_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the white lid from the container and put it on the table', and now you are performing subtask 'press the white lid.'\nBegin at [279, 11] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[279, 11], [227, 30], [222, 34], [225, 38], [206, 38], [218, 60], [217, 63], [211, 59], [211, 64], [209, 59]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/16021_exterior_image_1_left#0.jpg", + "gt": "[[279, 11], [227, 30], [222, 34], [225, 38], [206, 38], [218, 60], [217, 63], [211, 59], [211, 64], [209, 59]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0035_user_0016_scene_0001_cfg_0004_104122062823#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up a small block', and now you are performing subtask 'pick up a small block.'\nYou begin at [290, 0]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[290, 0], [354, 0], [344, 6], [355, 36], [346, 61], [355, 69], [354, 84], [358, 58], [356, 34], [359, 36]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg4_task_0035_user_0016_scene_0001_cfg_0004_104122062823#0.jpg", + "gt": "[[290, 0], [354, 0], [344, 6], [355, 36], [346, 61], [355, 69], [354, 84], [358, 58], [356, 34], [359, 36]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "81663_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the cup and put it on top of the table, then pick up the cloth and put it in the bowl and close the drawer', and now you are performing subtask 'place the cloth into the bowl.'\nYour starting position is [186, 11]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[186, 11], [193, 25], [189, 17], [193, 25], [180, 39], [181, 53], [184, 44], [219, 12], [243, 7], [237, 13]]}" + } + ], + "images": "81663_exterior_image_1_left#159", + "gt": "[[186, 11], [193, 25], [189, 17], [193, 25], [180, 39], [181, 53], [184, 44], [219, 12], [243, 7], [237, 13]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0039_user_0007_scene_0007_cfg_0005_104122063678#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pour the water from a cup into another empty cup', and now you are performing subtask 'pour the water from a cup into another empty cup.'\nFrom start point [323, 132], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[323, 132], [317, 108], [332, 126], [322, 147], [329, 133], [348, 138], [356, 192], [368, 194], [336, 134], [324, 167]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0039_user_0007_scene_0007_cfg_0005_104122063678#0.jpg", + "gt": "[[323, 132], [317, 108], [332, 126], [322, 147], [329, 133], [348, 138], [356, 192], [368, 194], [336, 134], [324, 167]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0034_user_0016_scene_0009_cfg_0004_104122062823#TrajectoryPrediction_Task#12", + "task": "TrajectoryPrediction_Task", + "p_index": 12, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the squares into a pyramid shape', and now you are performing subtask 'pick up the third block on the cardboard, transfer the third block from the cardboard to on top of the first and second blocks, place the third block on top of the first and second blocks.'\nThe trajectory starts at [353, 77]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[353, 77], [322, 57], [301, 58], [297, 89], [283, 107], [341, 65], [381, 69], [376, 36], [349, 20], [312, 16]]}" + } + ], + "images": "RH20T_cfg4_task_0034_user_0016_scene_0009_cfg_0004_104122062823#366", + "gt": "[[353, 77], [322, 57], [301, 58], [297, 89], [283, 107], [341, 65], [381, 69], [376, 36], [349, 20], [312, 16]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0094_user_0014_scene_0010_cfg_0001_038522063145#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open a box', and now you are performing subtask 'fold the fourth lid on the box on the table.'\nStart at [472, 153]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[472, 153], [495, 133], [492, 146], [492, 134], [536, 121], [554, 135], [535, 146], [539, 110], [529, 102], [509, 110]]}" + } + ], + "images": "RH20T_cfg1_task_0094_user_0014_scene_0010_cfg_0001_038522063145#191", + "gt": "[[472, 153], [495, 133], [492, 146], [492, 134], [536, 121], [554, 135], [535, 146], [539, 110], [529, 102], [509, 110]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "79403_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the cauliflower, red ball, and light blue object into the silver bowl', and now you are performing subtask 'pick up the red ball from the blue bowl.'\nWith start location [239, 75], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[239, 75], [231, 73], [234, 100], [232, 85], [219, 89], [205, 112], [205, 121], [228, 91], [236, 92], [236, 101]]}" + } + ], + "images": "79403_exterior_image_2_left#0", + "gt": "[[239, 75], [231, 73], [234, 100], [232, 85], [219, 89], [205, 112], [205, 121], [228, 91], [236, 92], [236, 101]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "57625_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'cover the pan with the silver lid', and now you are performing subtask 'cover the pan with the silver lid.'\nWith start location [221.5, 4.0], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[221.5, 4.0], [218.5, 109.0], [214.5, 89.0], [197.5, 112.0], [190.5, 103.0], [187.5, 116.0], [197.5, 120.0], [190.5, 111.0], [192.5, 92.0], [192.5, 92.0]]}" + } + ], + "images": "57625_exterior_image_1_left#0", + "gt": "[[221.5, 4.0], [218.5, 109.0], [214.5, 89.0], [197.5, 112.0], [190.5, 103.0], [187.5, 116.0], [197.5, 120.0], [190.5, 111.0], [192.5, 92.0], [192.5, 92.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "31545_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close the top drawer on the left', and now you are performing subtask 'push the handle of the top drawer on the left to close the drawer.'\nYou start from [169, 95]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[169, 95], [166, 96], [164, 100], [161, 101], [158, 106], [157, 106], [155, 109], [152, 109], [153, 109], [153, 111]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/31545_exterior_image_1_left#47.jpg", + "gt": "[[169, 95], [166, 96], [164, 100], [161, 101], [158, 106], [157, 106], [155, 109], [152, 109], [153, 109], [153, 111]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "72158_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the yellow cylinder inside the orange pot', and now you are performing subtask 'put the yellow cylinder inside the orange pot.'\nStarting at [179, 2], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[179, 2], [193, 26], [197, 44], [198, 65], [204, 82], [210, 88], [214, 72], [213, 47], [205, 70], [206, 50]]}" + } + ], + "images": "72158_exterior_image_1_left#0", + "gt": "[[179, 2], [193, 26], [197, 44], [198, 65], [204, 82], [210, 88], [214, 72], [213, 47], [205, 70], [206, 50]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "52362_exterior_image_1_left#TrajectoryPrediction_Task#10", + "task": "TrajectoryPrediction_Task", + "p_index": 10, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'arrange the two small pillows against the right armrest of the sofa', and now you are performing subtask 'pick up the small pillow on the left side of the sofa.'\nStart at [164, 100]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[164, 100], [166, 105], [176, 113], [176, 115], [171, 116], [164, 123], [161, 109], [162, 103], [160, 104], [174, 112]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/52362_exterior_image_1_left#506.jpg", + "gt": "[[164, 100], [166, 105], [176, 113], [176, 115], [171, 116], [164, 123], [161, 109], [162, 103], [160, 104], [174, 112]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "75634_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the drawer, take out the fruit toy, place it in the basket, and then close the drawer', and now you are performing subtask 'pull the handle of the drawer to open the drawer.'\nWith start location [197.5, 64.5], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[197.5, 64.5], [185.5, 39.5], [189.5, 44.5], [175.5, 46.5], [161.5, 58.5], [166.5, 86.5], [156.5, 95.5], [189.5, 100.5], [187.5, 79.5], [171.5, 69.5]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/75634_exterior_image_1_left#0.jpg", + "gt": "[[197.5, 64.5], [185.5, 39.5], [189.5, 44.5], [175.5, 46.5], [161.5, 58.5], [166.5, 86.5], [156.5, 95.5], [189.5, 100.5], [187.5, 79.5], [171.5, 69.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0075_user_0007_scene_0004_cfg_0005_104122063678#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'finish setting up the starting position of the chessboard that is almost arranged', and now you are performing subtask 'place the black chess piece next to the black chess piece on the chessboard, pick up the white chess piece on the table, transfer the white chess piece from the table to the white chess piece on the chessboard, place the white chess piece next to the white chess piece on the chessboard.'\nYou begin at [302, 198]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[302, 198], [309, 185], [385, 181], [402, 185], [405, 200], [406, 194], [381, 197], [387, 190], [396, 183], [433, 176]]}" + } + ], + "images": "RH20T_cfg5_task_0075_user_0007_scene_0004_cfg_0005_104122063678#426", + "gt": "[[302, 198], [309, 185], [385, 181], [402, 185], [405, 200], [406, 194], [381, 197], [387, 190], [396, 183], [433, 176]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "17981_exterior_image_2_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the orange cloth', and now you are performing subtask 'push the cloth to the right side of the table.'\nYou begin at [229, 135]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[229, 135], [229, 139], [234, 145], [232, 146], [234, 150], [234, 152], [231, 156], [231, 160], [229, 160], [221, 153]]}" + } + ], + "images": "17981_exterior_image_2_left#105", + "gt": "[[229, 135], [229, 139], [234, 145], [232, 146], [234, 150], [234, 152], [231, 156], [231, 160], [229, 160], [221, 153]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "74724_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'throw the pen from the table into the green bowl', and now you are performing subtask 'throw the pen from the table into the green bowl.'\nFrom start point [319, 20], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[319, 20], [277, 36], [223, 70], [169, 115], [160, 125], [162, 131], [161, 88], [167, 49], [164, 47], [159, 50]]}" + } + ], + "images": "74724_exterior_image_2_left#0", + "gt": "[[319, 20], [277, 36], [223, 70], [169, 115], [160, 125], [162, 131], [161, 88], [167, 49], [164, 47], [159, 50]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg3_task_0003_user_0016_scene_0005_cfg_0003_104122062823#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press three buttons in sequence', and now you are performing subtask 'press the green button on the gray and white base.'\nStarting at [311, 63], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[311, 63], [303, 66], [281, 65], [285, 60], [280, 58], [279, 59], [281, 62], [273, 69], [275, 57], [270, 52]]}" + } + ], + "images": "RH20T_cfg3_task_0003_user_0016_scene_0005_cfg_0003_104122062823#266", + "gt": "[[311, 63], [303, 66], [281, 65], [285, 60], [280, 58], [279, 59], [281, 62], [273, 69], [275, 57], [270, 52]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0089_user_0014_scene_0001_cfg_0004_104122062823#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'push an object with obstacles', and now you are performing subtask 'push the block upward, push the block upward, push the block upward.'\nThe trajectory starts at [400, 109]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[400, 109], [387, 111], [391, 113], [407, 119], [418, 116], [425, 106], [424, 93], [416, 93], [437, 99], [454, 109]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg4_task_0089_user_0014_scene_0001_cfg_0004_104122062823#220.jpg", + "gt": "[[400, 109], [387, 111], [391, 113], [407, 119], [418, 116], [425, 106], [424, 93], [416, 93], [437, 99], [454, 109]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg3_task_0018_user_0010_scene_0003_cfg_0003_036422060909#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'transfer the wooden block from the block pile to the tabletop', and now you are performing subtask 'transfer the wooden block from the block pile to the tabletop.'\nYour initial coordinate is [339, 87]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[339, 87], [330, 72], [335, 97], [309, 88], [288, 104], [307, 142], [278, 109], [287, 102], [300, 124], [305, 100]]}" + } + ], + "images": "RH20T_cfg3_task_0018_user_0010_scene_0003_cfg_0003_036422060909#0", + "gt": "[[339, 87], [330, 72], [335, 97], [309, 88], [288, 104], [307, 142], [278, 109], [287, 102], [300, 124], [305, 100]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "21213_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the two paper bags out of the wooden crate', and now you are performing subtask 'place the bag in the box.'\nYou start from [217, 131]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[217, 131], [209, 135], [212, 140], [216, 102], [224, 107], [236, 101], [236, 109], [242, 105], [224, 117], [228, 120]]}" + } + ], + "images": "21213_exterior_image_1_left#0", + "gt": "[[217, 131], [209, 135], [212, 140], [216, 102], [224, 107], [236, 101], [236, 109], [242, 105], [224, 117], [228, 120]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "16021_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the white lid from the container and put it on the table', and now you are performing subtask 'place the white lid on the tabletop.'\nStarting at [206, 60], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[206, 60], [201, 61], [205, 60], [205, 47], [200, 36], [188, 39], [181, 48], [190, 111], [184, 108], [189, 69]]}" + } + ], + "images": "16021_exterior_image_1_left#187", + "gt": "[[206, 60], [201, 61], [205, 60], [205, 47], [200, 36], [188, 39], [181, 48], [190, 111], [184, 108], [189, 69]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "91717_exterior_image_2_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the orange cloth', and now you are performing subtask 'fold the orange cloth on the tabletop.'\nStart at [198, 98]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[198, 98], [194, 98], [198, 111], [191, 115], [215, 113], [285, 123], [220, 85], [208, 76], [204, 70], [209, 72]]}" + } + ], + "images": "91717_exterior_image_2_left#106", + "gt": "[[198, 98], [194, 98], [198, 111], [191, 115], [215, 113], [285, 123], [220, 85], [208, 76], [204, 70], [209, 72]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0003_user_0010_scene_0005_cfg_0005_036422060215#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press three buttons from left to right in sequence', and now you are performing subtask 'press the green button on the right.'\nYou start from [286, 108]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[286, 108], [286, 114], [303, 111], [312, 119], [312, 111], [308, 117], [300, 116], [303, 144], [309, 120], [290, 130]]}" + } + ], + "images": "RH20T_cfg5_task_0003_user_0010_scene_0005_cfg_0005_036422060215#0", + "gt": "[[286, 108], [286, 114], [303, 111], [312, 119], [312, 111], [308, 117], [300, 116], [303, 144], [309, 120], [290, 130]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "89189_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the faucet spout to the left and move the doll forward', and now you are performing subtask 'twist faucet spout clockwise.'\nStart at [155, 0]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[155, 0], [177, 39], [188, 52], [187, 64], [181, 63], [174, 43], [174, 33], [178, 31], [176, 44], [176, 44]]}" + } + ], + "images": "89189_exterior_image_1_left#0", + "gt": "[[155, 0], [177, 39], [188, 52], [187, 64], [181, 63], [174, 43], [174, 33], [178, 31], [176, 44], [176, 44]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0037_user_0020_scene_0009_cfg_0006_104122064161#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'place the first block on the second block, pick up the third block from the table, transfer the third block from the table to the first block, place the third block on the first block, pick up the fourth block from the table.'\nStarting at [354, 125], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[354, 125], [381, 97], [371, 122], [372, 105], [349, 135], [351, 151], [389, 106], [409, 122], [413, 142], [413, 142]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg6_task_0037_user_0020_scene_0009_cfg_0006_104122064161#346.jpg", + "gt": "[[354, 125], [381, 97], [371, 122], [372, 105], [349, 135], [351, 151], [389, 106], [409, 122], [413, 142], [413, 142]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0047_user_0020_scene_0004_cfg_0007_104122064161#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the cup off the cup rack', and now you are performing subtask 'take the cup off the cup rack.'\nStarting at [337, 115], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[337, 115], [369, 131], [381, 114], [398, 124], [403, 146], [406, 111], [382, 85], [378, 99], [379, 75], [372, 83]]}" + } + ], + "images": "RH20T_cfg7_task_0047_user_0020_scene_0004_cfg_0007_104122064161#0", + "gt": "[[337, 115], [369, 131], [381, 114], [398, 124], [403, 146], [406, 111], [382, 85], [378, 99], [379, 75], [372, 83]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "30469_exterior_image_1_left#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the drawer, then take out a plush toy from the drawer, then close the drawer', and now you are performing subtask 'push the drawer back to the closed position.'\nYour initial coordinate is [155, 62]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[155, 62], [164, 57], [198, 82], [211, 85], [218, 90], [214, 101], [180, 102], [195, 93], [198, 86], [198, 86]]}" + } + ], + "images": "30469_exterior_image_1_left#753", + "gt": "[[155, 62], [164, 57], [198, 82], [211, 85], [218, 90], [214, 101], [180, 102], [195, 93], [198, 86], [198, 86]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "43225_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'fold the cloth', and now you are performing subtask 'fold the cloth.'\nYour starting position is [223, 96]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[223, 96], [155, 84], [107, 94], [149, 46], [183, 73], [157, 81], [146, 72], [141, 80], [151, 89], [142, 81]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/43225_exterior_image_2_left#0.jpg", + "gt": "[[223, 96], [155, 84], [107, 94], [149, 46], [183, 73], [157, 81], [146, 72], [141, 80], [151, 89], [142, 81]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "44675_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the maize cob to the left', and now you are performing subtask 'move the maize cob to the left.'\nYou begin at [170, 7]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[170, 7], [205, 106], [221, 125], [209, 153], [221, 152], [215, 158], [167, 106], [161, 134], [150, 96], [157, 95]]}" + } + ], + "images": "44675_exterior_image_1_left#0", + "gt": "[[170, 7], [205, 106], [221, 125], [209, 153], [221, 152], [215, 158], [167, 106], [161, 134], [150, 96], [157, 95]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0094_user_0014_scene_0003_cfg_0004_104122062823#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open a box', and now you are performing subtask 'push the lid on the left side of the box, push the lid on the top of the box.'\nYour starting position is [414, 2]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[414, 2], [419, 10], [417, 36], [418, 35], [418, 11], [419, 7], [418, 1], [415, 0], [434, 0], [413, 0]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg4_task_0094_user_0014_scene_0003_cfg_0004_104122062823#249.jpg", + "gt": "[[414, 2], [419, 10], [417, 36], [418, 35], [418, 11], [419, 7], [418, 1], [415, 0], [434, 0], [413, 0]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "25352_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'fold the white towel from right to left', and now you are performing subtask 'fold the white towel from right to left.'\nThe trajectory starts at [137, 81]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[137, 81], [151, 106], [152, 124], [146, 124], [157, 132], [156, 145], [149, 144], [147, 149], [147, 127], [119, 105]]}" + } + ], + "images": "25352_exterior_image_1_left#0", + "gt": "[[137, 81], [151, 106], [152, 124], [146, 124], [157, 132], [156, 145], [149, 144], [147, 149], [147, 127], [119, 105]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0094_user_0007_scene_0006_cfg_0005_037522062165#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open a box', and now you are performing subtask 'press the part of the box, press the part of the box.'\nStart at [289, 152]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[289, 152], [274, 154], [250, 165], [243, 209], [231, 231], [236, 238], [256, 248], [264, 264], [260, 256], [235, 244]]}" + } + ], + "images": "RH20T_cfg5_task_0094_user_0007_scene_0006_cfg_0005_037522062165#0", + "gt": "[[289, 152], [274, 154], [250, 165], [243, 209], [231, 231], [236, 238], [256, 248], [264, 264], [260, 256], [235, 244]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "86129_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the pen from the cup and put it on the table', and now you are performing subtask 'pick up the pen from the cup and put it on the table.'\nWith start location [286, 0], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[286, 0], [282, 18], [246, 30], [231, 63], [174, 102], [186, 100], [176, 119], [217, 53], [237, 106], [221, 105]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/86129_exterior_image_2_left#0.jpg", + "gt": "[[286, 0], [282, 18], [246, 30], [231, 63], [174, 102], [186, 100], [176, 119], [217, 53], [237, 106], [221, 105]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "69880_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the masking tape from the rack', and now you are performing subtask 'remove the masking tape from the rack.'\nYour initial coordinate is [145, 78]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[145, 78], [215, 70], [185, 78], [210, 83], [202, 76], [198, 82], [198, 127], [209, 126], [203, 134], [193, 75]]}" + } + ], + "images": "69880_exterior_image_2_left#0", + "gt": "[[145, 78], [215, 70], [185, 78], [210, 83], [202, 76], [198, 82], [198, 127], [209, 126], [203, 134], [193, 75]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0057_user_0015_scene_0009_cfg_0001_038522063145#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn them on', and now you are performing subtask 'press the first button on the right side of the power strip, press the second button on the right side of the power strip.'\nThe trajectory starts at [441, 99]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[441, 99], [439, 103], [485, 150], [488, 165], [527, 222], [522, 227], [524, 253], [514, 255], [531, 237], [522, 214]]}" + } + ], + "images": "RH20T_cfg1_task_0057_user_0015_scene_0009_cfg_0001_038522063145#0", + "gt": "[[441, 99], [439, 103], [485, 150], [488, 165], [527, 222], [522, 227], [524, 253], [514, 255], [531, 237], [522, 214]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0073_user_0007_scene_0009_cfg_0005_104122063678#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the left block in the drawer', and now you are performing subtask 'pick up the block on the left side of the table, transfer the block from the left side of the table to the drawer, place the block in the drawer.'\nBegin at [390, 147] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[390, 147], [370, 123], [316, 127], [279, 176], [305, 139], [332, 123], [356, 122], [375, 147], [381, 187], [373, 124]]}" + } + ], + "images": "RH20T_cfg5_task_0073_user_0007_scene_0009_cfg_0005_104122063678#333", + "gt": "[[390, 147], [370, 123], [316, 127], [279, 176], [305, 139], [332, 123], [356, 122], [375, 147], [381, 187], [373, 124]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0057_user_0014_scene_0009_cfg_0004_038522062288#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn on the power strips', and now you are performing subtask 'press the first button from the right on the power socket, press the second button from the right on the power socket.'\nWith start location [242, 160], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[242, 160], [239, 150], [230, 147], [223, 155], [222, 163], [230, 160], [238, 160], [240, 165], [241, 151], [245, 158]]}" + } + ], + "images": "RH20T_cfg4_task_0057_user_0014_scene_0009_cfg_0004_038522062288#141", + "gt": "[[242, 160], [239, 150], [230, 147], [223, 155], [222, 163], [230, 160], [238, 160], [240, 165], [241, 151], [245, 158]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "48744_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'slide the grey towel to the left', and now you are performing subtask 'slide the grey towel to the left.'\nThe trajectory starts at [172, 5]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[172, 5], [189, 19], [190, 23], [175, 21], [185, 30], [197, 77], [217, 94], [200, 92], [174, 75], [176, 52]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/48744_exterior_image_1_left#0.jpg", + "gt": "[[172, 5], [189, 19], [190, 23], [175, 21], [185, 30], [197, 77], [217, 94], [200, 92], [174, 75], [176, 52]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0061_user_0020_scene_0001_cfg_0007_104122064161#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the lid of the gift box on the table, then take everything out of the gift box and place it all on the table', and now you are performing subtask 'place the lid on the tabletop, pick up the cube from the gift box, transfer the cube from the gift box to the tabletop, place the cube on the tabletop.'\nYou start from [370, 103]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[370, 103], [375, 97], [380, 104], [392, 141], [392, 158], [396, 162], [395, 148], [388, 130], [399, 137], [396, 209]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg7_task_0061_user_0020_scene_0001_cfg_0007_104122064161#203.jpg", + "gt": "[[370, 103], [375, 97], [380, 104], [392, 141], [392, 158], [396, 162], [395, 148], [388, 130], [399, 137], [396, 209]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0061_user_0001_scene_0005_cfg_0001_819112070044#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take everything out of the gift box', and now you are performing subtask 'pick up the big square from the gift box, transfer the big square from the gift box to above the fabric, place the big square on the fabric, pick up the small square from the gift box.'\nYou begin at [400, 167]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[400, 167], [406, 181], [419, 172], [416, 185], [413, 161], [393, 161], [360, 196], [347, 182], [376, 165], [410, 171]]}" + } + ], + "images": "RH20T_cfg1_task_0061_user_0001_scene_0005_cfg_0001_819112070044#0", + "gt": "[[400, 167], [406, 181], [419, 172], [416, 185], [413, 161], [393, 161], [360, 196], [347, 182], [376, 165], [410, 171]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg3_task_0073_user_0010_scene_0010_cfg_0003_104122062823#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the things in the drawer', and now you are performing subtask 'place the small square in the drawer, push the drawer to close the drawer.'\nYour starting position is [277, 39]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[277, 39], [289, 67], [277, 87], [257, 65], [254, 55], [264, 60], [267, 88], [233, 47], [276, 0], [289, 11]]}" + } + ], + "images": "RH20T_cfg3_task_0073_user_0010_scene_0010_cfg_0003_104122062823#220", + "gt": "[[277, 39], [289, 67], [277, 87], [257, 65], [254, 55], [264, 60], [267, 88], [233, 47], [276, 0], [289, 11]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "66111_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the small bottle backward and then place the big bottle beside the small bottle', and now you are performing subtask 'place the big bottle beside the small bottle.'\nThe trajectory starts at [107.0, 112.5]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[107.0, 112.5], [103.0, 117.5], [104.0, 127.5], [110.0, 117.5], [126.0, 118.5], [134.0, 110.5], [142.0, 111.5], [141.0, 119.5], [139.0, 106.5], [134.0, 99.5]]}" + } + ], + "images": "66111_exterior_image_1_left#372", + "gt": "[[107.0, 112.5], [103.0, 117.5], [104.0, 127.5], [110.0, 117.5], [126.0, 118.5], [134.0, 110.5], [142.0, 111.5], [141.0, 119.5], [139.0, 106.5], [134.0, 99.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "52362_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'arrange the two small pillows against the right armrest of the sofa', and now you are performing subtask 'pick up the small pillow on the right side of the sofa.'\nThe trajectory starts at [202, 87]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[202, 87], [197, 88], [202, 102], [192, 102], [185, 106], [181, 110], [181, 114], [185, 117], [186, 104], [186, 111]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/52362_exterior_image_1_left#0.jpg", + "gt": "[[202, 87], [197, 88], [202, 102], [192, 102], [185, 106], [181, 110], [181, 114], [185, 117], [186, 104], [186, 111]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "90634_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the measuring tape back into the box', and now you are performing subtask 'put the measuring tape back into the box.'\nWith start location [174, 175], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[174, 175], [208, 123], [210, 100], [208, 110], [223, 96], [219, 82], [206, 75], [150, 76], [166, 75], [184, 84]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/90634_exterior_image_2_left#0.jpg", + "gt": "[[174, 175], [208, 123], [210, 100], [208, 110], [223, 96], [219, 82], [206, 75], [150, 76], [166, 75], [184, 84]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0064_user_0016_scene_0003_cfg_0004_104122062823#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the roll of paper down from the shelf', and now you are performing subtask 'pick up the roll of paper from the shelf.'\nYour initial coordinate is [380, 67]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[380, 67], [373, 60], [374, 56], [379, 52], [386, 50], [394, 46], [397, 45], [397, 44], [396, 43], [396, 43]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg4_task_0064_user_0016_scene_0003_cfg_0004_104122062823#153.jpg", + "gt": "[[380, 67], [373, 60], [374, 56], [379, 52], [386, 50], [394, 46], [397, 45], [397, 44], [396, 43], [396, 43]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0094_user_0007_scene_0009_cfg_0005_105422061350#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open a box', and now you are performing subtask 'press the cardboard box on the side.'\nThe trajectory starts at [276, 47]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[276, 47], [263, 38], [258, 38], [256, 40], [242, 35], [240, 38], [242, 26], [244, 22], [243, 31], [243, 25]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0094_user_0007_scene_0009_cfg_0005_105422061350#0.jpg", + "gt": "[[276, 47], [263, 38], [258, 38], [256, 40], [242, 35], [240, 38], [242, 26], [244, 22], [243, 31], [243, 25]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0015_user_0001_scene_0006_cfg_0001_035622060973#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'play the drum', and now you are performing subtask 'play the drum.'\nWith start location [279, 141], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[279, 141], [258, 192], [234, 208], [268, 230], [239, 201], [186, 200], [182, 176], [237, 169], [246, 149], [240, 162]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0015_user_0001_scene_0006_cfg_0001_035622060973#0.jpg", + "gt": "[[279, 141], [258, 192], [234, 208], [268, 230], [239, 201], [186, 200], [182, 176], [237, 169], [246, 149], [240, 162]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "65705_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the towel', and now you are performing subtask 'fold the towel to fully unfold.'\nYour starting position is [141, 99]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[141, 99], [148, 96], [150, 89], [149, 92], [169, 94], [181, 102], [180, 107], [182, 99], [171, 93], [145, 98]]}" + } + ], + "images": "65705_exterior_image_2_left#0", + "gt": "[[141, 99], [148, 96], [150, 89], [149, 92], [169, 94], [181, 102], [180, 107], [182, 99], [171, 93], [145, 98]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg2_task_0003_user_0006_scene_0007_cfg_0002_104422070044#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the three buttons in sequence', and now you are performing subtask 'press the gray base green button.'\nYour starting position is [309, 188]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[309, 188], [335, 198], [374, 181], [371, 184], [380, 194], [377, 206], [387, 215], [382, 224], [381, 215], [376, 220]]}" + } + ], + "images": "RH20T_cfg2_task_0003_user_0006_scene_0007_cfg_0002_104422070044#0", + "gt": "[[309, 188], [335, 198], [374, 181], [371, 184], [380, 194], [377, 206], [387, 215], [382, 224], [381, 215], [376, 220]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "15615_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the marker in the cup then put it back on the table', and now you are performing subtask 'place the marker in the cup.'\nFrom start point [254, 31], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[254, 31], [201, 66], [176, 96], [177, 87], [187, 81], [176, 72], [174, 56], [178, 53], [174, 64], [181, 51]]}" + } + ], + "images": "15615_exterior_image_2_left#0", + "gt": "[[254, 31], [201, 66], [176, 96], [177, 87], [187, 81], [176, 72], [174, 56], [178, 53], [174, 64], [181, 51]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0001_user_0010_scene_0004_cfg_0004_104122062823#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the button from top to bottom', and now you are performing subtask 'press the button on the surface from top to bottom.'\nBegin at [362, 55] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[362, 55], [351, 80], [342, 57], [349, 33], [342, 52], [346, 58], [347, 45], [351, 64], [354, 37], [343, 29]]}" + } + ], + "images": "RH20T_cfg4_task_0001_user_0010_scene_0004_cfg_0004_104122062823#202", + "gt": "[[362, 55], [351, 80], [342, 57], [349, 33], [342, 52], [346, 58], [347, 45], [351, 64], [354, 37], [343, 29]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "37507_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the second drawer from the right, pick up the clear lid from the counter and place it in the open drawer', and now you are performing subtask 'place the clear cup in the second drawer from the right.'\nFrom start point [104.5, 108.0], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[104.5, 108.0], [124.5, 77.0], [157.5, 61.0], [159.5, 71.0], [168.5, 76.0], [149.5, 74.0], [120.5, 92.0], [132.5, 109.0], [144.5, 110.0], [129.5, 82.0]]}" + } + ], + "images": "37507_exterior_image_1_left#132", + "gt": "[[104.5, 108.0], [124.5, 77.0], [157.5, 61.0], [159.5, 71.0], [168.5, 76.0], [149.5, 74.0], [120.5, 92.0], [132.5, 109.0], [144.5, 110.0], [129.5, 82.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "64889_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the lid on the bottle', and now you are performing subtask 'put the lid on the bottle.'\nThe trajectory starts at [230, 36]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[230, 36], [162, 49], [150, 86], [143, 84], [148, 89], [167, 68], [150, 79], [164, 88], [159, 93], [161, 85]]}" + } + ], + "images": "64889_exterior_image_1_left#0", + "gt": "[[230, 36], [162, 49], [150, 86], [143, 84], [148, 89], [167, 68], [150, 79], [164, 88], [159, 93], [161, 85]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "92163_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the towel', and now you are performing subtask 'unfold the towel on the table.'\nYour initial coordinate is [145, 118]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[145, 118], [136, 122], [134, 131], [143, 123], [136, 126], [137, 117], [109, 106], [122, 106], [143, 114], [143, 114]]}" + } + ], + "images": "92163_exterior_image_1_left#253", + "gt": "[[145, 118], [136, 122], [134, 131], [143, 123], [136, 126], [137, 117], [109, 106], [122, 106], [143, 114], [143, 114]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "21978_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the pen on the counter', and now you are performing subtask 'put the pen on the counter.'\nThe trajectory starts at [191, 0]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[191, 0], [183, 8], [196, 6], [189, 13], [130, 33], [138, 37], [128, 55], [134, 7], [145, 6], [195, 56]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/21978_exterior_image_2_left#0.jpg", + "gt": "[[191, 0], [183, 8], [196, 6], [189, 13], [130, 33], [138, 37], [128, 55], [134, 7], [145, 6], [195, 56]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0058_user_0014_scene_0008_cfg_0004_038522062288#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn off the power strips', and now you are performing subtask 'press the third button of the power socket to turn it off, press the fourth button of the power socket to turn it off.'\nBegin at [285, 72] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[285, 72], [285, 70], [288, 69], [288, 70], [293, 74], [293, 75], [290, 70], [279, 67], [274, 67], [273, 65]]}" + } + ], + "images": "RH20T_cfg4_task_0058_user_0014_scene_0008_cfg_0004_038522062288#182", + "gt": "[[285, 72], [285, 70], [288, 69], [288, 70], [293, 74], [293, 75], [290, 70], [279, 67], [274, 67], [273, 65]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0225_user_0014_scene_0006_cfg_0006_104122064161#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the cup into the microwave', and now you are performing subtask 'pick up the cup from above the microwave, transfer the cup from the microwave to inside the microwave, place the cup inside the microwave.'\nThe trajectory starts at [379, 75]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[379, 75], [425, 90], [439, 110], [404, 71], [364, 66], [352, 50], [356, 97], [388, 121], [401, 143], [366, 86]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg6_task_0225_user_0014_scene_0006_cfg_0006_104122064161#394.jpg", + "gt": "[[379, 75], [425, 90], [439, 110], [404, 71], [364, 66], [352, 50], [356, 97], [388, 121], [401, 143], [366, 86]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "78597_exterior_image_1_left#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'fold the towel', and now you are performing subtask 'fold the towel on the countertop.'\nYour starting position is [194, 101]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[194, 101], [191, 98], [192, 93], [187, 91], [184, 94], [187, 102], [185, 103], [188, 107], [187, 93], [192, 98]]}" + } + ], + "images": "78597_exterior_image_1_left#399", + "gt": "[[194, 101], [191, 98], [192, 93], [187, 91], [184, 94], [187, 102], [185, 103], [188, 107], [187, 93], [192, 98]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0037_user_0017_scene_0006_cfg_0004_036422060909#TrajectoryPrediction_Task#8", + "task": "TrajectoryPrediction_Task", + "p_index": 8, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'place the fourth block on top of the third block on the right side of the table, pick up the fifth block from the left side of the table, place the fifth block on top of the fourth block on the right side of the table, transfer the fifth block from the left side of the table to the right side of the table.'\nYou begin at [297, 118]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[297, 118], [281, 113], [224, 132], [216, 146], [225, 154], [242, 125], [261, 109], [291, 98], [295, 108], [341, 79]]}" + } + ], + "images": "RH20T_cfg4_task_0037_user_0017_scene_0006_cfg_0004_036422060909#444", + "gt": "[[297, 118], [281, 113], [224, 132], [216, 146], [225, 154], [242, 125], [261, 109], [291, 98], [295, 108], [341, 79]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "1654_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the whisk to the right, remove the spoon from the cup and put it beside the whisk', and now you are performing subtask 'pick up the spoon from the table.'\nFrom start point [191, 57], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[191, 57], [187, 54], [172, 57], [165, 74], [168, 73], [165, 43], [174, 31], [184, 32], [199, 79], [202, 110]]}" + } + ], + "images": "1654_exterior_image_1_left#235", + "gt": "[[191, 57], [187, 54], [172, 57], [165, 74], [168, 73], [165, 43], [174, 31], [184, 32], [199, 79], [202, 110]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg3_task_0021_user_0010_scene_0009_cfg_0003_036422060909#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn off the desk lamp by pressing the button', and now you are performing subtask 'turn off the desk lamp by pressing the button.'\nBegin at [335, 88] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[335, 88], [293, 65], [312, 90], [304, 114], [324, 103], [262, 129], [231, 166], [228, 189], [238, 192], [219, 194]]}" + } + ], + "images": "RH20T_cfg3_task_0021_user_0010_scene_0009_cfg_0003_036422060909#0", + "gt": "[[335, 88], [293, 65], [312, 90], [304, 114], [324, 103], [262, 129], [231, 166], [228, 189], [238, 192], [219, 194]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0029_user_0014_scene_0005_cfg_0006_104122061018#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the drawer', and now you are performing subtask 'open the drawer.'\nStart at [367, 28]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[367, 28], [362, 21], [369, 25], [371, 16], [366, 13], [358, 26], [388, 57], [404, 111], [424, 74], [424, 55]]}" + } + ], + "images": "RH20T_cfg6_task_0029_user_0014_scene_0005_cfg_0006_104122061018#0", + "gt": "[[367, 28], [362, 21], [369, 25], [371, 16], [366, 13], [358, 26], [388, 57], [404, 111], [424, 74], [424, 55]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "89414_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the marker out of the cup and place it on the table', and now you are performing subtask 'take the marker out of the cup and place it on the table.'\nYou start from [160.5, 21.0]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[160.5, 21.0], [214.5, 53.0], [212.5, 58.0], [226.5, 75.0], [226.5, 64.0], [211.5, 65.0], [204.5, 87.0], [208.5, 87.0], [208.5, 82.0], [202.5, 58.0]]}" + } + ], + "images": "89414_exterior_image_1_left#0", + "gt": "[[160.5, 21.0], [214.5, 53.0], [212.5, 58.0], [226.5, 75.0], [226.5, 64.0], [211.5, 65.0], [204.5, 87.0], [208.5, 87.0], [208.5, 82.0], [202.5, 58.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0105_user_0020_scene_0007_cfg_0006_037522061512#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the object on the shelf', and now you are performing subtask 'pick up the object from the table, transfer the object from the table to the shelf, place the object on the shelf, pick up the object from the tabletop.'\nStarting at [256, 84], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[256, 84], [245, 104], [210, 119], [210, 151], [188, 127], [163, 136], [165, 206], [152, 179], [152, 154], [218, 119]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg6_task_0105_user_0020_scene_0007_cfg_0006_037522061512#0.jpg", + "gt": "[[256, 84], [245, 104], [210, 119], [210, 151], [188, 127], [163, 136], [165, 206], [152, 179], [152, 154], [218, 119]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0015_user_0014_scene_0008_cfg_0007_104122061330#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'play the drum', and now you are performing subtask 'play the drum.'\nStart at [266, 103]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[266, 103], [304, 178], [319, 239], [314, 250], [330, 196], [331, 179], [325, 171], [352, 110], [328, 180], [292, 123]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg7_task_0015_user_0014_scene_0008_cfg_0007_104122061330#0.jpg", + "gt": "[[266, 103], [304, 178], [319, 239], [314, 250], [330, 196], [331, 179], [325, 171], [352, 110], [328, 180], [292, 123]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "43389_exterior_image_1_left#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the top drawer, pick up the watermelon plush toy from the countertop and put it in the basket. pick up the banana plush toy from the basket in the drawer and put it on the countertop. close the top drawer', and now you are performing subtask 'place the banana toy on the table.'\nBegin at [200, 147] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[200, 147], [196, 143], [193, 146], [206, 147], [203, 148], [207, 146], [205, 137], [189, 123], [153, 118], [140, 125]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/43389_exterior_image_1_left#345.jpg", + "gt": "[[200, 147], [196, 143], [193, 146], [206, 147], [203, 148], [207, 146], [205, 137], [189, 123], [153, 118], [140, 125]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0014_user_0014_scene_0008_cfg_0006_104122061018#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the object from the scale', and now you are performing subtask 'remove the object from the scale.'\nYour starting position is [367, 28]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[367, 28], [342, 92], [339, 138], [377, 58], [373, 51], [365, 56], [373, 93], [378, 106], [391, 106], [391, 106]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg6_task_0014_user_0014_scene_0008_cfg_0006_104122061018#0.jpg", + "gt": "[[367, 28], [342, 92], [339, 138], [377, 58], [373, 51], [365, 56], [373, 93], [378, 106], [391, 106], [391, 106]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0074_user_0015_scene_0006_cfg_0004_104422070011#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the button horizontally', and now you are performing subtask 'press the button horizontally.'\nStarting at [334, 100], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[334, 100], [343, 116], [251, 125], [245, 178], [193, 178], [166, 189], [158, 209], [126, 213], [194, 173], [374, 152]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg4_task_0074_user_0015_scene_0006_cfg_0004_104422070011#0.jpg", + "gt": "[[334, 100], [343, 116], [251, 125], [245, 178], [193, 178], [166, 189], [158, 209], [126, 213], [194, 173], [374, 152]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0051_user_0014_scene_0002_cfg_0006_104122061018#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the dish off the dish rack', and now you are performing subtask 'take the dish off the dish rack.'\nStart at [367, 28]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[367, 28], [258, 16], [245, 0], [298, 0], [305, 94], [284, 136], [282, 124], [308, 119], [296, 63], [318, 84]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg6_task_0051_user_0014_scene_0002_cfg_0006_104122061018#0.jpg", + "gt": "[[367, 28], [258, 16], [245, 0], [298, 0], [305, 94], [284, 136], [282, 124], [308, 119], [296, 63], [318, 84]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "14053_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the small brush from the mug and put it on the table. pick up the mug and slightly move it to the right. then pick up the small brush from the table and put it back in the mug', and now you are performing subtask 'place the small brush in the mug.'\nWith start location [183, 73], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[183, 73], [180, 61], [174, 58], [166, 72], [176, 49], [192, 56], [190, 73], [186, 74], [188, 58], [181, 54]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/14053_exterior_image_1_left#326.jpg", + "gt": "[[183, 73], [180, 61], [174, 58], [166, 72], [176, 49], [192, 56], [190, 73], [186, 74], [188, 58], [181, 54]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "11997_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the pen out of the mug and put it on the counter', and now you are performing subtask 'take the pen out of the mug and put it on the counter.'\nYou start from [277, 0]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[277, 0], [275, 18], [283, 28], [276, 57], [251, 73], [269, 48], [265, 41], [252, 45], [231, 81], [231, 81]]}" + } + ], + "images": "11997_exterior_image_2_left#0", + "gt": "[[277, 0], [275, 18], [283, 28], [276, 57], [251, 73], [269, 48], [265, 41], [252, 45], [231, 81], [231, 81]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "30133_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the yellow cob of maize into the white bowl', and now you are performing subtask 'move the yellow cob of maize into the white bowl.'\nWith start location [188, 2], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[188, 2], [192, 37], [189, 82], [201, 96], [198, 41], [175, 24], [160, 26], [146, 46], [143, 72], [149, 33]]}" + } + ], + "images": "30133_exterior_image_1_left#0", + "gt": "[[188, 2], [192, 37], [189, 82], [201, 96], [198, 41], [175, 24], [160, 26], [146, 46], [143, 72], [149, 33]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "61794_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the mug with the marker to the left', and now you are performing subtask 'transfer the screwdriver from the cup to the tabletop.'\nYou begin at [139, 65]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[139, 65], [148, 65], [151, 67], [154, 70], [159, 83], [168, 89], [168, 93], [163, 80], [162, 73], [162, 73]]}" + } + ], + "images": "61794_exterior_image_1_left#0", + "gt": "[[139, 65], [148, 65], [151, 67], [154, 70], [159, 83], [168, 89], [168, 93], [163, 80], [162, 73], [162, 73]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0078_user_0014_scene_0008_cfg_0006_037522061512#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close the microwave door', and now you are performing subtask 'push the door close the microwave door.'\nYour starting position is [257, 27]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[257, 27], [263, 21], [269, 19], [284, 18], [307, 11], [325, 0], [294, 1], [290, 10], [301, 22], [302, 27]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg6_task_0078_user_0014_scene_0008_cfg_0006_037522061512#125.jpg", + "gt": "[[257, 27], [263, 21], [269, 19], [284, 18], [307, 11], [325, 0], [294, 1], [290, 10], [301, 22], [302, 27]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "64234_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'fold the towel diagonally', and now you are performing subtask 'fold the towel diagonally.'\nYour starting position is [179, 119]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[179, 119], [235, 135], [243, 145], [217, 153], [255, 165], [231, 129], [185, 109], [182, 117], [196, 110], [198, 85]]}" + } + ], + "images": "64234_exterior_image_1_left#196", + "gt": "[[179, 119], [235, 135], [243, 145], [217, 153], [255, 165], [231, 129], [185, 109], [182, 117], [196, 110], [198, 85]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0057_user_0007_scene_0003_cfg_0005_104122063678#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn on the power strips', and now you are performing subtask 'press the fourth button on the power socket.'\nYou begin at [286, 221]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[286, 221], [289, 225], [283, 228], [282, 233], [288, 231], [286, 235], [283, 230], [283, 210], [293, 192], [290, 190]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0057_user_0007_scene_0003_cfg_0005_104122063678#643.jpg", + "gt": "[[286, 221], [289, 225], [283, 228], [282, 233], [288, 231], [286, 235], [283, 230], [283, 210], [293, 192], [290, 190]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg3_task_0032_user_0011_scene_0001_cfg_0003_104122062823#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'slide the outer casing onto the gift box', and now you are performing subtask 'slide the outer casing onto the gift box.'\nThe trajectory starts at [259, 127]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[259, 127], [182, 83], [229, 93], [154, 44], [140, 40], [143, 62], [121, 67], [187, 74], [223, 92], [223, 92]]}" + } + ], + "images": "RH20T_cfg3_task_0032_user_0011_scene_0001_cfg_0003_104122062823#368", + "gt": "[[259, 127], [182, 83], [229, 93], [154, 44], [140, 40], [143, 62], [121, 67], [187, 74], [223, 92], [223, 92]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "86836_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'fold the towel', and now you are performing subtask 'fold the towel on the table.'\nYour initial coordinate is [151, 98]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[151, 98], [174, 81], [150, 89], [174, 113], [171, 148], [142, 126], [134, 131], [139, 105], [120, 97], [67, 164]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/86836_exterior_image_1_left#0.jpg", + "gt": "[[151, 98], [174, 81], [150, 89], [174, 113], [171, 148], [142, 126], [134, 131], [139, 105], [120, 97], [67, 164]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0015_user_0014_scene_0005_cfg_0006_104122061602#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'play the drum', and now you are performing subtask 'play the drum.'\nYou begin at [446, 106]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[446, 106], [503, 137], [497, 182], [486, 195], [486, 177], [468, 125], [444, 107], [422, 110], [441, 134], [428, 103]]}" + } + ], + "images": "RH20T_cfg6_task_0015_user_0014_scene_0005_cfg_0006_104122061602#0", + "gt": "[[446, 106], [503, 137], [497, 182], [486, 195], [486, 177], [468, 125], [444, 107], [422, 110], [441, 134], [428, 103]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0066_user_0015_scene_0001_cfg_0004_104122063550#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with large Megabloks', and now you are performing subtask 'build with large Megabloks.'\nStart at [280, 188]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[280, 188], [315, 158], [293, 153], [311, 143], [307, 130], [296, 141], [296, 133], [295, 166], [334, 228], [334, 228]]}" + } + ], + "images": "RH20T_cfg4_task_0066_user_0015_scene_0001_cfg_0004_104122063550#0", + "gt": "[[280, 188], [315, 158], [293, 153], [311, 143], [307, 130], [296, 141], [296, 133], [295, 166], [334, 228], [334, 228]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0108_user_0014_scene_0004_cfg_0001_039422060546#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'sharpen the pencil with a pencil sharpener', and now you are performing subtask 'sharpen the pencil with a pencil sharpener.'\nStart at [265, 124]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[265, 124], [286, 104], [318, 92], [304, 80], [305, 120], [323, 137], [327, 135], [311, 102], [320, 78], [318, 63]]}" + } + ], + "images": "RH20T_cfg1_task_0108_user_0014_scene_0004_cfg_0001_039422060546#0", + "gt": "[[265, 124], [286, 104], [318, 92], [304, 80], [305, 120], [323, 137], [327, 135], [311, 102], [320, 78], [318, 63]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0037_user_0017_scene_0006_cfg_0004_036422060909#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'place the third block on top of the second block on the right side of the table, pick up the fourth block from the left side of the table, transfer the fourth block from the left side of the table to the right side of the table, place the fourth block on top of the third block on the right side of the table.'\nYour starting position is [290, 127]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[290, 127], [270, 115], [227, 138], [224, 149], [247, 180], [257, 138], [273, 113], [292, 102], [287, 110], [297, 118]]}" + } + ], + "images": "RH20T_cfg4_task_0037_user_0017_scene_0006_cfg_0004_036422060909#345", + "gt": "[[290, 127], [270, 115], [227, 138], [224, 149], [247, 180], [257, 138], [273, 113], [292, 102], [287, 110], [297, 118]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "46734_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the pulse oximeter next to the octopus plush toy', and now you are performing subtask 'put the pulse oximeter next to the octopus plush toy.'\nStart at [152, 19]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[152, 19], [181, 59], [178, 96], [201, 114], [193, 121], [209, 82], [219, 83], [212, 106], [212, 86], [220, 82]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/46734_exterior_image_2_left#0.jpg", + "gt": "[[152, 19], [181, 59], [178, 96], [201, 114], [193, 121], [209, 82], [219, 83], [212, 106], [212, 86], [220, 82]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0016_user_0014_scene_0003_cfg_0001_819112070044#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'hit the pool ball', and now you are performing subtask 'hit the pool ball.'\nStart at [399, 166]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[399, 166], [361, 175], [350, 195], [314, 216], [305, 274], [304, 251], [296, 266], [303, 258], [300, 251], [314, 242]]}" + } + ], + "images": "RH20T_cfg1_task_0016_user_0014_scene_0003_cfg_0001_819112070044#0", + "gt": "[[399, 166], [361, 175], [350, 195], [314, 216], [305, 274], [304, 251], [296, 266], [303, 258], [300, 251], [314, 242]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0016_user_0010_scene_0001_cfg_0005_104122063678#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'hit the pool ball', and now you are performing subtask 'hit the pool ball.'\nYou begin at [323, 132]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[323, 132], [324, 156], [300, 200], [279, 204], [295, 207], [296, 181], [327, 189], [298, 166], [303, 194], [323, 152]]}" + } + ], + "images": "RH20T_cfg5_task_0016_user_0010_scene_0001_cfg_0005_104122063678#0", + "gt": "[[323, 132], [324, 156], [300, 200], [279, 204], [295, 207], [296, 181], [327, 189], [298, 166], [303, 194], [323, 152]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0003_user_0014_scene_0010_cfg_0006_104122061602#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press three buttons from left to right in sequence', and now you are performing subtask 'press the green button in the middle, press the yellow button at the top.'\nYou begin at [499, 174]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[499, 174], [496, 152], [485, 141], [478, 140], [467, 146], [471, 149], [472, 141], [478, 132], [475, 127], [473, 128]]}" + } + ], + "images": "RH20T_cfg6_task_0003_user_0014_scene_0010_cfg_0006_104122061602#174", + "gt": "[[499, 174], [496, 152], [485, 141], [478, 140], [467, 146], [471, 149], [472, 141], [478, 132], [475, 127], [473, 128]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "65660_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the object on the upper half of the box', and now you are performing subtask 'put the object on the upper half of the box.'\nYou begin at [203.0, 82.0]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[203.0, 82.0], [178.0, 124.0], [182.0, 123.0], [185.0, 135.0], [179.0, 152.0], [184.0, 162.0], [179.0, 145.0], [186.0, 147.0], [182.0, 149.0], [175.0, 131.0]]}" + } + ], + "images": "65660_exterior_image_1_left#0", + "gt": "[[203.0, 82.0], [178.0, 124.0], [182.0, 123.0], [185.0, 135.0], [179.0, 152.0], [184.0, 162.0], [179.0, 145.0], [186.0, 147.0], [182.0, 149.0], [175.0, 131.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0066_user_0014_scene_0005_cfg_0007_104122063633#TrajectoryPrediction_Task#8", + "task": "TrajectoryPrediction_Task", + "p_index": 8, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with large Megabloks for the nth time with n blocks', and now you are performing subtask 'pick up the block on the flat surface, transfer the block from the flat surface to the other blocks, place the block on the other blocks.'\nFrom start point [188, 160], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[188, 160], [143, 189], [129, 210], [141, 189], [192, 157], [209, 163], [218, 180], [205, 177], [197, 164], [201, 161]]}" + } + ], + "images": "RH20T_cfg7_task_0066_user_0014_scene_0005_cfg_0007_104122063633#587", + "gt": "[[188, 160], [143, 189], [129, 210], [141, 189], [192, 157], [209, 163], [218, 180], [205, 177], [197, 164], [201, 161]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0070_user_0014_scene_0008_cfg_0001_038522062547#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open a sliding window', and now you are performing subtask 'open a sliding window.'\nYour starting position is [404, 132]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[404, 132], [431, 145], [434, 155], [439, 151], [441, 162], [445, 155], [443, 179], [438, 120], [423, 99], [409, 101]]}" + } + ], + "images": "RH20T_cfg1_task_0070_user_0014_scene_0008_cfg_0001_038522062547#0", + "gt": "[[404, 132], [431, 145], [434, 155], [439, 151], [441, 162], [445, 155], [443, 179], [438, 120], [423, 99], [409, 101]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "49706_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the plush toy from the box into the drawer after opening the drawer, then close the drawer', and now you are performing subtask 'pull the drawer handle to the open position.'\nStarting at [243, 82], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[243, 82], [223, 74], [200, 78], [191, 84], [195, 91], [187, 101], [206, 94], [187, 102], [206, 96], [203, 92]]}" + } + ], + "images": "49706_exterior_image_1_left#0", + "gt": "[[243, 82], [223, 74], [200, 78], [191, 84], [195, 91], [187, 101], [206, 94], [187, 102], [206, 96], [203, 92]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg2_task_0015_user_0006_scene_0003_cfg_0002_104422070044#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'play the drum', and now you are performing subtask 'play the drum.'\nWith start location [311, 189], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[311, 189], [350, 205], [362, 233], [357, 239], [384, 240], [357, 257], [366, 274], [350, 291], [352, 297], [303, 251]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg2_task_0015_user_0006_scene_0003_cfg_0002_104422070044#0.jpg", + "gt": "[[311, 189], [350, 205], [362, 233], [357, 239], [384, 240], [357, 257], [366, 274], [350, 291], [352, 297], [303, 251]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0050_user_0020_scene_0008_cfg_0007_104122061330#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the plate on the bowl rack', and now you are performing subtask 'put the plate on the bowl rack.'\nYour starting position is [266, 103]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[266, 103], [320, 156], [324, 151], [341, 186], [318, 159], [317, 82], [348, 0], [343, 30], [326, 15], [296, 51]]}" + } + ], + "images": "RH20T_cfg7_task_0050_user_0020_scene_0008_cfg_0007_104122061330#0", + "gt": "[[266, 103], [320, 156], [324, 151], [341, 186], [318, 159], [317, 82], [348, 0], [343, 30], [326, 15], [296, 51]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "61220_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn off the switch of the fourth position from the left', and now you are performing subtask 'press the switch of the fourth position from the left on the socket.'\nWith start location [206, 131], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[206, 131], [206, 139], [205, 140], [203, 139], [203, 137], [205, 136], [205, 139], [207, 143], [207, 141], [207, 141]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/61220_exterior_image_1_left#153.jpg", + "gt": "[[206, 131], [206, 139], [205, 140], [203, 139], [203, 137], [205, 136], [205, 139], [207, 143], [207, 141], [207, 141]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "54044_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up and put down the green block, then put the salt cellar into the pot and the green block into the sink', and now you are performing subtask 'place the green block on the countertop.'\nThe trajectory starts at [108, 0]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[108, 0], [135, 24], [141, 36], [141, 64], [130, 47], [140, 47], [143, 53], [134, 66], [146, 70], [142, 62]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/54044_exterior_image_2_left#0.jpg", + "gt": "[[108, 0], [135, 24], [141, 36], [141, 64], [130, 47], [140, 47], [143, 53], [134, 66], [146, 70], [142, 62]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "22632_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the towel then fold it again', and now you are performing subtask 'unfold the towel on the table.'\nYou start from [317, 54]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[317, 54], [283, 76], [307, 92], [278, 87], [247, 106], [246, 90], [232, 89], [230, 130], [200, 174], [208, 129]]}" + } + ], + "images": "22632_exterior_image_1_left#0", + "gt": "[[317, 54], [283, 76], [307, 92], [278, 87], [247, 106], [246, 90], [232, 89], [230, 130], [200, 174], [208, 129]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "69180_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the first drawer from the right, remove the glue stick from it and put the glue stick on the counter', and now you are performing subtask 'pick up the glue stick from the first drawer on the right.'\nBegin at [152.5, 40.5] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[152.5, 40.5], [138.5, 47.5], [123.5, 62.5], [137.5, 90.5], [153.5, 81.5], [134.5, 97.5], [127.5, 93.5], [124.5, 84.5], [127.5, 75.5], [135.5, 83.5]]}" + } + ], + "images": "69180_exterior_image_1_left#0", + "gt": "[[152.5, 40.5], [138.5, 47.5], [123.5, 62.5], [137.5, 90.5], [153.5, 81.5], [134.5, 97.5], [127.5, 93.5], [124.5, 84.5], [127.5, 75.5], [135.5, 83.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "64566_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'switch off the toaster', and now you are performing subtask 'switch off the toaster.'\nWith start location [212, 0], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[212, 0], [202, 4], [154, 45], [133, 53], [131, 61], [136, 65], [132, 66], [132, 62], [152, 65], [175, 58]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/64566_exterior_image_2_left#0.jpg", + "gt": "[[212, 0], [202, 4], [154, 45], [133, 53], [131, 61], [136, 65], [132, 66], [132, 62], [152, 65], [175, 58]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0067_user_0015_scene_0006_cfg_0004_104122062823#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press a button from top to bottom with obstacles', and now you are performing subtask 'press a button from top to bottom with obstacles.'\nYour initial coordinate is [291, 0]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[291, 0], [346, 8], [337, 22], [344, 40], [373, 52], [400, 87], [416, 94], [418, 108], [441, 111], [342, 69]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg4_task_0067_user_0015_scene_0006_cfg_0004_104122062823#0.jpg", + "gt": "[[291, 0], [346, 8], [337, 22], [344, 40], [373, 52], [400, 87], [416, 94], [418, 108], [441, 111], [342, 69]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "53612_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the white object on the plate, then pick up the yellow block and move it to the left on the counter, then pick up the object on the plate and put it on the right of the counter', and now you are performing subtask 'pick up the yellow block from the counter.'\nYou start from [70, 1]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[70, 1], [86, 63], [106, 89], [96, 82], [108, 74], [132, 81], [130, 87], [123, 81], [111, 83], [110, 92]]}" + } + ], + "images": "53612_exterior_image_1_left#0", + "gt": "[[70, 1], [86, 63], [106, 89], [96, 82], [108, 74], [132, 81], [130, 87], [123, 81], [111, 83], [110, 92]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0038_user_0014_scene_0006_cfg_0006_104122061602#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the cup', and now you are performing subtask 'pick up the cup.'\nWith start location [446, 106], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[446, 106], [439, 84], [454, 84], [463, 90], [472, 115], [481, 124], [490, 163], [493, 133], [488, 107], [478, 83]]}" + } + ], + "images": "RH20T_cfg6_task_0038_user_0014_scene_0006_cfg_0006_104122061602#0", + "gt": "[[446, 106], [439, 84], [454, 84], [463, 90], [472, 115], [481, 124], [490, 163], [493, 133], [488, 107], [478, 83]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "53689_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the napkin completely', and now you are performing subtask 'unfold the napkin completely.'\nYou start from [256, 90]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[256, 90], [236, 88], [207, 92], [175, 109], [170, 107], [169, 118], [171, 106], [180, 100], [203, 104], [227, 101]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/53689_exterior_image_1_left#0.jpg", + "gt": "[[256, 90], [236, 88], [207, 92], [175, 109], [170, 107], [169, 118], [171, 106], [180, 100], [203, 104], [227, 101]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "79230_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the green bottle to the right of the silver bowl', and now you are performing subtask 'pick up the green bottle on the counter.'\nYou start from [170, 24]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[170, 24], [157, 33], [151, 42], [150, 55], [146, 63], [159, 69], [159, 75], [161, 78], [157, 70], [155, 69]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/79230_exterior_image_2_left#0.jpg", + "gt": "[[170, 24], [157, 33], [151, 42], [150, 55], [146, 63], [159, 69], [159, 75], [161, 78], [157, 70], [155, 69]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "70471_exterior_image_2_left#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the white and black mugs from the drawer, push the drawer closed, close the open bottom cabinet', and now you are performing subtask 'push the door of the lower cabinet closed.'\nStart at [133, 128]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[133, 128], [128, 131], [132, 154], [137, 136], [135, 140], [135, 136], [117, 140], [112, 136], [115, 131], [120, 130]]}" + } + ], + "images": "70471_exterior_image_2_left#800", + "gt": "[[133, 128], [128, 131], [132, 154], [137, 136], [135, 140], [135, 136], [117, 140], [112, 136], [115, 131], [120, 130]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0016_user_0014_scene_0008_cfg_0001_819112071037#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'hit the pool ball', and now you are performing subtask 'hit the pool ball.'\nStarting at [311, 0], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[311, 0], [296, 91], [300, 143], [323, 202], [314, 233], [301, 213], [300, 236], [305, 197], [360, 203], [365, 187]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0016_user_0014_scene_0008_cfg_0001_819112071037#0.jpg", + "gt": "[[311, 0], [296, 91], [300, 143], [323, 202], [314, 233], [301, 213], [300, 236], [305, 197], [360, 203], [365, 187]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "14884_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn on the microwave light, turn off the microwave light', and now you are performing subtask 'press a button on the microwave.'\nYou begin at [109, 105]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[109, 105], [124, 99], [140, 101], [148, 96], [157, 103], [176, 104], [176, 101], [168, 106], [158, 104], [158, 101]]}" + } + ], + "images": "14884_exterior_image_2_left#0", + "gt": "[[109, 105], [124, 99], [140, 101], [148, 96], [157, 103], [176, 104], [176, 101], [168, 106], [158, 104], [158, 101]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0096_user_0015_scene_0001_cfg_0004_104122062823#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take something out of a drawer', and now you are performing subtask 'pull the drawer handle to open the drawer.'\nYou begin at [290, 0]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[290, 0], [315, 0], [288, 9], [310, 0], [299, 16], [326, 25], [373, 18], [364, 15], [380, 11], [376, 0]]}" + } + ], + "images": "RH20T_cfg4_task_0096_user_0015_scene_0001_cfg_0004_104122062823#0", + "gt": "[[290, 0], [315, 0], [288, 9], [310, 0], [299, 16], [326, 25], [373, 18], [364, 15], [380, 11], [376, 0]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "81381_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the red marker into the maroon mug, then take the marker out, and move the mug to the left', and now you are performing subtask 'transfer the red marker from the maroon mug to the table.'\nWith start location [213.5, 41.0], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[213.5, 41.0], [210.5, 37.0], [181.5, 38.0], [179.5, 44.0], [212.5, 73.0], [204.5, 39.0], [175.5, 69.0], [179.5, 90.0], [184.5, 72.0], [184.5, 72.0]]}" + } + ], + "images": "81381_exterior_image_1_left#172", + "gt": "[[213.5, 41.0], [210.5, 37.0], [181.5, 38.0], [179.5, 44.0], [212.5, 73.0], [204.5, 39.0], [175.5, 69.0], [179.5, 90.0], [184.5, 72.0], [184.5, 72.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "51697_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the marker in the mug', and now you are performing subtask 'place the marker in the mug.'\nStart at [255.0, 97.0]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[255.0, 97.0], [250.0, 84.0], [251.0, 54.0], [255.0, 48.0], [264.0, 49.0], [262.0, 64.0], [259.0, 60.0], [259.0, 43.0], [267.0, 36.0], [262.0, 37.0]]}" + } + ], + "images": "51697_exterior_image_1_left#70", + "gt": "[[255.0, 97.0], [250.0, 84.0], [251.0, 54.0], [255.0, 48.0], [264.0, 49.0], [262.0, 64.0], [259.0, 60.0], [259.0, 43.0], [267.0, 36.0], [262.0, 37.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "46053_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'wipe the table with the towel', and now you are performing subtask 'wipe the table with the towel.'\nWith start location [157, 4], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[157, 4], [154, 71], [160, 87], [208, 104], [200, 86], [207, 109], [162, 69], [169, 84], [206, 98], [210, 81]]}" + } + ], + "images": "46053_exterior_image_1_left#0", + "gt": "[[157, 4], [154, 71], [160, 87], [208, 104], [200, 86], [207, 109], [162, 69], [169, 84], [206, 98], [210, 81]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0012_user_0010_scene_0005_cfg_0004_104122062823#TrajectoryPrediction_Task#8", + "task": "TrajectoryPrediction_Task", + "p_index": 8, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'push the soccer ball into the goal', and now you are performing subtask 'push the soccer ball toward the goal.'\nThe trajectory starts at [248, 141]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[248, 141], [250, 148], [248, 154], [245, 156], [239, 153], [238, 154], [238, 177], [245, 190], [245, 192], [247, 192]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg4_task_0012_user_0010_scene_0005_cfg_0004_104122062823#240.jpg", + "gt": "[[248, 141], [250, 148], [248, 154], [245, 156], [239, 153], [238, 154], [238, 177], [245, 190], [245, 192], [247, 192]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0001_user_0014_scene_0007_cfg_0007_104122060811#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the nearest green button', and now you are performing subtask 'press the nearest green button.'\nBegin at [387, 130] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[387, 130], [389, 131], [391, 121], [388, 110], [384, 113], [383, 121], [387, 108], [392, 112], [395, 129], [395, 129]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg7_task_0001_user_0014_scene_0007_cfg_0007_104122060811#0.jpg", + "gt": "[[387, 130], [389, 131], [391, 121], [388, 110], [384, 113], [383, 121], [387, 108], [392, 112], [395, 129], [395, 129]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0094_user_0007_scene_0006_cfg_0005_104422070044#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open a box', and now you are performing subtask 'press the part of the box, press the part of the box.'\nYour starting position is [415, 151]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[415, 151], [420, 149], [435, 134], [443, 119], [444, 126], [442, 117], [416, 137], [405, 150], [399, 161], [398, 160]]}" + } + ], + "images": "RH20T_cfg5_task_0094_user_0007_scene_0006_cfg_0005_104422070044#168", + "gt": "[[415, 151], [420, 149], [435, 134], [443, 119], [444, 126], [442, 117], [416, 137], [405, 150], [399, 161], [398, 160]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "70860_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the cable from the top of the rice cooker', and now you are performing subtask 'remove the cable from the top of the rice cooker.'\nYou start from [227, 88]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[227, 88], [265, 101], [227, 107], [223, 97], [222, 110], [202, 93], [175, 99], [136, 134], [155, 154], [143, 128]]}" + } + ], + "images": "70860_exterior_image_1_left#0", + "gt": "[[227, 88], [265, 101], [227, 107], [223, 97], [222, 110], [202, 93], [175, 99], [136, 134], [155, 154], [143, 128]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "42410_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the pen and put it in the white mug', and now you are performing subtask 'pick up the pen and put it in the white mug.'\nWith start location [94, 43], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[94, 43], [138, 48], [160, 62], [182, 89], [186, 117], [192, 122], [189, 127], [200, 83], [189, 87], [183, 73]]}" + } + ], + "images": "42410_exterior_image_1_left#0", + "gt": "[[94, 43], [138, 48], [160, 62], [182, 89], [186, 117], [192, 122], [189, 127], [200, 83], [189, 87], [183, 73]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "67544_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close the left cabinet's drawer', and now you are performing subtask 'close the left cabinet's drawer.'\nBegin at [137, 113] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[137, 113], [138, 112], [138, 94], [139, 92], [141, 74], [144, 75], [148, 71], [150, 71], [150, 70], [154, 70]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/67544_exterior_image_2_left#0.jpg", + "gt": "[[137, 113], [138, 112], [138, 94], [139, 92], [141, 74], [144, 75], [148, 71], [150, 71], [150, 70], [154, 70]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0037_user_0020_scene_0004_cfg_0006_104122061018#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'place the block on the other block, pick up the block on the surface, transfer the block from the surface to the other block, place the block on the other block.'\nFrom start point [370, 139], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[370, 139], [383, 171], [374, 187], [380, 176], [384, 182], [375, 200], [384, 196], [389, 137], [387, 125], [377, 126]]}" + } + ], + "images": "RH20T_cfg6_task_0037_user_0020_scene_0004_cfg_0006_104122061018#414", + "gt": "[[370, 139], [383, 171], [374, 187], [380, 176], [384, 182], [375, 200], [384, 196], [389, 137], [387, 125], [377, 126]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0103_user_0014_scene_0012_cfg_0004_036422060909#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'drag the plate to the goal post after holding it down', and now you are performing subtask 'push the plate towards the target bar, push the plate towards the target bar.'\nWith start location [339, 80], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[339, 80], [341, 92], [350, 85], [340, 108], [347, 125], [345, 167], [352, 183], [362, 172], [351, 161], [322, 157]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg4_task_0103_user_0014_scene_0012_cfg_0004_036422060909#0.jpg", + "gt": "[[339, 80], [341, 92], [350, 85], [340, 108], [347, 125], [345, 167], [352, 183], [362, 172], [351, 161], [322, 157]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "63897_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the pen from the table and put it in a mug cup', and now you are performing subtask 'pick up the pen from the table and put it in a mug cup.'\nStart at [113.5, 70.0]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[113.5, 70.0], [136.5, 76.0], [157.5, 93.0], [161.5, 106.0], [167.5, 112.0], [169.5, 121.0], [171.5, 105.0], [168.5, 94.0], [165.5, 96.0], [162.5, 90.0]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/63897_exterior_image_1_left#0.jpg", + "gt": "[[113.5, 70.0], [136.5, 76.0], [157.5, 93.0], [161.5, 106.0], [167.5, 112.0], [169.5, 121.0], [171.5, 105.0], [168.5, 94.0], [165.5, 96.0], [162.5, 90.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "36682_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the brown object in the drawer, then put in the white bowl, then put the knife in the drawer', and now you are performing subtask 'place the object in the brown box.'\nYour starting position is [115.5, 7.5]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[115.5, 7.5], [220.5, 28.5], [213.5, 64.5], [171.5, 42.5], [158.5, 70.5], [157.5, 26.5], [208.5, 24.5], [222.5, 31.5], [207.5, 46.5], [212.5, 35.5]]}" + } + ], + "images": "36682_exterior_image_1_left#0", + "gt": "[[115.5, 7.5], [220.5, 28.5], [213.5, 64.5], [171.5, 42.5], [158.5, 70.5], [157.5, 26.5], [208.5, 24.5], [222.5, 31.5], [207.5, 46.5], [212.5, 35.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "14884_exterior_image_2_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn on the microwave light, turn off the microwave light', and now you are performing subtask 'press the button on the microwave again.'\nFrom start point [158, 101], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[158, 101], [158, 96], [161, 97], [163, 96], [173, 102], [172, 107], [166, 111], [159, 112], [157, 114], [151, 113]]}" + } + ], + "images": "14884_exterior_image_2_left#170", + "gt": "[[158, 101], [158, 96], [161, 97], [163, 96], [173, 102], [172, 107], [166, 111], [159, 112], [157, 114], [151, 113]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0034_user_0007_scene_0005_cfg_0005_037522062165#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the squares in a row', and now you are performing subtask 'place the first square in the center of the table, pick up the second square from the table, transfer the second square from the table to the table next to the first square, place the second square on the table next to the first square, pick up the third square from the table.'\nWith start location [264, 223], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[264, 223], [262, 291], [252, 306], [285, 264], [289, 234], [280, 242], [280, 202], [234, 151], [214, 140], [235, 189]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0034_user_0007_scene_0005_cfg_0005_037522062165#247.jpg", + "gt": "[[264, 223], [262, 291], [252, 306], [285, 264], [289, 234], [280, 242], [280, 202], [234, 151], [214, 140], [235, 189]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg2_task_0034_user_0003_scene_0006_cfg_0002_104122061850#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the squares into a pyramid shape', and now you are performing subtask 'place the third square to the right of the first square, pick up the fourth square from the countertop, transfer the fourth square from the countertop to the first and third squares, place the fourth square on the first and third squares.'\nYour initial coordinate is [314, 256]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[314, 256], [310, 243], [325, 241], [372, 258], [385, 253], [397, 258], [394, 267], [325, 236], [308, 236], [313, 241]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg2_task_0034_user_0003_scene_0006_cfg_0002_104122061850#618.jpg", + "gt": "[[314, 256], [310, 243], [325, 241], [372, 258], [385, 253], [397, 258], [394, 267], [325, 236], [308, 236], [313, 241]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg3_task_0057_user_0010_scene_0007_cfg_0003_104122062823#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn on the power strips', and now you are performing subtask 'press the button of the power socket in the first position, press the button of the power socket in the second position.'\nFrom start point [246, 0], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[246, 0], [262, 0], [232, 3], [195, 31], [201, 22], [185, 23], [207, 103], [187, 121], [187, 148], [181, 125]]}" + } + ], + "images": "RH20T_cfg3_task_0057_user_0010_scene_0007_cfg_0003_104122062823#0", + "gt": "[[246, 0], [262, 0], [232, 3], [195, 31], [201, 22], [185, 23], [207, 103], [187, 121], [187, 148], [181, 125]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg2_task_0015_user_0006_scene_0003_cfg_0002_104122063678#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'play the drum', and now you are performing subtask 'play the drum.'\nThe trajectory starts at [289, 199]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[289, 199], [308, 230], [308, 255], [288, 290], [272, 295], [301, 319], [273, 318], [280, 344], [246, 353], [220, 265]]}" + } + ], + "images": "RH20T_cfg2_task_0015_user_0006_scene_0003_cfg_0002_104122063678#0", + "gt": "[[289, 199], [308, 230], [308, 255], [288, 290], [272, 295], [301, 319], [273, 318], [280, 344], [246, 353], [220, 265]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0037_user_0016_scene_0002_cfg_0004_036422060909#TrajectoryPrediction_Task#8", + "task": "TrajectoryPrediction_Task", + "p_index": 8, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'transfer the fourth block from the surface to the position above the third block, place the fourth block on the third block, pick up the fifth block on the surface.'\nStarting at [290, 187], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[290, 187], [290, 114], [294, 78], [296, 87], [304, 91], [302, 86], [299, 84], [291, 87], [291, 57], [293, 60]]}" + } + ], + "images": "RH20T_cfg4_task_0037_user_0016_scene_0002_cfg_0004_036422060909#241", + "gt": "[[290, 187], [290, 114], [294, 78], [296, 87], [304, 91], [302, 86], [299, 84], [291, 87], [291, 57], [293, 60]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "16348_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the lid off the pot', and now you are performing subtask 'take the lid off the pot.'\nYour starting position is [218, 23]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[218, 23], [204, 32], [192, 52], [199, 68], [198, 63], [190, 58], [170, 57], [161, 70], [160, 89], [164, 81]]}" + } + ], + "images": "16348_exterior_image_2_left#0", + "gt": "[[218, 23], [204, 32], [192, 52], [199, 68], [198, 63], [190, 58], [170, 57], [161, 70], [160, 89], [164, 81]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0047_user_0014_scene_0014_cfg_0004_104422070011#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the cup off the cup rack', and now you are performing subtask 'take the cup off the cup rack.'\nThe trajectory starts at [337, 103]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[337, 103], [451, 155], [450, 141], [340, 137], [291, 103], [275, 125], [288, 146], [393, 130], [417, 148], [417, 148]]}" + } + ], + "images": "RH20T_cfg4_task_0047_user_0014_scene_0014_cfg_0004_104422070011#0", + "gt": "[[337, 103], [451, 155], [450, 141], [340, 137], [291, 103], [275, 125], [288, 146], [393, 130], [417, 148], [417, 148]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "57097_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the white cloth on the table', and now you are performing subtask 'put the white cloth on the table.'\nYou begin at [75, 39]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[75, 39], [103, 35], [119, 37], [126, 49], [122, 51], [139, 63], [137, 75], [140, 80], [100, 88], [100, 88]]}" + } + ], + "images": "57097_exterior_image_2_left#0", + "gt": "[[75, 39], [103, 35], [119, 37], [126, 49], [122, 51], [139, 63], [137, 75], [140, 80], [100, 88], [100, 88]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "73153_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn on the main adapter switch', and now you are performing subtask 'press the switch on the main adapter.'\nStart at [119, 42]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[119, 42], [164, 87], [169, 89], [172, 85], [187, 94], [196, 92], [203, 100], [205, 95], [192, 91], [198, 88]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/73153_exterior_image_1_left#0.jpg", + "gt": "[[119, 42], [164, 87], [169, 89], [172, 85], [187, 94], [196, 92], [203, 100], [205, 95], [192, 91], [198, 88]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "7985_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the towel', and now you are performing subtask 'pull the towel to the edge of the table.'\nYour initial coordinate is [195, 110]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[195, 110], [171, 63], [153, 68], [159, 76], [149, 90], [170, 88], [150, 92], [155, 101], [182, 103], [178, 87]]}" + } + ], + "images": "7985_exterior_image_1_left#0", + "gt": "[[195, 110], [171, 63], [153, 68], [159, 76], [149, 90], [170, 88], [150, 92], [155, 101], [182, 103], [178, 87]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "17853_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the spoon out of the mug and put it on the table', and now you are performing subtask 'take the spoon out of the mug and put it on the table.'\nStart at [292.0, 0.5]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[292.0, 0.5], [278.0, 10.5], [249.0, 72.5], [269.0, 7.5], [278.0, 0.0], [292.0, 0.0], [303.0, 12.5], [292.0, 56.5], [312.0, 79.5], [272.0, 41.5]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/17853_exterior_image_1_left#0.jpg", + "gt": "[[292.0, 0.5], [278.0, 10.5], [249.0, 72.5], [269.0, 7.5], [278.0, 0.0], [292.0, 0.0], [303.0, 12.5], [292.0, 56.5], [312.0, 79.5], [272.0, 41.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "2823_exterior_image_1_left#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the fridge', and now you are performing subtask 'pull the fridge handle to open the fridge.'\nFrom start point [132, 90], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[132, 90], [128, 87], [129, 86], [120, 81], [122, 70], [129, 71], [131, 77], [133, 78], [135, 76], [130, 75]]}" + } + ], + "images": "2823_exterior_image_1_left#759", + "gt": "[[132, 90], [128, 87], [129, 86], [120, 81], [122, 70], [129, 71], [131, 77], [133, 78], [135, 76], [130, 75]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0002_user_0014_scene_0003_cfg_0005_104122063678#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pull out a napkin', and now you are performing subtask 'pull out a napkin.'\nWith start location [323, 132], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[323, 132], [350, 128], [362, 160], [356, 173], [344, 180], [377, 123], [373, 127], [344, 90], [332, 82], [339, 97]]}" + } + ], + "images": "RH20T_cfg5_task_0002_user_0014_scene_0003_cfg_0005_104122063678#0", + "gt": "[[323, 132], [350, 128], [362, 160], [356, 173], [344, 180], [377, 123], [373, 127], [344, 90], [332, 82], [339, 97]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "23851_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the apple and lemons inside the glass bowl', and now you are performing subtask 'place the first lemon in the glass bowl.'\nThe trajectory starts at [232, 89]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[232, 89], [209, 109], [186, 114], [174, 134], [182, 110], [202, 91], [223, 92], [224, 109], [227, 102], [220, 92]]}" + } + ], + "images": "23851_exterior_image_1_left#180", + "gt": "[[232, 89], [209, 109], [186, 114], [174, 134], [182, 110], [202, 91], [223, 92], [224, 109], [227, 102], [220, 92]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0037_user_0014_scene_0010_cfg_0001_750612070851#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'place the block from the table onto the three blocks standing upright, pick up the block from the right side of the table, transfer the block from the table to the four blocks standing upright, place the block from the table onto the four blocks standing upright.'\nYour initial coordinate is [416, 294]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[416, 294], [429, 289], [481, 299], [457, 297], [446, 309], [436, 308], [462, 286], [433, 271], [424, 305], [451, 240]]}" + } + ], + "images": "RH20T_cfg1_task_0037_user_0014_scene_0010_cfg_0001_750612070851#331", + "gt": "[[416, 294], [429, 289], [481, 299], [457, 297], [446, 309], [436, 308], [462, 286], [433, 271], [424, 305], [451, 240]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg2_task_0065_user_0007_scene_0010_cfg_0002_105422061350#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with small Lego blocks for the nth time with n blocks', and now you are performing subtask 'pick up the blue Lego block from the table, transfer the blue Lego block from the table to the building area, place the blue Lego block in the building area, press the blue Lego block in the building area.'\nThe trajectory starts at [218, 96]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[218, 96], [191, 86], [181, 76], [191, 75], [224, 104], [301, 131], [306, 144], [295, 139], [317, 131], [313, 142]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg2_task_0065_user_0007_scene_0010_cfg_0002_105422061350#948.jpg", + "gt": "[[218, 96], [191, 86], [181, 76], [191, 75], [224, 104], [301, 131], [306, 144], [295, 139], [317, 131], [313, 142]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0096_user_0014_scene_0001_cfg_0001_750612070851#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take something out of a drawer', and now you are performing subtask 'pull the drawer handle to the outside of the table, pick up the object from the drawer, transfer the object from the drawer to the top of the table, place the object on the table.'\nStart at [411, 156]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[411, 156], [449, 118], [466, 130], [458, 146], [470, 116], [448, 96], [400, 123], [364, 156], [342, 208], [373, 109]]}" + } + ], + "images": "RH20T_cfg1_task_0096_user_0014_scene_0001_cfg_0001_750612070851#158", + "gt": "[[411, 156], [449, 118], [466, 130], [458, 146], [470, 116], [448, 96], [400, 123], [364, 156], [342, 208], [373, 109]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "64534_exterior_image_2_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'wipe the plate with the yellow cloth and then put the fork on the plate', and now you are performing subtask 'place the fork on the plate.'\nBegin at [143, 54] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[143, 54], [149, 57], [148, 69], [141, 79], [137, 74], [131, 79], [145, 80], [136, 73], [131, 76], [132, 72]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/64534_exterior_image_2_left#361.jpg", + "gt": "[[143, 54], [149, 57], [148, 69], [141, 79], [137, 74], [131, 79], [145, 80], [136, 73], [131, 76], [132, 72]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0085_user_0015_scene_0002_cfg_0001_819112070044#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the bubble ring from the assembled bubble ring and ball', and now you are performing subtask 'remove the bubble ring from the assembled bubble ring and ball.'\nYour initial coordinate is [400, 168]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[400, 168], [340, 179], [340, 201], [349, 185], [391, 176], [398, 177], [390, 182], [394, 172], [413, 165], [413, 165]]}" + } + ], + "images": "RH20T_cfg1_task_0085_user_0015_scene_0002_cfg_0001_819112070044#0", + "gt": "[[400, 168], [340, 179], [340, 201], [349, 185], [391, 176], [398, 177], [390, 182], [394, 172], [413, 165], [413, 165]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "51700_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the towel on the rack', and now you are performing subtask 'put the towel on the rack.'\nFrom start point [168, 2], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[168, 2], [123, 26], [131, 19], [133, 59], [127, 0], [172, 0], [178, 14], [190, 17], [184, 28], [144, 32]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/51700_exterior_image_2_left#0.jpg", + "gt": "[[168, 2], [123, 26], [131, 19], [133, 59], [127, 0], [172, 0], [178, 14], [190, 17], [184, 28], [144, 32]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "82330_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the marker from the cup to the table', and now you are performing subtask 'move the marker from the cup to the table.'\nFrom start point [119.0, 25.5], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[119.0, 25.5], [198.0, 45.5], [215.0, 62.5], [214.0, 90.5], [225.0, 81.5], [224.0, 95.5], [218.0, 51.5], [193.0, 48.5], [175.0, 61.5], [178.0, 69.5]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/82330_exterior_image_1_left#0.jpg", + "gt": "[[119.0, 25.5], [198.0, 45.5], [215.0, 62.5], [214.0, 90.5], [225.0, 81.5], [224.0, 95.5], [218.0, 51.5], [193.0, 48.5], [175.0, 61.5], [178.0, 69.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "27910_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the orange cube on the green cube', and now you are performing subtask 'put the orange cube on the green cube.'\nYour initial coordinate is [22, 82]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[22, 82], [65, 87], [80, 95], [96, 117], [109, 108], [116, 108], [118, 110], [116, 119], [114, 119], [112, 116]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/27910_exterior_image_2_left#0.jpg", + "gt": "[[22, 82], [65, 87], [80, 95], [96, 117], [109, 108], [116, 108], [118, 110], [116, 119], [114, 119], [112, 116]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0026_user_0014_scene_0007_cfg_0006_104122061018#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'use the gripper to push and close the drawer', and now you are performing subtask 'use the gripper to push and close the drawer.'\nStart at [367, 28]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[367, 28], [348, 72], [354, 103], [390, 126], [406, 144], [466, 168], [440, 128], [432, 83], [423, 68], [427, 64]]}" + } + ], + "images": "RH20T_cfg6_task_0026_user_0014_scene_0007_cfg_0006_104122061018#0", + "gt": "[[367, 28], [348, 72], [354, 103], [390, 126], [406, 144], [466, 168], [440, 128], [432, 83], [423, 68], [427, 64]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "46919_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the door of the washing machine and push the tray back in', and now you are performing subtask 'push the tray back into the washing machine.'\nYour initial coordinate is [154, 142]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[154, 142], [168, 166], [186, 133], [181, 148], [185, 136], [177, 147], [151, 144], [140, 134], [143, 117], [138, 106]]}" + } + ], + "images": "46919_exterior_image_1_left#140", + "gt": "[[154, 142], [168, 166], [186, 133], [181, 148], [185, 136], [177, 147], [151, 144], [140, 134], [143, 117], [138, 106]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "37344_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the button to open the rice cooker', and now you are performing subtask 'press the button to open the rice cooker.'\nYour starting position is [204, 118]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[204, 118], [172, 131], [154, 120], [128, 115], [127, 106], [120, 106], [121, 122], [130, 81], [155, 75], [191, 78]]}" + } + ], + "images": "37344_exterior_image_2_left#0", + "gt": "[[204, 118], [172, 131], [154, 120], [128, 115], [127, 106], [120, 106], [121, 122], [130, 81], [155, 75], [191, 78]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "69546_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the cloth on the table', and now you are performing subtask 'put the cloth on the table.'\nWith start location [151, 73], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[151, 73], [165, 77], [166, 88], [183, 85], [191, 94], [204, 135], [201, 173], [205, 117], [202, 91], [202, 91]]}" + } + ], + "images": "69546_exterior_image_2_left#0", + "gt": "[[151, 73], [165, 77], [166, 88], [183, 85], [191, 94], [204, 135], [201, 173], [205, 117], [202, 91], [202, 91]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0073_user_0001_scene_0003_cfg_0001_039422060546#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the things in the drawer', and now you are performing subtask 'place the block in the drawer, push the drawer handle to close the drawer.'\nWith start location [214, 137], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[214, 137], [205, 102], [225, 81], [230, 62], [210, 66], [210, 91], [169, 151], [196, 115], [246, 86], [247, 91]]}" + } + ], + "images": "RH20T_cfg1_task_0073_user_0001_scene_0003_cfg_0001_039422060546#214", + "gt": "[[214, 137], [205, 102], [225, 81], [230, 62], [210, 66], [210, 91], [169, 151], [196, 115], [246, 86], [247, 91]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg2_task_0015_user_0006_scene_0003_cfg_0002_036422060215#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'play the drum', and now you are performing subtask 'play the drum.'\nStart at [350, 255]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[350, 255], [401, 249], [447, 272], [460, 261], [419, 309], [437, 326], [435, 336], [422, 344], [428, 335], [409, 317]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg2_task_0015_user_0006_scene_0003_cfg_0002_036422060215#0.jpg", + "gt": "[[350, 255], [401, 249], [447, 272], [460, 261], [419, 309], [437, 326], [435, 336], [422, 344], [428, 335], [409, 317]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "80108_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick the carrot and put it on the pan', and now you are performing subtask 'pick the carrot and put it on the pan.'\nFrom start point [276, 1], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[276, 1], [231, 30], [227, 64], [240, 29], [234, 6], [199, 44], [233, 32], [177, 59], [189, 72], [185, 57]]}" + } + ], + "images": "80108_exterior_image_2_left#0", + "gt": "[[276, 1], [231, 30], [227, 64], [240, 29], [234, 6], [199, 44], [233, 32], [177, 59], [189, 72], [185, 57]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0070_user_0014_scene_0008_cfg_0001_039422060546#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open a sliding window', and now you are performing subtask 'open a sliding window.'\nThe trajectory starts at [266, 122]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[266, 122], [310, 159], [322, 179], [325, 173], [336, 183], [336, 202], [328, 213], [322, 216], [325, 128], [297, 100]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0070_user_0014_scene_0008_cfg_0001_039422060546#0.jpg", + "gt": "[[266, 122], [310, 159], [322, 179], [325, 173], [336, 183], [336, 202], [328, 213], [322, 216], [325, 128], [297, 100]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "6777_exterior_image_2_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'the contents in the flask', and now you are performing subtask 'throw away the brush.'\nBegin at [94, 44] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[94, 44], [93, 30], [113, 65], [113, 103], [95, 30], [110, 56], [140, 76], [149, 116], [156, 117], [153, 95]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/6777_exterior_image_2_left#179.jpg", + "gt": "[[94, 44], [93, 30], [113, 65], [113, 103], [95, 30], [110, 56], [140, 76], [149, 116], [156, 117], [153, 95]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "7321_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the jar on the shelf', and now you are performing subtask 'put the jar on the shelf.'\nThe trajectory starts at [89, 91]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[89, 91], [107, 126], [119, 125], [97, 68], [110, 20], [132, 38], [112, 32], [102, 45], [102, 67], [113, 86]]}" + } + ], + "images": "7321_exterior_image_1_left#0", + "gt": "[[89, 91], [107, 126], [119, 125], [97, 68], [110, 20], [132, 38], [112, 32], [102, 45], [102, 67], [113, 86]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg2_task_0051_user_0016_scene_0003_cfg_0002_036422060215#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the dish off the dish rack', and now you are performing subtask 'take the dish off the dish rack.'\nThe trajectory starts at [294, 161]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[294, 161], [295, 171], [287, 173], [270, 162], [255, 171], [182, 150], [173, 166], [197, 136], [235, 141], [230, 145]]}" + } + ], + "images": "RH20T_cfg2_task_0051_user_0016_scene_0003_cfg_0002_036422060215#0", + "gt": "[[294, 161], [295, 171], [287, 173], [270, 162], [255, 171], [182, 150], [173, 166], [197, 136], [235, 141], [230, 145]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "16789_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close the side door', and now you are performing subtask 'close the side door.'\nYou start from [188, 60]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[188, 60], [227, 68], [239, 93], [231, 103], [223, 100], [271, 140], [262, 122], [236, 105], [300, 98], [276, 109]]}" + } + ], + "images": "16789_exterior_image_2_left#0", + "gt": "[[188, 60], [227, 68], [239, 93], [231, 103], [223, 100], [271, 140], [262, 122], [236, 105], [300, 98], [276, 109]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0081_user_0010_scene_0001_cfg_0001_039422060546#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the leg of the glasses (with one hand)', and now you are performing subtask 'pull the leg of the glasses outward.'\nThe trajectory starts at [265, 122]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[265, 122], [277, 115], [269, 130], [271, 143], [280, 133], [271, 137], [272, 146], [272, 127], [289, 104], [271, 104]]}" + } + ], + "images": "RH20T_cfg1_task_0081_user_0010_scene_0001_cfg_0001_039422060546#0", + "gt": "[[265, 122], [277, 115], [269, 130], [271, 143], [280, 133], [271, 137], [272, 146], [272, 127], [289, 104], [271, 104]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg3_task_0073_user_0010_scene_0010_cfg_0003_038522062288#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the things in the drawer', and now you are performing subtask 'place the small square in the drawer, push the drawer to close the drawer.'\nStarting at [221, 251], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[221, 251], [214, 239], [211, 227], [207, 190], [209, 187], [218, 195], [223, 210], [232, 218], [234, 229], [224, 210]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg3_task_0073_user_0010_scene_0010_cfg_0003_038522062288#201.jpg", + "gt": "[[221, 251], [214, 239], [211, 227], [207, 190], [209, 187], [218, 195], [223, 210], [232, 218], [234, 229], [224, 210]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0013_user_0020_scene_0010_cfg_0007_037522061512#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'place the block on the scale', and now you are performing subtask 'pick up the small block from the table, transfer the small block from the table to the big block, place the small block on the big block.'\nYour initial coordinate is [243, 106]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[243, 106], [264, 107], [272, 116], [272, 125], [250, 104], [241, 106], [230, 121], [245, 92], [260, 84], [266, 84]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg7_task_0013_user_0020_scene_0010_cfg_0007_037522061512#254.jpg", + "gt": "[[243, 106], [264, 107], [272, 116], [272, 125], [250, 104], [241, 106], [230, 121], [245, 92], [260, 84], [266, 84]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0003_user_0010_scene_0001_cfg_0005_036422060215#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press three buttons from left to right in sequence', and now you are performing subtask 'press the green button on the left.'\nYour starting position is [227, 143]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[227, 143], [204, 156], [202, 148], [197, 155], [198, 165], [202, 140], [228, 113], [257, 101], [303, 96], [303, 96]]}" + } + ], + "images": "RH20T_cfg5_task_0003_user_0010_scene_0001_cfg_0005_036422060215#345", + "gt": "[[227, 143], [204, 156], [202, 148], [197, 155], [198, 165], [202, 140], [228, 113], [257, 101], [303, 96], [303, 96]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0065_user_0014_scene_0003_cfg_0007_104122061330#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with small Lego blocks for the nth time with n blocks', and now you are performing subtask 'place the first Lego block on the Lego baseplate, pick up the second Lego block from the right side of the workbench, transfer the second Lego block from the right side of the workbench to the center Lego baseplate, place the second Lego block on the Lego baseplate.'\nThe trajectory starts at [352, 175]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[352, 175], [355, 169], [350, 166], [354, 171], [355, 165], [370, 184], [382, 228], [370, 176], [356, 153], [354, 162]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg7_task_0065_user_0014_scene_0003_cfg_0007_104122061330#246.jpg", + "gt": "[[352, 175], [355, 169], [350, 166], [354, 171], [355, 165], [370, 184], [382, 228], [370, 176], [356, 153], [354, 162]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "67484_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the faucet to the right, push the faucet handle upwards', and now you are performing subtask 'move the faucet to the right, push the faucet handle upwards.'\nWith start location [129.5, 85.5], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[129.5, 85.5], [153.5, 72.5], [229.5, 91.5], [264.5, 87.5], [211.5, 84.5], [211.5, 75.5], [228.5, 69.5], [230.5, 48.5], [194.5, 64.5], [194.5, 64.5]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/67484_exterior_image_1_left#0.jpg", + "gt": "[[129.5, 85.5], [153.5, 72.5], [229.5, 91.5], [264.5, 87.5], [211.5, 84.5], [211.5, 75.5], [228.5, 69.5], [230.5, 48.5], [194.5, 64.5], [194.5, 64.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "89114_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the plush toy in the bowl, wipe the counter with the blue towel, and move the faucet to the center', and now you are performing subtask 'twist the faucet counterclockwise.'\nBegin at [102, 95] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[102, 95], [112, 97], [138, 83], [140, 88], [136, 95], [150, 111], [128, 102], [109, 83], [117, 87], [116, 91]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/89114_exterior_image_1_left#269.jpg", + "gt": "[[102, 95], [112, 97], [138, 83], [140, 88], [136, 95], [150, 111], [128, 102], [109, 83], [117, 87], [116, 91]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0044_user_0014_scene_0005_cfg_0007_104122063633#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up a bag of things', and now you are performing subtask 'pick up a bag of things.'\nYour initial coordinate is [234, 121]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[234, 121], [218, 128], [205, 119], [213, 122], [213, 130], [212, 124], [219, 113], [235, 98], [238, 89], [236, 81]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg7_task_0044_user_0014_scene_0005_cfg_0007_104122063633#0.jpg", + "gt": "[[234, 121], [218, 128], [205, 119], [213, 122], [213, 130], [212, 124], [219, 113], [235, 98], [238, 89], [236, 81]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0066_user_0014_scene_0007_cfg_0007_104122061330#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with large Megabloks for the nth time with n blocks', and now you are performing subtask 'pick up the building blocks on the table, transfer the building blocks from the desktop to the pile of building blocks on the building board, place the building blocks on the pile of building blocks on the building board.'\nStart at [328, 185]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[328, 185], [385, 233], [318, 186], [321, 173], [293, 163], [285, 176], [271, 159], [269, 169], [275, 159], [289, 163]]}" + } + ], + "images": "RH20T_cfg7_task_0066_user_0014_scene_0007_cfg_0007_104122061330#325", + "gt": "[[328, 185], [385, 233], [318, 186], [321, 173], [293, 163], [285, 176], [271, 159], [269, 169], [275, 159], [289, 163]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0058_user_0014_scene_0001_cfg_0006_104122063633#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the switches on the power strip in sequence', and now you are performing subtask 'press the third button on the power strip, press the fourth button on the power strip.'\nWith start location [236, 188], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[236, 188], [238, 192], [238, 191], [237, 193], [236, 193], [242, 191], [243, 194], [247, 198], [249, 199], [253, 199]]}" + } + ], + "images": "RH20T_cfg6_task_0058_user_0014_scene_0001_cfg_0006_104122063633#208", + "gt": "[[236, 188], [238, 192], [238, 191], [237, 193], [236, 193], [242, 191], [243, 194], [247, 198], [249, 199], [253, 199]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0016_user_0014_scene_0003_cfg_0001_035622060973#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'hit the pool ball', and now you are performing subtask 'pick up the pool cue from the table, strike the pool ball on the table.'\nStarting at [246, 130], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[246, 130], [244, 163], [272, 185], [286, 228], [306, 226], [327, 238], [318, 234], [316, 249], [316, 240], [307, 237]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0016_user_0014_scene_0003_cfg_0001_035622060973#0.jpg", + "gt": "[[246, 130], [244, 163], [272, 185], [286, 228], [306, 226], [327, 238], [318, 234], [316, 249], [316, 240], [307, 237]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "218_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the blue and white towel in the open cabinet', and now you are performing subtask 'put the blue and white towel in the open cabinet.'\nYour initial coordinate is [229, 91]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[229, 91], [203, 95], [183, 155], [170, 109], [176, 79], [182, 68], [186, 75], [164, 79], [173, 90], [203, 94]]}" + } + ], + "images": "218_exterior_image_2_left#0", + "gt": "[[229, 91], [203, 95], [183, 155], [170, 109], [176, 79], [182, 68], [186, 75], [164, 79], [173, 90], [203, 94]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "69180_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the first drawer from the right, remove the glue stick from it and put the glue stick on the counter', and now you are performing subtask 'pull the handle of the first drawer on the right to open the drawer.'\nYour initial coordinate is [202, 37]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[202, 37], [174, 76], [172, 114], [151, 109], [176, 129], [170, 106], [165, 116], [166, 90], [170, 91], [165, 92]]}" + } + ], + "images": "69180_exterior_image_2_left#0", + "gt": "[[202, 37], [174, 76], [172, 114], [151, 109], [176, 129], [170, 106], [165, 116], [166, 90], [170, 91], [165, 92]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "45177_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the marker from the cup and put it on the counter', and now you are performing subtask 'remove the marker from the cup and put it on the counter.'\nWith start location [317, 78], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[317, 78], [281, 92], [273, 102], [277, 106], [245, 108], [269, 90], [245, 106], [228, 127], [225, 127], [226, 120]]}" + } + ], + "images": "45177_exterior_image_2_left#0", + "gt": "[[317, 78], [281, 92], [273, 102], [277, 106], [245, 108], [269, 90], [245, 106], [228, 127], [225, 127], [226, 120]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "65705_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the towel', and now you are performing subtask 'fold the towel on the counter.'\nStarting at [171, 110], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[171, 110], [166, 113], [164, 125], [152, 113], [155, 110], [181, 110], [194, 107], [226, 109], [202, 92], [192, 91]]}" + } + ], + "images": "65705_exterior_image_1_left#189", + "gt": "[[171, 110], [166, 113], [164, 125], [152, 113], [155, 110], [181, 110], [194, 107], [226, 109], [202, 92], [192, 91]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0008_user_0014_scene_0007_cfg_0006_104122061602#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'grab the block and place it at the designated location', and now you are performing subtask 'grab the block and place it at the designated location.'\nFrom start point [446, 106], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[446, 106], [471, 156], [475, 197], [438, 135], [410, 106], [387, 108], [385, 122], [393, 110], [386, 112], [386, 112]]}" + } + ], + "images": "RH20T_cfg6_task_0008_user_0014_scene_0007_cfg_0006_104122061602#0", + "gt": "[[446, 106], [471, 156], [475, 197], [438, 135], [410, 106], [387, 108], [385, 122], [393, 110], [386, 112], [386, 112]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg3_task_0018_user_0011_scene_0004_cfg_0003_038522062288#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'play jenga', and now you are performing subtask 'play jenga.'\nBegin at [238, 128] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[238, 128], [256, 133], [240, 116], [238, 92], [231, 187], [246, 190], [261, 210], [215, 178], [213, 191], [212, 177]]}" + } + ], + "images": "RH20T_cfg3_task_0018_user_0011_scene_0004_cfg_0003_038522062288#0", + "gt": "[[238, 128], [256, 133], [240, 116], [238, 92], [231, 187], [246, 190], [261, 210], [215, 178], [213, 191], [212, 177]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0061_user_0001_scene_0006_cfg_0001_038522062547#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take everything out of the gift box', and now you are performing subtask 'place the large block on the table, pick up the small block from the gift box, transfer the small block from the gift box to the table, place the small block on the table.'\nThe trajectory starts at [531, 193]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[531, 193], [433, 154], [407, 163], [384, 149], [421, 151], [411, 166], [441, 124], [451, 232], [467, 204], [460, 166]]}" + } + ], + "images": "RH20T_cfg1_task_0061_user_0001_scene_0006_cfg_0001_038522062547#198", + "gt": "[[531, 193], [433, 154], [407, 163], [384, 149], [421, 151], [411, 166], [441, 124], [451, 232], [467, 204], [460, 166]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg3_task_0005_user_0016_scene_0003_cfg_0003_104122063550#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'approach and touch the side of the small block', and now you are performing subtask 'approach and touch the side of the small block.'\nWith start location [279, 185], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[279, 185], [275, 177], [289, 167], [320, 164], [325, 170], [319, 164], [315, 174], [335, 172], [328, 208], [339, 224]]}" + } + ], + "images": "RH20T_cfg3_task_0005_user_0016_scene_0003_cfg_0003_104122063550#0", + "gt": "[[279, 185], [275, 177], [289, 167], [320, 164], [325, 170], [319, 164], [315, 174], [335, 172], [328, 208], [339, 224]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "47067_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pour the contents of the orange cup into the green bowl', and now you are performing subtask 'pour the contents of the orange cup into the green bowl.'\nYour initial coordinate is [214, 85]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[214, 85], [157, 99], [153, 105], [158, 114], [153, 117], [153, 108], [160, 100], [186, 111], [184, 106], [185, 110]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/47067_exterior_image_1_left#0.jpg", + "gt": "[[214, 85], [157, 99], [153, 105], [158, 114], [153, 117], [153, 108], [160, 100], [186, 111], [184, 106], [185, 110]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "83136_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'folding the towel', and now you are performing subtask 'fold the towel.'\nBegin at [106, 0] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[106, 0], [153, 10], [178, 29], [197, 76], [183, 102], [188, 129], [181, 136], [162, 94], [132, 82], [95, 91]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/83136_exterior_image_1_left#0.jpg", + "gt": "[[106, 0], [153, 10], [178, 29], [197, 76], [183, 102], [188, 129], [181, 136], [162, 94], [132, 82], [95, 91]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0075_user_0007_scene_0004_cfg_0005_036422060215#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'finish setting up the starting position of the chessboard that is almost arranged', and now you are performing subtask 'finish setting up the starting position of the chessboard that is almost arranged.'\nStarting at [286, 108], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[286, 108], [273, 141], [274, 218], [275, 189], [259, 185], [250, 142], [223, 115], [212, 125], [227, 136], [232, 82]]}" + } + ], + "images": "RH20T_cfg5_task_0075_user_0007_scene_0004_cfg_0005_036422060215#0", + "gt": "[[286, 108], [273, 141], [274, 218], [275, 189], [259, 185], [250, 142], [223, 115], [212, 125], [227, 136], [232, 82]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "19614_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the orange doll to the right, then put it back in the original position, and then move the green towel to the left', and now you are performing subtask 'slide the green cloth to the left.'\nYour starting position is [152, 58]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[152, 58], [162, 62], [161, 75], [145, 58], [121, 48], [112, 54], [113, 66], [113, 62], [99, 49], [100, 39]]}" + } + ], + "images": "19614_exterior_image_1_left#133", + "gt": "[[152, 58], [162, 62], [161, 75], [145, 58], [121, 48], [112, 54], [113, 66], [113, 62], [99, 49], [100, 39]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg3_task_0003_user_0016_scene_0002_cfg_0003_036422060909#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the three buttons in sequence', and now you are performing subtask 'press the green button in the middle, press the red button on the left.'\nYou begin at [345, 132]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[345, 132], [339, 121], [311, 140], [306, 156], [278, 161], [265, 177], [273, 165], [259, 144], [217, 146], [246, 131]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg3_task_0003_user_0016_scene_0002_cfg_0003_036422060909#194.jpg", + "gt": "[[345, 132], [339, 121], [311, 140], [306, 156], [278, 161], [265, 177], [273, 165], [259, 144], [217, 146], [246, 131]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0066_user_0014_scene_0005_cfg_0007_104122061018#TrajectoryPrediction_Task#8", + "task": "TrajectoryPrediction_Task", + "p_index": 8, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with large Megabloks for the nth time with n blocks', and now you are performing subtask 'place the block on the other blocks, pick up the block on the flat surface, transfer the block from the flat surface to the other blocks, place the block on the other blocks.'\nStart at [319, 82]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[319, 82], [328, 70], [331, 78], [297, 103], [248, 191], [319, 96], [337, 105], [334, 117], [323, 108], [336, 97]]}" + } + ], + "images": "RH20T_cfg7_task_0066_user_0014_scene_0005_cfg_0007_104122061018#570", + "gt": "[[319, 82], [328, 70], [331, 78], [297, 103], [248, 191], [319, 96], [337, 105], [334, 117], [323, 108], [336, 97]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "7985_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the towel', and now you are performing subtask 'fold the towel.'\nYour initial coordinate is [178, 87]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[178, 87], [175, 89], [175, 91], [171, 97], [170, 97], [170, 94], [174, 90], [190, 79], [190, 77], [186, 76]]}" + } + ], + "images": "7985_exterior_image_1_left#155", + "gt": "[[178, 87], [175, 89], [175, 91], [171, 97], [170, 97], [170, 94], [174, 90], [190, 79], [190, 77], [186, 76]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "69345_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the cloth from the clear screen and put it on the table', and now you are performing subtask 'take the cloth from the clear screen and put it on the table.'\nStart at [101, 40]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[101, 40], [118, 44], [145, 43], [142, 44], [147, 49], [148, 54], [144, 61], [123, 74], [120, 81], [122, 77]]}" + } + ], + "images": "69345_exterior_image_2_left#0", + "gt": "[[101, 40], [118, 44], [145, 43], [142, 44], [147, 49], [148, 54], [144, 61], [123, 74], [120, 81], [122, 77]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "14083_exterior_image_2_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'spoon out some contents from the bowl on the left using the silver spoon and place them in the bowl on the right', and now you are performing subtask 'place the spoon in the bowl on the right.'\nYour initial coordinate is [96, 86]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[96, 86], [95, 94], [86, 88], [99, 77], [96, 93], [100, 82], [99, 99], [111, 112], [94, 83], [102, 86]]}" + } + ], + "images": "14083_exterior_image_2_left#97", + "gt": "[[96, 86], [95, 94], [86, 88], [99, 77], [96, 93], [100, 82], [99, 99], [111, 112], [94, 83], [102, 86]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0091_user_0007_scene_0006_cfg_0004_104122062823#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move an object from one box to another', and now you are performing subtask 'move an object from one box to another.'\nStarting at [293, 0], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[293, 0], [375, 41], [382, 129], [375, 65], [333, 0], [317, 0], [277, 46], [368, 0], [405, 1], [441, 32]]}" + } + ], + "images": "RH20T_cfg4_task_0091_user_0007_scene_0006_cfg_0004_104122062823#0", + "gt": "[[293, 0], [375, 41], [382, 129], [375, 65], [333, 0], [317, 0], [277, 46], [368, 0], [405, 1], [441, 32]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "62246_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the marker in the bowl', and now you are performing subtask 'put the marker in the bowl.'\nStarting at [0.5, 23.0], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[0.5, 23.0], [52.5, 56.0], [70.5, 82.0], [97.5, 100.0], [118.5, 126.0], [122.5, 112.0], [137.5, 102.0], [161.5, 98.0], [165.5, 100.0], [165.5, 110.0]]}" + } + ], + "images": "62246_exterior_image_1_left#0", + "gt": "[[0.5, 23.0], [52.5, 56.0], [70.5, 82.0], [97.5, 100.0], [118.5, 126.0], [122.5, 112.0], [137.5, 102.0], [161.5, 98.0], [165.5, 100.0], [165.5, 110.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "30022_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the black lid from the small pot to the pan', and now you are performing subtask 'move the black lid from the small pot to the pan.'\nStart at [320, 57]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[320, 57], [174, 93], [171, 71], [181, 57], [215, 45], [246, 65], [250, 86], [241, 86], [230, 50], [235, 17]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/30022_exterior_image_1_left#0.jpg", + "gt": "[[320, 57], [174, 93], [171, 71], [181, 57], [215, 45], [246, 65], [250, 86], [241, 86], [230, 50], [235, 17]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "43647_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'wipe the table with the yellow towel', and now you are performing subtask 'wipe the table with the yellow towel.'\nStart at [104, 30]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[104, 30], [143, 55], [129, 83], [166, 79], [130, 95], [182, 91], [149, 79], [180, 102], [143, 83], [141, 44]]}" + } + ], + "images": "43647_exterior_image_2_left#0", + "gt": "[[104, 30], [143, 55], [129, 83], [166, 79], [130, 95], [182, 91], [149, 79], [180, 102], [143, 83], [141, 44]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "17981_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the orange cloth', and now you are performing subtask 'fold the cloth on the table once again.'\nYou start from [167, 80]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[167, 80], [155, 92], [159, 86], [159, 84], [158, 86], [157, 85], [160, 65], [164, 53], [168, 50], [173, 51]]}" + } + ], + "images": "17981_exterior_image_1_left#249", + "gt": "[[167, 80], [155, 92], [159, 86], [159, 84], [158, 86], [157, 85], [160, 65], [164, 53], [168, 50], [173, 51]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg3_task_0003_user_0016_scene_0001_cfg_0003_104122062295#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press three buttons from left to right in sequence', and now you are performing subtask 'press the red button on the left.'\nYou begin at [331, 200]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[331, 200], [350, 225], [356, 243], [336, 293], [351, 246], [342, 235], [323, 221], [315, 220], [313, 226], [313, 226]]}" + } + ], + "images": "RH20T_cfg3_task_0003_user_0016_scene_0001_cfg_0003_104122062295#235", + "gt": "[[331, 200], [350, 225], [356, 243], [336, 293], [351, 246], [342, 235], [323, 221], [315, 220], [313, 226], [313, 226]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "9303_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the cloth', and now you are performing subtask 'fold the cloth on the table.'\nStart at [317, 87]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[317, 87], [182, 76], [193, 77], [156, 117], [181, 108], [192, 93], [185, 87], [223, 113], [241, 143], [241, 143]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/9303_exterior_image_1_left#0.jpg", + "gt": "[[317, 87], [182, 76], [193, 77], [156, 117], [181, 108], [192, 93], [185, 87], [223, 113], [241, 143], [241, 143]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "19382_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn off the light and then turn it back on', and now you are performing subtask 'press the switch on the wall to turn off the light.'\nStarting at [145, 99], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[145, 99], [142, 95], [104, 74], [97, 72], [95, 73], [95, 76], [102, 81], [100, 82], [96, 80], [96, 80]]}" + } + ], + "images": "19382_exterior_image_1_left#0", + "gt": "[[145, 99], [142, 95], [104, 74], [97, 72], [95, 73], [95, 76], [102, 81], [100, 82], [96, 80], [96, 80]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0073_user_0007_scene_0001_cfg_0005_104122063678#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the things in the drawer', and now you are performing subtask 'grab the handle to pull the drawer open.'\nWith start location [331, 195], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[331, 195], [333, 198], [328, 204], [328, 206], [318, 189], [315, 181], [317, 177], [322, 174], [322, 175], [328, 169]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0073_user_0007_scene_0001_cfg_0005_104122063678#423.jpg", + "gt": "[[331, 195], [333, 198], [328, 204], [328, 206], [318, 189], [315, 181], [317, 177], [322, 174], [322, 175], [328, 169]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "30342_exterior_image_2_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the garlic on the counter into the glass bowl one by one', and now you are performing subtask 'place the third garlic into the glass bowl.'\nYour starting position is [156, 91]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[156, 91], [169, 99], [168, 115], [166, 103], [161, 97], [152, 96], [151, 101], [150, 95], [153, 91], [157, 92]]}" + } + ], + "images": "30342_exterior_image_2_left#236", + "gt": "[[156, 91], [169, 99], [168, 115], [166, 103], [161, 97], [152, 96], [151, 101], [150, 95], [153, 91], [157, 92]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "48680_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the pen from the table and place it in the blue cup', and now you are performing subtask 'take the pen from the table and place it in the blue cup.'\nYou start from [123, 19]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[123, 19], [131, 0], [150, 0], [165, 28], [171, 59], [166, 24], [187, 21], [187, 53], [186, 14], [186, 14]]}" + } + ], + "images": "48680_exterior_image_1_left#0", + "gt": "[[123, 19], [131, 0], [150, 0], [165, 28], [171, 59], [166, 24], [187, 21], [187, 53], [186, 14], [186, 14]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "58228_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the object on the wooden stand', and now you are performing subtask 'put the object on the wooden stand.'\nThe trajectory starts at [319.5, 90.0]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[319.5, 90.0], [279.5, 97.0], [261.5, 129.0], [240.5, 135.0], [232.5, 148.0], [236.5, 96.0], [244.5, 84.0], [220.5, 86.0], [228.5, 66.0], [224.5, 83.0]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/58228_exterior_image_1_left#0.jpg", + "gt": "[[319.5, 90.0], [279.5, 97.0], [261.5, 129.0], [240.5, 135.0], [232.5, 148.0], [236.5, 96.0], [244.5, 84.0], [220.5, 86.0], [228.5, 66.0], [224.5, 83.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "14672_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the red marker out of the yellow cup and put it on the table', and now you are performing subtask 'take the red marker out of the yellow cup and put it on the table.'\nYou start from [125, 2]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[125, 2], [117, 14], [137, 75], [135, 84], [136, 69], [146, 56], [144, 72], [161, 101], [162, 91], [152, 71]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/14672_exterior_image_2_left#0.jpg", + "gt": "[[125, 2], [117, 14], [137, 75], [135, 84], [136, 69], [146, 56], [144, 72], [161, 101], [162, 91], [152, 71]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "78664_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the red cup to the left side of the pot lid', and now you are performing subtask 'move the red cup to the left side of the pot lid.'\nWith start location [122.0, 47.0], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[122.0, 47.0], [135.0, 54.0], [111.0, 92.0], [133.0, 101.0], [142.0, 119.0], [139.0, 40.0], [102.0, 42.0], [113.0, 42.0], [103.0, 72.0], [100.0, 56.0]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/78664_exterior_image_1_left#0.jpg", + "gt": "[[122.0, 47.0], [135.0, 54.0], [111.0, 92.0], [133.0, 101.0], [142.0, 119.0], [139.0, 40.0], [102.0, 42.0], [113.0, 42.0], [103.0, 72.0], [100.0, 56.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0061_user_0020_scene_0003_cfg_0007_037522061512#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take everything out of the gift box', and now you are performing subtask 'place the lid on the table, pick up the object in the container, transfer the object from the container to the surface, place the object on the surface.'\nYour starting position is [195, 157]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[195, 157], [198, 155], [198, 168], [190, 140], [196, 126], [229, 97], [239, 102], [238, 123], [234, 101], [231, 110]]}" + } + ], + "images": "RH20T_cfg7_task_0061_user_0020_scene_0003_cfg_0007_037522061512#286", + "gt": "[[195, 157], [198, 155], [198, 168], [190, 140], [196, 126], [229, 97], [239, 102], [238, 123], [234, 101], [231, 110]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "33838_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the lid off of the pot', and now you are performing subtask 'take the lid off of the pot.'\nStarting at [4, 14], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[4, 14], [94, 60], [121, 78], [142, 103], [132, 93], [105, 84], [100, 84], [111, 92], [117, 100], [100, 99]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/33838_exterior_image_1_left#0.jpg", + "gt": "[[4, 14], [94, 60], [121, 78], [142, 103], [132, 93], [105, 84], [100, 84], [111, 92], [117, 100], [100, 99]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "3767_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the marker in the mug', and now you are performing subtask 'put the marker in the mug.'\nThe trajectory starts at [93.5, 71.0]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[93.5, 71.0], [169.5, 77.0], [198.5, 100.0], [213.5, 126.0], [209.5, 140.0], [192.5, 119.0], [149.5, 94.0], [156.5, 116.0], [166.5, 108.0], [174.5, 112.0]]}" + } + ], + "images": "3767_exterior_image_1_left#0", + "gt": "[[93.5, 71.0], [169.5, 77.0], [198.5, 100.0], [213.5, 126.0], [209.5, 140.0], [192.5, 119.0], [149.5, 94.0], [156.5, 116.0], [166.5, 108.0], [174.5, 112.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "4309_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pull out a tissue square from the pink box', and now you are performing subtask 'pull out a tissue square from the pink box.'\nThe trajectory starts at [156.5, 95.5]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[156.5, 95.5], [168.5, 120.5], [194.5, 141.5], [187.5, 150.5], [194.5, 161.5], [185.5, 137.5], [186.5, 117.5], [220.5, 113.5], [223.5, 125.5], [208.5, 133.5]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/4309_exterior_image_1_left#0.jpg", + "gt": "[[156.5, 95.5], [168.5, 120.5], [194.5, 141.5], [187.5, 150.5], [194.5, 161.5], [185.5, 137.5], [186.5, 117.5], [220.5, 113.5], [223.5, 125.5], [208.5, 133.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "15679_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the orange plush toy on the counter then close the drawer', and now you are performing subtask 'put the orange plush toy on the countertop.'\nYour starting position is [143, 22]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[143, 22], [184, 16], [173, 19], [180, 26], [168, 68], [190, 95], [185, 129], [185, 98], [208, 80], [208, 80]]}" + } + ], + "images": "15679_exterior_image_2_left#0", + "gt": "[[143, 22], [184, 16], [173, 19], [180, 26], [168, 68], [190, 95], [185, 129], [185, 98], [208, 80], [208, 80]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0073_user_0001_scene_0003_cfg_0001_038522063145#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the things in the drawer', and now you are performing subtask 'pick up the block on the drawer, transfer the block from above the drawer to inside the drawer, place the block in the drawer, push the drawer handle to close the drawer.'\nBegin at [444, 99] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[444, 99], [452, 78], [469, 68], [522, 97], [510, 117], [506, 105], [459, 81], [443, 123], [443, 92], [408, 74]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0073_user_0001_scene_0003_cfg_0001_038522063145#0.jpg", + "gt": "[[444, 99], [452, 78], [469, 68], [522, 97], [510, 117], [506, 105], [459, 81], [443, 123], [443, 92], [408, 74]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "90712_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the soda can from the cabinet to the countertop', and now you are performing subtask 'move the soda can from the cabinet to the countertop.'\nWith start location [110, 94], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[110, 94], [106, 30], [113, 27], [117, 33], [114, 23], [113, 71], [131, 128], [130, 132], [124, 123], [118, 98]]}" + } + ], + "images": "90712_exterior_image_1_left#0", + "gt": "[[110, 94], [106, 30], [113, 27], [117, 33], [114, 23], [113, 71], [131, 128], [130, 132], [124, 123], [118, 98]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "24904_exterior_image_2_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close the lid on the clear container', and now you are performing subtask 'place the lid on the clear container.'\nThe trajectory starts at [171, 95]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[171, 95], [190, 119], [188, 118], [186, 122], [188, 126], [179, 125], [175, 122], [180, 114], [183, 100], [183, 100]]}" + } + ], + "images": "24904_exterior_image_2_left#154", + "gt": "[[171, 95], [190, 119], [188, 118], [186, 122], [188, 126], [179, 125], [175, 122], [180, 114], [183, 100], [183, 100]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "47158_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'use the white cloth to wipe the pan', and now you are performing subtask 'use the white cloth to wipe the pan.'\nWith start location [144, 14], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[144, 14], [145, 89], [135, 68], [137, 100], [125, 115], [120, 106], [137, 62], [143, 83], [140, 66], [157, 61]]}" + } + ], + "images": "47158_exterior_image_2_left#0", + "gt": "[[144, 14], [145, 89], [135, 68], [137, 100], [125, 115], [120, 106], [137, 62], [143, 83], [140, 66], [157, 61]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "66631_exterior_image_2_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'use the towel to wipe the table', and now you are performing subtask 'fold the towel.'\nThe trajectory starts at [196, 98]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[196, 98], [201, 98], [203, 101], [197, 94], [189, 94], [182, 102], [180, 109], [186, 107], [188, 104], [189, 94]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/66631_exterior_image_2_left#236.jpg", + "gt": "[[196, 98], [201, 98], [203, 101], [197, 94], [189, 94], [182, 102], [180, 109], [186, 107], [188, 104], [189, 94]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "1629_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'switch off the third switch from the right', and now you are performing subtask 'switch off the third switch from the right.'\nYour initial coordinate is [179, 1]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[179, 1], [181, 10], [175, 12], [184, 42], [183, 88], [184, 97], [187, 98], [184, 110], [188, 99], [190, 70]]}" + } + ], + "images": "1629_exterior_image_2_left#0", + "gt": "[[179, 1], [181, 10], [175, 12], [184, 42], [183, 88], [184, 97], [187, 98], [184, 110], [188, 99], [190, 70]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "19614_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the orange doll to the right, then put it back in the original position, and then move the green towel to the left', and now you are performing subtask 'slide the green cloth to the left.'\nThe trajectory starts at [100, 39]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[100, 39], [117, 26], [146, 33], [159, 51], [170, 88], [165, 106], [172, 97], [168, 83], [156, 77], [160, 73]]}" + } + ], + "images": "19614_exterior_image_1_left#247", + "gt": "[[100, 39], [117, 26], [146, 33], [159, 51], [170, 88], [165, 106], [172, 97], [168, 83], [156, 77], [160, 73]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "78332_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the door of the second washing machine', and now you are performing subtask 'open the door of the second washing machine.'\nWith start location [230, 60], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[230, 60], [207, 89], [182, 143], [182, 156], [194, 166], [215, 175], [230, 174], [221, 137], [223, 90], [218, 72]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/78332_exterior_image_2_left#0.jpg", + "gt": "[[230, 60], [207, 89], [182, 143], [182, 156], [194, 166], [215, 175], [230, 174], [221, 137], [223, 90], [218, 72]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "66357_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the spoon out of the bowl and put it into the cup, then slightly move the two cups to the left side of the bowl', and now you are performing subtask 'place the cup on the left side of the bowl.'\nFrom start point [181, 147], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[181, 147], [192, 158], [188, 166], [180, 149], [166, 145], [156, 147], [170, 149], [155, 158], [157, 142], [171, 146]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/66357_exterior_image_1_left#484.jpg", + "gt": "[[181, 147], [192, 158], [188, 166], [180, 149], [166, 145], [156, 147], [170, 149], [155, 158], [157, 142], [171, 146]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0039_user_0014_scene_0002_cfg_0006_104122063633#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pour the water from one cup into another empty cup', and now you are performing subtask 'pour the water from one cup into another empty cup.'\nYou start from [233, 118]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[233, 118], [230, 148], [230, 124], [216, 117], [208, 200], [202, 115], [208, 103], [215, 176], [218, 148], [217, 185]]}" + } + ], + "images": "RH20T_cfg6_task_0039_user_0014_scene_0002_cfg_0006_104122063633#0", + "gt": "[[233, 118], [230, 148], [230, 124], [216, 117], [208, 200], [202, 115], [208, 103], [215, 176], [218, 148], [217, 185]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "44059_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'place the blue and white plush toy on the right side of the table', and now you are performing subtask 'place the blue and white plush toy on the right side of the table.'\nYou start from [308, 7]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[308, 7], [254, 67], [196, 96], [178, 117], [171, 115], [194, 98], [204, 101], [216, 114], [198, 95], [196, 81]]}" + } + ], + "images": "44059_exterior_image_2_left#0", + "gt": "[[308, 7], [254, 67], [196, 96], [178, 117], [171, 115], [194, 98], [204, 101], [216, 114], [198, 95], [196, 81]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "52926_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the two pillows and move them to the right side of the couch', and now you are performing subtask 'pick up the second pillow on the sofa.'\nFrom start point [204, 68], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[204, 68], [180, 87], [167, 114], [172, 124], [168, 128], [174, 116], [197, 108], [186, 114], [162, 105], [153, 121]]}" + } + ], + "images": "52926_exterior_image_1_left#0", + "gt": "[[204, 68], [180, 87], [167, 114], [172, 124], [168, 128], [174, 116], [197, 108], [186, 114], [162, 105], [153, 121]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0015_user_0014_scene_0008_cfg_0007_104122061018#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'play the drum', and now you are performing subtask 'play the drum.'\nThe trajectory starts at [363, 31]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[363, 31], [313, 40], [264, 64], [253, 82], [251, 105], [276, 75], [323, 130], [293, 103], [300, 132], [331, 51]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg7_task_0015_user_0014_scene_0008_cfg_0007_104122061018#0.jpg", + "gt": "[[363, 31], [313, 40], [264, 64], [253, 82], [251, 105], [276, 75], [323, 130], [293, 103], [300, 132], [331, 51]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "6005_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'lay the charger across the table', and now you are performing subtask 'place the power cable below the table.'\nBegin at [181, 74] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[181, 74], [182, 79], [174, 80], [171, 76], [133, 88], [104, 108], [90, 109], [85, 114], [87, 90], [95, 81]]}" + } + ], + "images": "6005_exterior_image_1_left#381", + "gt": "[[181, 74], [182, 79], [174, 80], [171, 76], [133, 88], [104, 108], [90, 109], [85, 114], [87, 90], [95, 81]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0057_user_0007_scene_0003_cfg_0005_036422060215#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn on the power strips', and now you are performing subtask 'press the third button on the power socket, press the fourth button on the power socket.'\nYou start from [264, 180]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[264, 180], [285, 193], [286, 196], [280, 195], [281, 197], [283, 192], [285, 194], [292, 192], [292, 190], [292, 190]]}" + } + ], + "images": "RH20T_cfg5_task_0057_user_0007_scene_0003_cfg_0005_036422060215#473", + "gt": "[[264, 180], [285, 193], [286, 196], [280, 195], [281, 197], [283, 192], [285, 194], [292, 192], [292, 190], [292, 190]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "50349_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the glass lid on the black pot', and now you are performing subtask 'put the glass lid on the black pot.'\nFrom start point [82.5, 1.5], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[82.5, 1.5], [113.5, 63.5], [127.5, 83.5], [128.5, 95.5], [134.5, 99.5], [126.5, 86.5], [134.5, 79.5], [154.5, 87.5], [161.5, 101.5], [154.5, 86.5]]}" + } + ], + "images": "50349_exterior_image_1_left#0", + "gt": "[[82.5, 1.5], [113.5, 63.5], [127.5, 83.5], [128.5, 95.5], [134.5, 99.5], [126.5, 86.5], [134.5, 79.5], [154.5, 87.5], [161.5, 101.5], [154.5, 86.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0065_user_0014_scene_0002_cfg_0001_750612070853#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with small Lego blocks for the nth time with n blocks', and now you are performing subtask 'place the pink block in the building area, pick up the light green block on the desktop, transfer the light green block from the desktop to the building area, place the light green block on the pink block.'\nWith start location [334, 166], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[334, 166], [334, 160], [326, 161], [283, 173], [279, 182], [304, 156], [336, 161], [290, 181], [317, 159], [320, 166]]}" + } + ], + "images": "RH20T_cfg1_task_0065_user_0014_scene_0002_cfg_0001_750612070853#312", + "gt": "[[334, 166], [334, 160], [326, 161], [283, 173], [279, 182], [304, 156], [336, 161], [290, 181], [317, 159], [320, 166]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "6997_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the peach plush toy in the box and remove the green plush from the box and put it on the tray', and now you are performing subtask 'place peach plush toy in box.'\nStarting at [138, 100], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[138, 100], [151, 124], [148, 129], [152, 144], [144, 152], [143, 143], [153, 124], [165, 115], [172, 116], [169, 124]]}" + } + ], + "images": "6997_exterior_image_2_left#0", + "gt": "[[138, 100], [151, 124], [148, 129], [152, 144], [144, 152], [143, 143], [153, 124], [165, 115], [172, 116], [169, 124]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0057_user_0007_scene_0003_cfg_0005_104122063678#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn on the power strips', and now you are performing subtask 'press the first button on the power socket, press the second button on the power socket.'\nBegin at [323, 132] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[323, 132], [317, 119], [312, 117], [307, 124], [322, 166], [320, 176], [303, 179], [303, 191], [296, 184], [297, 201]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0057_user_0007_scene_0003_cfg_0005_104122063678#0.jpg", + "gt": "[[323, 132], [317, 119], [312, 117], [307, 124], [322, 166], [320, 176], [303, 179], [303, 191], [296, 184], [297, 201]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "79681_exterior_image_1_left#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the towel and lay it flat on the countertop', and now you are performing subtask 'slide the towel to the left.'\nFrom start point [201, 90], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[201, 90], [193, 94], [187, 118], [163, 139], [186, 160], [169, 141], [201, 114], [206, 88], [217, 83], [211, 77]]}" + } + ], + "images": "79681_exterior_image_1_left#360", + "gt": "[[201, 90], [193, 94], [187, 118], [163, 139], [186, 160], [169, 141], [201, 114], [206, 88], [217, 83], [211, 77]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0003_user_0015_scene_0008_cfg_0001_039422060546#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the three buttons from left to right in sequence', and now you are performing subtask 'press the green button on the right, press the orange button on the left, press the yellow button in the middle.'\nYou start from [277, 143]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[277, 143], [305, 101], [268, 108], [272, 118], [275, 106], [258, 81], [278, 84], [275, 69], [301, 33], [303, 47]]}" + } + ], + "images": "RH20T_cfg1_task_0003_user_0015_scene_0008_cfg_0001_039422060546#97", + "gt": "[[277, 143], [305, 101], [268, 108], [272, 118], [275, 106], [258, 81], [278, 84], [275, 69], [301, 33], [303, 47]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "26514_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'fold the towel in half then fold it in half again', and now you are performing subtask 'fold the towel in half and place it on the table.'\nYou begin at [156, 38]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[156, 38], [159, 65], [153, 59], [189, 71], [197, 91], [168, 128], [162, 174], [235, 118], [198, 88], [166, 84]]}" + } + ], + "images": "26514_exterior_image_1_left#0", + "gt": "[[156, 38], [159, 65], [153, 59], [189, 71], [197, 91], [168, 128], [162, 174], [235, 118], [198, 88], [166, 84]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "68771_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the marker from the cup and put it on the left side of the table', and now you are performing subtask 'remove the marker from the cup and put it on the left side of the table.'\nYour initial coordinate is [80, 0]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[80, 0], [182, 22], [179, 39], [152, 67], [153, 87], [170, 83], [173, 67], [159, 70], [169, 35], [121, 40]]}" + } + ], + "images": "68771_exterior_image_2_left#0", + "gt": "[[80, 0], [182, 22], [179, 39], [152, 67], [153, 87], [170, 83], [173, 67], [159, 70], [169, 35], [121, 40]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "48910_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'fold the towel twice', and now you are performing subtask 'fold the towel in half.'\nThe trajectory starts at [93, 3]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[93, 3], [144, 4], [180, 35], [191, 110], [177, 132], [185, 107], [133, 112], [161, 84], [132, 93], [132, 93]]}" + } + ], + "images": "48910_exterior_image_1_left#0", + "gt": "[[93, 3], [144, 4], [180, 35], [191, 110], [177, 132], [185, 107], [133, 112], [161, 84], [132, 93], [132, 93]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "90957_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the green pen out of the white bowl', and now you are performing subtask 'take the green pen out of the white bowl.'\nStart at [64.5, 5.5]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[64.5, 5.5], [109.5, 33.5], [123.5, 51.5], [122.5, 63.5], [132.5, 63.5], [155.5, 85.5], [151.5, 75.5], [110.5, 66.5], [115.5, 83.5], [130.5, 89.5]]}" + } + ], + "images": "90957_exterior_image_1_left#0", + "gt": "[[64.5, 5.5], [109.5, 33.5], [123.5, 51.5], [122.5, 63.5], [132.5, 63.5], [155.5, 85.5], [151.5, 75.5], [110.5, 66.5], [115.5, 83.5], [130.5, 89.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0033_user_0015_scene_0008_cfg_0001_035622060973#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the block', and now you are performing subtask 'push the square in front of the cardboard to the adjacent square in the middle of the cardboard, pick up the square on the cardboard, transfer the square from the cardboard to the right side of the middle square on the cardboard.'\nThe trajectory starts at [246, 130]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[246, 130], [0, 360], [209, 156], [187, 183], [205, 210], [243, 190], [236, 181], [247, 187], [236, 170], [244, 161]]}" + } + ], + "images": "RH20T_cfg1_task_0033_user_0015_scene_0008_cfg_0001_035622060973#0", + "gt": "[[246, 130], [0, 360], [209, 156], [187, 183], [205, 210], [243, 190], [236, 181], [247, 187], [236, 170], [244, 161]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0057_user_0007_scene_0002_cfg_0005_036422060215#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press a row of four power strip buttons to turn on the power strips', and now you are performing subtask 'press the third button on the power socket, press the fourth button on the power socket.'\nBegin at [289, 182] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[289, 182], [298, 178], [300, 184], [298, 185], [300, 184], [300, 179], [295, 166], [301, 161], [309, 149], [316, 147]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0057_user_0007_scene_0002_cfg_0005_036422060215#594.jpg", + "gt": "[[289, 182], [298, 178], [300, 184], [298, 185], [300, 184], [300, 179], [295, 166], [301, 161], [309, 149], [316, 147]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "75130_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the towel from the table and put it on the tripod', and now you are performing subtask 'pick up the towel from the table and put it on the tripod.'\nYou begin at [200, 0]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[200, 0], [165, 50], [166, 78], [160, 79], [120, 22], [99, 47], [98, 64], [104, 74], [93, 64], [99, 65]]}" + } + ], + "images": "75130_exterior_image_1_left#0", + "gt": "[[200, 0], [165, 50], [166, 78], [160, 79], [120, 22], [99, 47], [98, 64], [104, 74], [93, 64], [99, 65]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0032_user_0016_scene_0002_cfg_0004_104422070011#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'slide the outer casing onto the gift box', and now you are performing subtask 'slide the outer casing onto the gift box.'\nYou begin at [334, 103]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[334, 103], [355, 128], [365, 106], [394, 102], [375, 160], [350, 155], [363, 180], [376, 159], [370, 195], [376, 139]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg4_task_0032_user_0016_scene_0002_cfg_0004_104422070011#0.jpg", + "gt": "[[334, 103], [355, 128], [365, 106], [394, 102], [375, 160], [350, 155], [363, 180], [376, 159], [370, 195], [376, 139]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "74682_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the marker from the cup and place it on the table', and now you are performing subtask 'remove the marker from the cup and place it on the table.'\nYou begin at [190, 111]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[190, 111], [181, 117], [182, 120], [179, 122], [152, 130], [151, 138], [155, 113], [154, 118], [147, 111], [143, 113]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/74682_exterior_image_2_left#0.jpg", + "gt": "[[190, 111], [181, 117], [182, 120], [179, 122], [152, 130], [151, 138], [155, 113], [154, 118], [147, 111], [143, 113]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "21098_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pour the contents in the cup into the bowl', and now you are performing subtask 'pour the contents in the cup into the bowl.'\nYou start from [140, 103]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[140, 103], [142, 102], [140, 103], [140, 107], [143, 111], [142, 106], [147, 97], [154, 97], [155, 100], [162, 98]]}" + } + ], + "images": "21098_exterior_image_2_left#0", + "gt": "[[140, 103], [142, 102], [140, 103], [140, 107], [143, 111], [142, 106], [147, 97], [154, 97], [155, 100], [162, 98]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "76191_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the bottle cap', and now you are performing subtask 'press the bottle cap.'\nStart at [110, 50]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[110, 50], [117, 46], [124, 27], [146, 27], [162, 36], [156, 56], [171, 72], [167, 94], [164, 64], [164, 64]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/76191_exterior_image_1_left#0.jpg", + "gt": "[[110, 50], [117, 46], [124, 27], [146, 27], [162, 36], [156, 56], [171, 72], [167, 94], [164, 64], [164, 64]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "40415_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the banana from the pot', and now you are performing subtask 'remove the banana from the pot.'\nBegin at [246, 3] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[246, 3], [167, 70], [155, 87], [149, 106], [145, 109], [140, 105], [133, 115], [137, 124], [135, 115], [131, 115]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/40415_exterior_image_2_left#0.jpg", + "gt": "[[246, 3], [167, 70], [155, 87], [149, 106], [145, 109], [140, 105], [133, 115], [137, 124], [135, 115], [131, 115]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0037_user_0014_scene_0010_cfg_0001_038522062547#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'pick up a block from the table, transfer a block from the table to the top of a block, place the block on another block.'\nYou begin at [406, 134]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[406, 134], [418, 118], [420, 128], [414, 130], [424, 117], [447, 100], [461, 99], [468, 102], [465, 114], [461, 115]]}" + } + ], + "images": "RH20T_cfg1_task_0037_user_0014_scene_0010_cfg_0001_038522062547#0", + "gt": "[[406, 134], [418, 118], [420, 128], [414, 130], [424, 117], [447, 100], [461, 99], [468, 102], [465, 114], [461, 115]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg3_task_0043_user_0010_scene_0006_cfg_0003_104122062823#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unscrew the lid from the cup', and now you are performing subtask 'twist the lid counterclockwise to unscrew it from the cup.'\nYour initial coordinate is [282, 49]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[282, 49], [289, 58], [281, 61], [287, 64], [273, 62], [276, 54], [289, 50], [291, 58], [286, 65], [286, 65]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg3_task_0043_user_0010_scene_0006_cfg_0003_104122062823#238.jpg", + "gt": "[[282, 49], [289, 58], [281, 61], [287, 64], [273, 62], [276, 54], [289, 50], [291, 58], [286, 65], [286, 65]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "76032_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the plastic broccoli from the bowl and put it on the table', and now you are performing subtask 'take the plastic broccoli from the bowl and put it on the table.'\nStarting at [185, 2], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[185, 2], [187, 37], [179, 89], [193, 120], [190, 124], [190, 93], [181, 81], [172, 85], [190, 104], [194, 84]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/76032_exterior_image_1_left#0.jpg", + "gt": "[[185, 2], [187, 37], [179, 89], [193, 120], [190, 124], [190, 93], [181, 81], [172, 85], [190, 104], [194, 84]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0046_user_0020_scene_0010_cfg_0006_104122061018#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the cup on the cup rack', and now you are performing subtask 'put the cup on the cup rack.'\nYou start from [361, 31]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[361, 31], [304, 72], [275, 69], [265, 110], [271, 90], [296, 108], [318, 93], [345, 110], [328, 75], [343, 76]]}" + } + ], + "images": "RH20T_cfg6_task_0046_user_0020_scene_0010_cfg_0006_104122061018#0", + "gt": "[[361, 31], [304, 72], [275, 69], [265, 110], [271, 90], [296, 108], [318, 93], [345, 110], [328, 75], [343, 76]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0094_user_0007_scene_0009_cfg_0004_104122062823#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open a box', and now you are performing subtask 'push the box to open the box, push the box to open the box.'\nYou start from [282, 13]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[282, 13], [290, 28], [307, 9], [338, 12], [349, 26], [352, 49], [345, 18], [313, 7], [288, 17], [271, 51]]}" + } + ], + "images": "RH20T_cfg4_task_0094_user_0007_scene_0009_cfg_0004_104122062823#150", + "gt": "[[282, 13], [290, 28], [307, 9], [338, 12], [349, 26], [352, 49], [345, 18], [313, 7], [288, 17], [271, 51]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0037_user_0007_scene_0008_cfg_0005_037522062165#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'pick up the block on the plane, transfer the block from the plane to the other blocks, place the block on the other blocks.'\nWith start location [207, 233], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[207, 233], [184, 244], [178, 287], [186, 272], [246, 233], [264, 212], [271, 185], [300, 170], [329, 179], [359, 222]]}" + } + ], + "images": "RH20T_cfg5_task_0037_user_0007_scene_0008_cfg_0005_037522062165#677", + "gt": "[[207, 233], [184, 244], [178, 287], [186, 272], [246, 233], [264, 212], [271, 185], [300, 170], [329, 179], [359, 222]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "54044_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up and put down the green block, then put the salt cellar into the pot and the green block into the sink', and now you are performing subtask 'place the green block in the sink.'\nYour starting position is [217, 80]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[217, 80], [200, 94], [208, 101], [199, 105], [208, 100], [201, 94], [210, 98], [204, 105], [175, 113], [231, 89]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/54044_exterior_image_1_left#531.jpg", + "gt": "[[217, 80], [200, 94], [208, 101], [199, 105], [208, 100], [201, 94], [210, 98], [204, 105], [175, 113], [231, 89]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0037_user_0007_scene_0010_cfg_0005_104122061850#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'place the fourth block on top of the third block, pick up the fifth block on the table, transfer the fifth block from the table to the position of the fourth block, place the fifth block on top of the fourth block.'\nYour initial coordinate is [303, 132]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[303, 132], [286, 96], [288, 85], [304, 89], [327, 113], [326, 125], [305, 98], [266, 69], [301, 109], [273, 95]]}" + } + ], + "images": "RH20T_cfg5_task_0037_user_0007_scene_0010_cfg_0005_104122061850#791", + "gt": "[[303, 132], [286, 96], [288, 85], [304, 89], [327, 113], [326, 125], [305, 98], [266, 69], [301, 109], [273, 95]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0094_user_0007_scene_0003_cfg_0004_104122062295#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the box', and now you are performing subtask 'push the lid of the box.'\nStart at [280, 50]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[280, 50], [272, 48], [285, 62], [275, 59], [295, 65], [293, 84], [281, 92], [235, 63], [214, 72], [220, 65]]}" + } + ], + "images": "RH20T_cfg4_task_0094_user_0007_scene_0003_cfg_0004_104122062295#0", + "gt": "[[280, 50], [272, 48], [285, 62], [275, 59], [295, 65], [293, 84], [281, 92], [235, 63], [214, 72], [220, 65]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "4134_exterior_image_2_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'insert the small object into the green building block', and now you are performing subtask 'press the blue block onto the green block.'\nStarting at [128, 88], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[128, 88], [129, 103], [124, 84], [126, 101], [116, 90], [111, 105], [119, 109], [113, 83], [117, 105], [124, 80]]}" + } + ], + "images": "4134_exterior_image_2_left#248", + "gt": "[[128, 88], [129, 103], [124, 84], [126, 101], [116, 90], [111, 105], [119, 109], [113, 83], [117, 105], [124, 80]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0013_user_0020_scene_0004_cfg_0007_104122064161#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'place the block on the scale', and now you are performing subtask 'place the block on the scale.'\nFrom start point [337, 115], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[337, 115], [357, 133], [352, 124], [359, 124], [372, 147], [361, 188], [366, 235], [365, 175], [337, 149], [337, 149]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg7_task_0013_user_0020_scene_0004_cfg_0007_104122064161#0.jpg", + "gt": "[[337, 115], [357, 133], [352, 124], [359, 124], [372, 147], [361, 188], [366, 235], [365, 175], [337, 149], [337, 149]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "40658_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the green cloth', and now you are performing subtask 'unfold the green cloth.'\nBegin at [157, 1] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[157, 1], [177, 67], [171, 63], [175, 73], [170, 92], [148, 68], [153, 52], [168, 62], [161, 72], [153, 66]]}" + } + ], + "images": "40658_exterior_image_1_left#0", + "gt": "[[157, 1], [177, 67], [171, 63], [175, 73], [170, 92], [148, 68], [153, 52], [168, 62], [161, 72], [153, 66]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0127_user_0020_scene_0006_cfg_0006_104122061330#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'plug in the power cord of the desk lamp, turn on the socket, and light up the desk lamp', and now you are performing subtask 'pick up the power cable on the table, transfer the power cable from the table to the socket on the desktop, insert the power cable into the socket on the desktop.'\nYour initial coordinate is [266, 97]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[266, 97], [321, 79], [416, 98], [422, 132], [415, 148], [417, 129], [390, 121], [361, 124], [351, 143], [351, 143]]}" + } + ], + "images": "RH20T_cfg6_task_0127_user_0020_scene_0006_cfg_0006_104122061330#0", + "gt": "[[266, 97], [321, 79], [416, 98], [422, 132], [415, 148], [417, 129], [390, 121], [361, 124], [351, 143], [351, 143]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0061_user_0007_scene_0010_cfg_0005_104122063678#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take everything out of the gift box', and now you are performing subtask 'pick up the object in the container, transfer the object from the container to the table, place the object on the table.'\nYour initial coordinate is [323, 132]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[323, 132], [333, 141], [334, 179], [319, 202], [324, 172], [312, 149], [301, 141], [291, 164], [300, 140], [300, 140]]}" + } + ], + "images": "RH20T_cfg5_task_0061_user_0007_scene_0010_cfg_0005_104122063678#0", + "gt": "[[323, 132], [333, 141], [334, 179], [319, 202], [324, 172], [312, 149], [301, 141], [291, 164], [300, 140], [300, 140]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "75930_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the white cloth from the black stand', and now you are performing subtask 'remove the white cloth from the black stand.'\nYou begin at [187, 36]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[187, 36], [184, 37], [178, 30], [175, 30], [162, 46], [156, 49], [138, 50], [156, 46], [155, 55], [161, 60]]}" + } + ], + "images": "75930_exterior_image_1_left#0", + "gt": "[[187, 36], [184, 37], [178, 30], [175, 30], [162, 46], [156, 49], [138, 50], [156, 46], [155, 55], [161, 60]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0123_user_0010_scene_0004_cfg_0005_104422070044#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the knife on the knife rack', and now you are performing subtask 'place the knife on the knife rack, pick up the knife on the knife rack, put the knife on the knife rack.'\nYour initial coordinate is [414, 143]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[414, 143], [418, 147], [411, 152], [413, 168], [423, 154], [423, 147], [441, 142], [430, 132], [386, 137], [379, 122]]}" + } + ], + "images": "RH20T_cfg5_task_0123_user_0010_scene_0004_cfg_0005_104422070044#299", + "gt": "[[414, 143], [418, 147], [411, 152], [413, 168], [423, 154], [423, 147], [441, 142], [430, 132], [386, 137], [379, 122]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "46919_exterior_image_2_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the door of the washing machine and push the tray back in', and now you are performing subtask 'push the tray back into the washing machine.'\nYour starting position is [234, 122]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[234, 122], [235, 124], [233, 128], [221, 129], [220, 125], [211, 117], [204, 115], [207, 116], [212, 114], [215, 115]]}" + } + ], + "images": "46919_exterior_image_2_left#142", + "gt": "[[234, 122], [235, 124], [233, 128], [221, 129], [220, 125], [211, 117], [204, 115], [207, 116], [212, 114], [215, 115]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg3_task_0038_user_0010_scene_0003_cfg_0003_104122063550#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the cup to the top of the cup rack and then place it down', and now you are performing subtask 'move the cup to the top of the cup rack and then place it down.'\nYour starting position is [277, 192]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[277, 192], [326, 170], [349, 186], [337, 202], [271, 215], [256, 233], [261, 221], [225, 229], [248, 222], [234, 208]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg3_task_0038_user_0010_scene_0003_cfg_0003_104122063550#0.jpg", + "gt": "[[277, 192], [326, 170], [349, 186], [337, 202], [271, 215], [256, 233], [261, 221], [225, 229], [248, 222], [234, 208]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0013_user_0020_scene_0004_cfg_0007_104122063633#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'place the block on the scale', and now you are performing subtask 'place the block on the scale.'\nStart at [234, 121]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[234, 121], [205, 166], [209, 184], [192, 197], [179, 227], [212, 144], [204, 141], [206, 127], [223, 123], [234, 131]]}" + } + ], + "images": "RH20T_cfg7_task_0013_user_0020_scene_0004_cfg_0007_104122063633#0", + "gt": "[[234, 121], [205, 166], [209, 184], [192, 197], [179, 227], [212, 144], [204, 141], [206, 127], [223, 123], [234, 131]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "67833_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the cylindrical object inside the box', and now you are performing subtask 'pick up another cylindrical object from the table.'\nThe trajectory starts at [168, 2]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[168, 2], [173, 24], [159, 93], [163, 106], [163, 65], [152, 60], [147, 81], [156, 58], [167, 61], [177, 77]]}" + } + ], + "images": "67833_exterior_image_2_left#0", + "gt": "[[168, 2], [173, 24], [159, 93], [163, 106], [163, 65], [152, 60], [147, 81], [156, 58], [167, 61], [177, 77]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "41592_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'cover the pot with the lid', and now you are performing subtask 'cover the pot with the lid.'\nYou begin at [81, 0]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[81, 0], [138, 56], [157, 100], [137, 72], [152, 55], [212, 63], [246, 110], [252, 100], [235, 108], [241, 99]]}" + } + ], + "images": "41592_exterior_image_1_left#0", + "gt": "[[81, 0], [138, 56], [157, 100], [137, 72], [152, 55], [212, 63], [246, 110], [252, 100], [235, 108], [241, 99]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "30832_exterior_image_1_left#TrajectoryPrediction_Task#8", + "task": "TrajectoryPrediction_Task", + "p_index": 8, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the fruits from the glass bowl and place them on the countertop', and now you are performing subtask 'place the fruit on the countertop.'\nYou begin at [232, 82]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[232, 82], [230, 73], [219, 77], [192, 112], [219, 75], [232, 74], [255, 91], [245, 101], [255, 87], [248, 77]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/30832_exterior_image_1_left#504.jpg", + "gt": "[[232, 82], [230, 73], [219, 77], [192, 112], [219, 75], [232, 74], [255, 91], [245, 101], [255, 87], [248, 77]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "40844_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the toy to the pot in the sink', and now you are performing subtask 'move the toy to the pot in the sink.'\nYour initial coordinate is [211.0, 64.5]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[211.0, 64.5], [207.0, 92.5], [212.0, 113.5], [197.0, 143.5], [211.0, 128.5], [227.0, 126.5], [244.0, 135.5], [252.0, 143.5], [252.0, 152.5], [229.0, 122.5]]}" + } + ], + "images": "40844_exterior_image_1_left#0", + "gt": "[[211.0, 64.5], [207.0, 92.5], [212.0, 113.5], [197.0, 143.5], [211.0, 128.5], [227.0, 126.5], [244.0, 135.5], [252.0, 143.5], [252.0, 152.5], [229.0, 122.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0037_user_0014_scene_0001_cfg_0001_038522062547#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'place the third block on top of the second block, pick up the fourth block from the table, transfer the fourth block from the table to the position above the third block, place the fourth block on top of the third block.'\nYou begin at [399, 126]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[399, 126], [364, 128], [380, 123], [400, 103], [406, 47], [400, 19], [392, 25], [393, 9], [408, 17], [418, 83]]}" + } + ], + "images": "RH20T_cfg1_task_0037_user_0014_scene_0001_cfg_0001_038522062547#413", + "gt": "[[399, 126], [364, 128], [380, 123], [400, 103], [406, 47], [400, 19], [392, 25], [393, 9], [408, 17], [418, 83]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0046_user_0014_scene_0001_cfg_0007_104122064161#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the cup on the cup rack', and now you are performing subtask 'put the cup on the cup rack.'\nStart at [337, 115]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[337, 115], [371, 122], [371, 134], [349, 90], [311, 37], [311, 23], [300, 25], [317, 32], [326, 47], [325, 69]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg7_task_0046_user_0014_scene_0001_cfg_0007_104122064161#0.jpg", + "gt": "[[337, 115], [371, 122], [371, 134], [349, 90], [311, 37], [311, 23], [300, 25], [317, 32], [326, 47], [325, 69]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "64124_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the green spoon slightly to the left', and now you are performing subtask 'move the green spoon slightly to the left.'\nYou start from [128.5, 21.0]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[128.5, 21.0], [162.5, 21.0], [211.5, 38.0], [228.5, 50.0], [226.5, 93.0], [232.5, 95.0], [232.5, 103.0], [223.5, 94.0], [192.5, 106.0], [192.5, 79.0]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/64124_exterior_image_1_left#0.jpg", + "gt": "[[128.5, 21.0], [162.5, 21.0], [211.5, 38.0], [228.5, 50.0], [226.5, 93.0], [232.5, 95.0], [232.5, 103.0], [223.5, 94.0], [192.5, 106.0], [192.5, 79.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0077_user_0015_scene_0009_cfg_0004_104422070011#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the first Lego block at the top left corner of the table to the top left corner of the gray base plate', and now you are performing subtask 'move the first Lego block at the top left corner of the table to the top left corner of the gray base plate.'\nYou begin at [333, 103]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[333, 103], [340, 122], [380, 128], [388, 143], [417, 159], [426, 179], [362, 187], [348, 203], [345, 194], [345, 194]]}" + } + ], + "images": "RH20T_cfg4_task_0077_user_0015_scene_0009_cfg_0004_104422070011#0", + "gt": "[[333, 103], [340, 122], [380, 128], [388, 143], [417, 159], [426, 179], [362, 187], [348, 203], [345, 194], [345, 194]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0036_user_0020_scene_0001_cfg_0007_104122061330#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'shake the test tube', and now you are performing subtask 'shake the test tube.'\nBegin at [266, 103] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[266, 103], [287, 140], [314, 145], [315, 167], [308, 95], [297, 104], [308, 82], [304, 157], [306, 125], [280, 96]]}" + } + ], + "images": "RH20T_cfg7_task_0036_user_0020_scene_0001_cfg_0007_104122061330#0", + "gt": "[[266, 103], [287, 140], [314, 145], [315, 167], [308, 95], [297, 104], [308, 82], [304, 157], [306, 125], [280, 96]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0130_user_0014_scene_0004_cfg_0006_104122063633#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'plug in the bulb holder with a bulb to the socket and turn on the switch of the bulb', and now you are performing subtask 'insert the lamp holder into the socket, press the lamp holder button to turn on the light.'\nStart at [197, 172]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[197, 172], [195, 152], [211, 146], [209, 150], [200, 144], [188, 146], [180, 156], [180, 167], [190, 175], [184, 180]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg6_task_0130_user_0014_scene_0004_cfg_0006_104122063633#322.jpg", + "gt": "[[197, 172], [195, 152], [211, 146], [209, 150], [200, 144], [188, 146], [180, 156], [180, 167], [190, 175], [184, 180]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0061_user_0007_scene_0003_cfg_0005_104122063678#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take everything out of the gift box', and now you are performing subtask 'place the small cube on the desktop, pick up the large cube in the box, transfer the large cube from the box to the desktop, place the large square onto the table.'\nStart at [283, 109]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[283, 109], [302, 131], [299, 173], [293, 91], [294, 109], [297, 95], [326, 135], [311, 111], [317, 106], [317, 106]]}" + } + ], + "images": "RH20T_cfg5_task_0061_user_0007_scene_0003_cfg_0005_104122063678#306", + "gt": "[[283, 109], [302, 131], [299, 173], [293, 91], [294, 109], [297, 95], [326, 135], [311, 111], [317, 106], [317, 106]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "77557_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the trash bin', and now you are performing subtask 'open the trash bin.'\nYou begin at [172, 76]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[172, 76], [183, 77], [187, 83], [184, 83], [184, 105], [176, 115], [176, 122], [179, 98], [173, 92], [174, 91]]}" + } + ], + "images": "77557_exterior_image_2_left#0", + "gt": "[[172, 76], [183, 77], [187, 83], [184, 83], [184, 105], [176, 115], [176, 122], [179, 98], [173, 92], [174, 91]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "6005_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'lay the charger across the table', and now you are performing subtask 'move the power cable from the middle of the table to below the table.'\nBegin at [219, 0] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[219, 0], [168, 22], [174, 23], [163, 79], [168, 88], [172, 65], [198, 59], [237, 74], [231, 68], [181, 74]]}" + } + ], + "images": "6005_exterior_image_1_left#0", + "gt": "[[219, 0], [168, 22], [174, 23], [163, 79], [168, 88], [172, 65], [198, 59], [237, 74], [231, 68], [181, 74]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0032_user_0016_scene_0002_cfg_0004_104122062295#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'slide the outer casing onto the gift box', and now you are performing subtask 'slide the outer casing onto the gift box.'\nStarting at [240, 242], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[240, 242], [215, 237], [206, 229], [250, 250], [259, 251], [263, 248], [263, 242], [256, 234], [231, 212], [214, 203]]}" + } + ], + "images": "RH20T_cfg4_task_0032_user_0016_scene_0002_cfg_0004_104122062295#155", + "gt": "[[240, 242], [215, 237], [206, 229], [250, 250], [259, 251], [263, 248], [263, 242], [256, 234], [231, 212], [214, 203]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "18982_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the black slider on the top of the cup', and now you are performing subtask 'open the black slider on the top of the cup.'\nStarting at [302, 5], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[302, 5], [262, 39], [261, 46], [264, 45], [261, 52], [244, 72], [252, 77], [249, 65], [256, 48], [272, 35]]}" + } + ], + "images": "18982_exterior_image_1_left#0", + "gt": "[[302, 5], [262, 39], [261, 46], [264, 45], [261, 52], [244, 72], [252, 77], [249, 65], [256, 48], [272, 35]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0003_user_0014_scene_0010_cfg_0006_037522061512#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press three buttons from left to right in sequence', and now you are performing subtask 'press the red button at the bottom.'\nYou begin at [257, 83]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[257, 83], [254, 80], [259, 77], [256, 76], [248, 82], [258, 80], [260, 83], [258, 85], [242, 80], [242, 80]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg6_task_0003_user_0014_scene_0010_cfg_0006_037522061512#0.jpg", + "gt": "[[257, 83], [254, 80], [259, 77], [256, 76], [248, 82], [258, 80], [260, 83], [258, 85], [242, 80], [242, 80]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "18719_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'place the lid on the jar', and now you are performing subtask 'place the lid on the jar.'\nYour starting position is [318, 50]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[318, 50], [268, 104], [216, 74], [189, 78], [152, 129], [153, 62], [170, 57], [151, 55], [171, 43], [171, 43]]}" + } + ], + "images": "18719_exterior_image_1_left#0", + "gt": "[[318, 50], [268, 104], [216, 74], [189, 78], [152, 129], [153, 62], [170, 57], [151, 55], [171, 43], [171, 43]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "62709_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the can out of the sink and place it on the countertop', and now you are performing subtask 'take the can out of the sink and place it on the countertop.'\nYour starting position is [222, 111]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[222, 111], [216, 127], [232, 139], [230, 148], [224, 131], [212, 123], [186, 134], [174, 149], [179, 129], [227, 121]]}" + } + ], + "images": "62709_exterior_image_2_left#0", + "gt": "[[222, 111], [216, 127], [232, 139], [230, 148], [224, 131], [212, 123], [186, 134], [174, 149], [179, 129], [227, 121]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0044_user_0020_scene_0001_cfg_0007_104122063633#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up a bag of things', and now you are performing subtask 'pick up a bag of things.'\nYour starting position is [234, 121]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[234, 121], [227, 139], [215, 145], [212, 154], [212, 163], [214, 166], [216, 164], [219, 147], [217, 133], [226, 128]]}" + } + ], + "images": "RH20T_cfg7_task_0044_user_0020_scene_0001_cfg_0007_104122063633#0", + "gt": "[[234, 121], [227, 139], [215, 145], [212, 154], [212, 163], [214, 166], [216, 164], [219, 147], [217, 133], [226, 128]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0016_user_0014_scene_0003_cfg_0001_035622060973#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'hit the pool ball', and now you are performing subtask 'strike the pool ball on the table.'\nYour starting position is [307, 237]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[307, 237], [305, 236], [302, 228], [303, 227], [304, 228], [302, 229], [302, 227], [303, 227], [302, 228], [302, 227]]}" + } + ], + "images": "RH20T_cfg1_task_0016_user_0014_scene_0003_cfg_0001_035622060973#249", + "gt": "[[307, 237], [305, 236], [302, 228], [303, 227], [304, 228], [302, 229], [302, 227], [303, 227], [302, 228], [302, 227]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "88987_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the black marker from the table and place it in the pot', and now you are performing subtask 'pick up the black marker from the table and place it in the pot.'\nStarting at [176, 1], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[176, 1], [162, 28], [153, 63], [153, 41], [147, 44], [142, 58], [157, 56], [166, 45], [162, 46], [163, 49]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/88987_exterior_image_2_left#0.jpg", + "gt": "[[176, 1], [162, 28], [153, 63], [153, 41], [147, 44], [142, 58], [157, 56], [166, 45], [162, 46], [163, 49]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0127_user_0010_scene_0001_cfg_0004_104122062823#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'plug in the power cord of the desk lamp, turn on the socket, and light up the desk lamp', and now you are performing subtask 'pick up the power cable on the table, transfer the cable from the tabletop to the corresponding socket above, insert the power cable into the socket on the table.'\nStarting at [266, 54], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[266, 54], [266, 64], [268, 55], [325, 81], [319, 90], [314, 78], [313, 102], [281, 70], [300, 74], [300, 74]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg4_task_0127_user_0010_scene_0001_cfg_0004_104122062823#126.jpg", + "gt": "[[266, 54], [266, 64], [268, 55], [325, 81], [319, 90], [314, 78], [313, 102], [281, 70], [300, 74], [300, 74]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "86672_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pour the contents of the orange cup into the grey bowl', and now you are performing subtask 'pour the contents of the orange cup into the grey bowl.'\nStart at [129, 105]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[129, 105], [143, 111], [147, 116], [146, 98], [148, 98], [151, 93], [147, 89], [146, 81], [146, 85], [148, 86]]}" + } + ], + "images": "86672_exterior_image_2_left#0", + "gt": "[[129, 105], [143, 111], [147, 116], [146, 98], [148, 98], [151, 93], [147, 89], [146, 81], [146, 85], [148, 86]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "65705_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the towel', and now you are performing subtask 'fold the towel to fully unfold.'\nYou start from [265, 67]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[265, 67], [234, 62], [207, 70], [178, 87], [179, 94], [175, 93], [176, 80], [192, 117], [200, 120], [171, 110]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/65705_exterior_image_1_left#0.jpg", + "gt": "[[265, 67], [234, 62], [207, 70], [178, 87], [179, 94], [175, 93], [176, 80], [192, 117], [200, 120], [171, 110]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0066_user_0016_scene_0001_cfg_0004_104122062823#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with large megabloks for the nth time with n blocks', and now you are performing subtask 'pick up a large Megablok from the bottom right corner.'\nFrom start point [289, 0], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[289, 0], [326, 0], [383, 28], [454, 49], [477, 48], [514, 68], [510, 134], [516, 114], [501, 96], [501, 96]]}" + } + ], + "images": "RH20T_cfg4_task_0066_user_0016_scene_0001_cfg_0004_104122062823#0", + "gt": "[[289, 0], [326, 0], [383, 28], [454, 49], [477, 48], [514, 68], [510, 134], [516, 114], [501, 96], [501, 96]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "60471_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the orange toy and put it in the silver teacup', and now you are performing subtask 'pick up the orange toy and put it in the silver teacup.'\nFrom start point [244, 0], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[244, 0], [243, 16], [219, 61], [223, 79], [211, 84], [210, 56], [204, 48], [207, 58], [203, 61], [209, 44]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/60471_exterior_image_1_left#0.jpg", + "gt": "[[244, 0], [243, 16], [219, 61], [223, 79], [211, 84], [210, 56], [204, 48], [207, 58], [203, 61], [209, 44]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "38503_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the cloth off the glass then put it back', and now you are performing subtask 'take the cloth off the glass then put it back.'\nYour initial coordinate is [119, 46]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[119, 46], [138, 56], [116, 83], [118, 129], [118, 70], [131, 55], [130, 38], [137, 30], [155, 42], [161, 35]]}" + } + ], + "images": "38503_exterior_image_2_left#0", + "gt": "[[119, 46], [138, 56], [116, 83], [118, 129], [118, 70], [131, 55], [130, 38], [137, 30], [155, 42], [161, 35]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0010_user_0010_scene_0007_cfg_0005_104122061850#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'place the handset of the telephone on the corresponding phone cradle', and now you are performing subtask 'place the handset of the telephone on the corresponding phone cradle.'\nYou begin at [305, 50]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[305, 50], [310, 68], [302, 92], [290, 92], [308, 110], [306, 138], [258, 163], [261, 187], [253, 130], [291, 110]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0010_user_0010_scene_0007_cfg_0005_104122061850#0.jpg", + "gt": "[[305, 50], [310, 68], [302, 92], [290, 92], [308, 110], [306, 138], [258, 163], [261, 187], [253, 130], [291, 110]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "89639_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the green object from the sink to the left counter', and now you are performing subtask 'move the green object from the sink to the left counter.'\nStarting at [96.0, 95.0], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[96.0, 95.0], [136.0, 113.0], [169.0, 175.0], [180.0, 180.0], [179.0, 161.0], [167.0, 149.0], [150.0, 148.0], [91.0, 158.0], [102.0, 143.0], [118.0, 145.0]]}" + } + ], + "images": "89639_exterior_image_1_left#0", + "gt": "[[96.0, 95.0], [136.0, 113.0], [169.0, 175.0], [180.0, 180.0], [179.0, 161.0], [167.0, 149.0], [150.0, 148.0], [91.0, 158.0], [102.0, 143.0], [118.0, 145.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "80390_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'the towel on the folding table', and now you are performing subtask 'fold the towel on the table one more time.'\nYou begin at [302, 117]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[302, 117], [298, 133], [261, 122], [237, 131], [263, 99], [176, 79], [193, 82], [157, 57], [151, 16], [163, 2]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/80390_exterior_image_1_left#309.jpg", + "gt": "[[302, 117], [298, 133], [261, 122], [237, 131], [263, 99], [176, 79], [193, 82], [157, 57], [151, 16], [163, 2]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0037_user_0020_scene_0004_cfg_0006_104122063633#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'place the block on the other block, pick up the block on the surface, transfer the block from the surface to the other block, place the block on the other block.'\nYour starting position is [179, 189]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[179, 189], [175, 208], [182, 218], [178, 195], [192, 174], [215, 172], [238, 183], [221, 160], [199, 155], [184, 162]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg6_task_0037_user_0020_scene_0004_cfg_0006_104122063633#743.jpg", + "gt": "[[179, 189], [175, 208], [182, 218], [178, 195], [192, 174], [215, 172], [238, 183], [221, 160], [199, 155], [184, 162]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "61716_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the red bottle from the cup and put it on the counter', and now you are performing subtask 'remove the red bottle from the cup and put it on the counter.'\nBegin at [260, 1] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[260, 1], [226, 41], [213, 68], [195, 83], [195, 97], [199, 78], [196, 71], [194, 72], [186, 87], [199, 86]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/61716_exterior_image_2_left#0.jpg", + "gt": "[[260, 1], [226, 41], [213, 68], [195, 83], [195, 97], [199, 78], [196, 71], [194, 72], [186, 87], [199, 86]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0061_user_0020_scene_0002_cfg_0007_104122061018#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take everything out of the gift box', and now you are performing subtask 'place the object on the tabletop, pick up the cube in the box, transfer the cube from the box to the tabletop, place the cube on the tabletop.'\nStarting at [270, 61], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[270, 61], [269, 78], [272, 64], [313, 107], [316, 137], [319, 91], [303, 57], [303, 86], [309, 48], [339, 39]]}" + } + ], + "images": "RH20T_cfg7_task_0061_user_0020_scene_0002_cfg_0007_104122061018#510", + "gt": "[[270, 61], [269, 78], [272, 64], [313, 107], [316, 137], [319, 91], [303, 57], [303, 86], [309, 48], [339, 39]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "35951_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the towel from right to left', and now you are performing subtask 'slide the towel on the table.'\nYour initial coordinate is [221, 86]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[221, 86], [236, 96], [207, 105], [225, 115], [232, 137], [214, 114], [188, 108], [204, 109], [209, 80], [203, 80]]}" + } + ], + "images": "35951_exterior_image_1_left#259", + "gt": "[[221, 86], [236, 96], [207, 105], [225, 115], [232, 137], [214, 114], [188, 108], [204, 109], [209, 80], [203, 80]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "91549_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the towel then move the pot to the right', and now you are performing subtask 'place the pot on the specified position on the surface.'\nYou start from [86.5, 93.5]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[86.5, 93.5], [76.5, 108.5], [82.5, 104.5], [87.5, 109.5], [70.5, 97.5], [82.5, 87.5], [103.5, 89.5], [116.5, 98.5], [113.5, 125.5], [116.5, 98.5]]}" + } + ], + "images": "91549_exterior_image_1_left#163", + "gt": "[[86.5, 93.5], [76.5, 108.5], [82.5, 104.5], [87.5, 109.5], [70.5, 97.5], [82.5, 87.5], [103.5, 89.5], [116.5, 98.5], [113.5, 125.5], [116.5, 98.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg2_task_0037_user_0007_scene_0007_cfg_0002_105422061350#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'pick up the second block from the surface, transfer the second block from the surface to the top of the first block, place the second block on top of the first block, pick up the third block from the surface.'\nBegin at [319, 170] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[319, 170], [321, 164], [322, 170], [324, 169], [319, 166], [313, 183], [318, 187], [311, 185], [299, 175], [299, 175]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg2_task_0037_user_0007_scene_0007_cfg_0002_105422061350#296.jpg", + "gt": "[[319, 170], [321, 164], [322, 170], [324, 169], [319, 166], [313, 183], [318, 187], [311, 185], [299, 175], [299, 175]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0025_user_0010_scene_0006_cfg_0005_104122061850#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold a piece of paper that has been folded once (one end is pressed down by a heavy object)', and now you are performing subtask 'unfold a piece of paper that has been folded once (one end is pressed down by a heavy object).'\nThe trajectory starts at [305, 50]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[305, 50], [318, 86], [361, 118], [359, 158], [333, 138], [304, 144], [248, 127], [285, 92], [296, 69], [290, 47]]}" + } + ], + "images": "RH20T_cfg5_task_0025_user_0010_scene_0006_cfg_0005_104122061850#0", + "gt": "[[305, 50], [318, 86], [361, 118], [359, 158], [333, 138], [304, 144], [248, 127], [285, 92], [296, 69], [290, 47]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "60558_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the green marker out of the grey bowl', and now you are performing subtask 'take the green marker out of the grey bowl.'\nYour starting position is [5.5, 46.5]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[5.5, 46.5], [111.5, 78.5], [131.5, 96.5], [144.5, 100.5], [139.5, 101.5], [151.5, 107.5], [156.5, 122.5], [148.5, 94.5], [130.5, 83.5], [126.5, 92.5]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/60558_exterior_image_1_left#0.jpg", + "gt": "[[5.5, 46.5], [111.5, 78.5], [131.5, 96.5], [144.5, 100.5], [139.5, 101.5], [151.5, 107.5], [156.5, 122.5], [148.5, 94.5], [130.5, 83.5], [126.5, 92.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "27640_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'flip the second switch on the left side of the adaptor', and now you are performing subtask 'press the second switch on the adaptor.'\nThe trajectory starts at [165, 107]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[165, 107], [177, 113], [178, 136], [193, 141], [185, 147], [189, 148], [191, 143], [202, 157], [192, 150], [200, 140]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/27640_exterior_image_1_left#0.jpg", + "gt": "[[165, 107], [177, 113], [178, 136], [193, 141], [185, 147], [189, 148], [191, 143], [202, 157], [192, 150], [200, 140]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0043_user_0020_scene_0001_cfg_0007_104122064161#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unscrew the lid from the jar', and now you are performing subtask 'unscrew the lid from the jar.'\nStart at [337, 115]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[337, 115], [353, 136], [355, 157], [372, 156], [387, 197], [389, 157], [369, 140], [369, 158], [377, 147], [358, 116]]}" + } + ], + "images": "RH20T_cfg7_task_0043_user_0020_scene_0001_cfg_0007_104122064161#0", + "gt": "[[337, 115], [353, 136], [355, 157], [372, 156], [387, 197], [389, 157], [369, 140], [369, 158], [377, 147], [358, 116]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0061_user_0015_scene_0001_cfg_0001_750612070851#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the things out of the gift box and put them on the table', and now you are performing subtask 'place the block on the table, pick up the orange ball from the gift box, transfer the gift box from the table to the table, place the orange ball on the table.'\nYou begin at [264, 224]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[264, 224], [294, 167], [296, 177], [419, 152], [469, 161], [457, 171], [454, 158], [382, 167], [313, 231], [296, 265]]}" + } + ], + "images": "RH20T_cfg1_task_0061_user_0015_scene_0001_cfg_0001_750612070851#605", + "gt": "[[264, 224], [294, 167], [296, 177], [419, 152], [469, 161], [457, 171], [454, 158], [382, 167], [313, 231], [296, 265]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "75634_exterior_image_1_left#TrajectoryPrediction_Task#8", + "task": "TrajectoryPrediction_Task", + "p_index": 8, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the drawer, take out the fruit toy, place it in the basket, and then close the drawer', and now you are performing subtask 'push the handle of the drawer to close the drawer.'\nYour starting position is [170.5, 78.5]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[170.5, 78.5], [178.5, 79.5], [174.5, 83.5], [162.5, 83.5], [152.5, 81.5], [163.5, 79.5], [165.5, 80.5], [164.5, 82.5], [160.5, 84.5], [160.5, 84.5]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/75634_exterior_image_1_left#357.jpg", + "gt": "[[170.5, 78.5], [178.5, 79.5], [174.5, 83.5], [162.5, 83.5], [152.5, 81.5], [163.5, 79.5], [165.5, 80.5], [164.5, 82.5], [160.5, 84.5], [160.5, 84.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "79387_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close the top drawer of the white file cabinet', and now you are performing subtask 'close the top drawer of the white file cabinet.'\nStart at [134, 130]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[134, 130], [135, 130], [136, 126], [134, 97], [133, 95], [133, 79], [132, 77], [137, 74], [138, 72], [142, 73]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/79387_exterior_image_2_left#0.jpg", + "gt": "[[134, 130], [135, 130], [136, 126], [134, 97], [133, 95], [133, 79], [132, 77], [137, 74], [138, 72], [142, 73]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0091_user_0007_scene_0004_cfg_0005_105422061350#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move an object from one box to another', and now you are performing subtask 'throw the block onto the table, pick up the block from the table, move the block from the table to the blue box, place the object into the light blue box.'\nFrom start point [211, 25], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[211, 25], [204, 48], [219, 87], [238, 107], [237, 147], [233, 125], [193, 120], [154, 163], [152, 188], [181, 134]]}" + } + ], + "images": "RH20T_cfg5_task_0091_user_0007_scene_0004_cfg_0005_105422061350#279", + "gt": "[[211, 25], [204, 48], [219, 87], [238, 107], [237, 147], [233, 125], [193, 120], [154, 163], [152, 188], [181, 134]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0037_user_0017_scene_0006_cfg_0004_104122062823#TrajectoryPrediction_Task#8", + "task": "TrajectoryPrediction_Task", + "p_index": 8, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'place the fourth block on top of the third block on the right side of the table, pick up the fifth block from the left side of the table, place the fifth block on top of the fourth block on the right side of the table, transfer the fifth block from the left side of the table to the right side of the table.'\nYou start from [307, 56]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[307, 56], [274, 32], [254, 41], [265, 61], [292, 33], [308, 32], [308, 45], [332, 37], [325, 22], [333, 29]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg4_task_0037_user_0017_scene_0006_cfg_0004_104122062823#400.jpg", + "gt": "[[307, 56], [274, 32], [254, 41], [265, 61], [292, 33], [308, 32], [308, 45], [332, 37], [325, 22], [333, 29]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0081_user_0015_scene_0008_cfg_0004_036422060909#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the leg of the glasses with one hand', and now you are performing subtask 'fold the right leg of the glasses on the table.'\nStarting at [363, 96], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[363, 96], [342, 97], [363, 98], [349, 141], [357, 99], [308, 110], [344, 98], [320, 103], [349, 83], [340, 68]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg4_task_0081_user_0015_scene_0008_cfg_0004_036422060909#177.jpg", + "gt": "[[363, 96], [342, 97], [363, 98], [349, 141], [357, 99], [308, 110], [344, 98], [320, 103], [349, 83], [340, 68]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0003_user_0014_scene_0006_cfg_0005_105422061350#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press three buttons from left to right in sequence', and now you are performing subtask 'press the red button on the black and white base.'\nThe trajectory starts at [276, 47]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[276, 47], [256, 4], [247, 0], [199, 0], [230, 0], [238, 24], [224, 18], [225, 39], [215, 41], [227, 30]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0003_user_0014_scene_0006_cfg_0005_105422061350#0.jpg", + "gt": "[[276, 47], [256, 4], [247, 0], [199, 0], [230, 0], [238, 24], [224, 18], [225, 39], [215, 41], [227, 30]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0009_user_0014_scene_0001_cfg_0007_104122061602#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take out a Hanoi block and throw it aside', and now you are performing subtask 'take out a Hanoi block and throw it aside.'\nStarting at [448, 116], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[448, 116], [452, 102], [456, 127], [438, 154], [456, 143], [475, 146], [452, 123], [449, 106], [450, 95], [454, 96]]}" + } + ], + "images": "RH20T_cfg7_task_0009_user_0014_scene_0001_cfg_0007_104122061602#0", + "gt": "[[448, 116], [452, 102], [456, 127], [438, 154], [456, 143], [475, 146], [452, 123], [449, 106], [450, 95], [454, 96]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "60922_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the pineapple plush toy in the black pot', and now you are performing subtask 'put the pineapple plush toy in the black pot.'\nWith start location [294, 33], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[294, 33], [272, 58], [267, 72], [220, 93], [208, 105], [206, 82], [210, 71], [221, 60], [232, 62], [229, 58]]}" + } + ], + "images": "60922_exterior_image_1_left#0", + "gt": "[[294, 33], [272, 58], [267, 72], [220, 93], [208, 105], [206, 82], [210, 71], [221, 60], [232, 62], [229, 58]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0037_user_0007_scene_0004_cfg_0005_104122061850#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'pick up the second block from the surface, place the second block on top of the first block, pick up the third block from the surface.'\nWith start location [341, 113], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[341, 113], [354, 111], [372, 118], [387, 148], [391, 187], [389, 168], [382, 146], [367, 124], [336, 93], [336, 96]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0037_user_0007_scene_0004_cfg_0005_104122061850#413.jpg", + "gt": "[[341, 113], [354, 111], [372, 118], [387, 148], [391, 187], [389, 168], [382, 146], [367, 124], [336, 93], [336, 96]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "25615_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the cloth off the stand and put it on the table', and now you are performing subtask 'take the cloth off the stand and put it on the table.'\nYou start from [217, 9]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[217, 9], [189, 27], [175, 46], [167, 48], [176, 39], [186, 42], [196, 67], [195, 71], [190, 72], [195, 49]]}" + } + ], + "images": "25615_exterior_image_1_left#0", + "gt": "[[217, 9], [189, 27], [175, 46], [167, 48], [176, 39], [186, 42], [196, 67], [195, 71], [190, 72], [195, 49]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "68107_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the faucet to the left', and now you are performing subtask 'move the faucet to the left.'\nYou start from [267.5, 17.0]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[267.5, 17.0], [229.5, 104.0], [235.5, 141.0], [228.5, 149.0], [234.5, 144.0], [222.5, 138.0], [214.5, 148.0], [185.5, 122.0], [193.5, 119.0], [180.5, 120.0]]}" + } + ], + "images": "68107_exterior_image_1_left#0", + "gt": "[[267.5, 17.0], [229.5, 104.0], [235.5, 141.0], [228.5, 149.0], [234.5, 144.0], [222.5, 138.0], [214.5, 148.0], [185.5, 122.0], [193.5, 119.0], [180.5, 120.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "78332_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the door of the second washing machine', and now you are performing subtask 'open the door of the second washing machine.'\nBegin at [139, 50] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[139, 50], [134, 100], [140, 111], [140, 125], [147, 133], [131, 143], [113, 147], [117, 141], [119, 117], [112, 61]]}" + } + ], + "images": "78332_exterior_image_1_left#0", + "gt": "[[139, 50], [134, 100], [140, 111], [140, 125], [147, 133], [131, 143], [113, 147], [117, 141], [119, 117], [112, 61]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "89980_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the Coca Cola can to the open cabinet', and now you are performing subtask 'move the Coca Cola can to the open cabinet.'\nWith start location [237, 69], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[237, 69], [225, 112], [228, 129], [217, 131], [207, 91], [208, 38], [202, 10], [190, 19], [211, 12], [219, 30]]}" + } + ], + "images": "89980_exterior_image_2_left#0", + "gt": "[[237, 69], [225, 112], [228, 129], [217, 131], [207, 91], [208, 38], [202, 10], [190, 19], [211, 12], [219, 30]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0081_user_0015_scene_0002_cfg_0004_104422070011#TrajectoryPrediction_Task#12", + "task": "TrajectoryPrediction_Task", + "p_index": 12, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the leg of the glasses (with one hand)', and now you are performing subtask 'pick up the glasses on the table.'\nYou begin at [275, 170]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[275, 170], [266, 167], [247, 154], [247, 151], [267, 154], [274, 128], [264, 122], [268, 113], [272, 115], [270, 119]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg4_task_0081_user_0015_scene_0002_cfg_0004_104422070011#382.jpg", + "gt": "[[275, 170], [266, 167], [247, 154], [247, 151], [267, 154], [274, 128], [264, 122], [268, 113], [272, 115], [270, 119]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "88295_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the lid from the table and put it on the pot', and now you are performing subtask 'pick up the lid from the table and put it on the pot.'\nYour starting position is [275, 14]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[275, 14], [218, 80], [205, 127], [212, 152], [200, 162], [207, 163], [219, 125], [232, 113], [229, 105], [223, 114]]}" + } + ], + "images": "88295_exterior_image_2_left#0", + "gt": "[[275, 14], [218, 80], [205, 127], [212, 152], [200, 162], [207, 163], [219, 125], [232, 113], [229, 105], [223, 114]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "42225_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pour some of the contents of the clear cup into the red bowl', and now you are performing subtask 'pour some of the contents of the clear cup into the red bowl.'\nBegin at [111, 104] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[111, 104], [127, 106], [121, 122], [134, 128], [137, 140], [138, 125], [133, 124], [140, 127], [139, 139], [139, 139]]}" + } + ], + "images": "42225_exterior_image_1_left#0", + "gt": "[[111, 104], [127, 106], [121, 122], [134, 128], [137, 140], [138, 125], [133, 124], [140, 127], [139, 139], [139, 139]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "47071_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the wooden spatula and mix the contents in the silver bowl', and now you are performing subtask 'take the wooden spatula and mix the contents in the silver bowl.'\nYou start from [147, 62]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[147, 62], [171, 61], [141, 62], [173, 28], [196, 68], [185, 66], [199, 70], [156, 28], [149, 59], [166, 63]]}" + } + ], + "images": "47071_exterior_image_1_left#0", + "gt": "[[147, 62], [171, 61], [141, 62], [173, 28], [196, 68], [185, 66], [199, 70], [156, 28], [149, 59], [166, 63]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "79222_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the carrot plushie in the pan', and now you are performing subtask 'put the carrot plushie in the pan.'\nBegin at [90.5, 18.5] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[90.5, 18.5], [140.5, 74.5], [161.5, 89.5], [183.5, 100.5], [186.5, 114.5], [164.5, 87.5], [153.5, 82.5], [142.5, 86.5], [139.5, 77.5], [142.5, 78.5]]}" + } + ], + "images": "79222_exterior_image_1_left#0", + "gt": "[[90.5, 18.5], [140.5, 74.5], [161.5, 89.5], [183.5, 100.5], [186.5, 114.5], [164.5, 87.5], [153.5, 82.5], [142.5, 86.5], [139.5, 77.5], [142.5, 78.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "71065_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'push the lid', and now you are performing subtask 'push the lid.'\nStart at [318.0, 31.5]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[318.0, 31.5], [282.0, 73.5], [281.0, 90.5], [271.0, 104.5], [271.0, 114.5], [266.0, 116.5], [274.0, 78.5], [280.0, 63.5], [289.0, 55.5], [288.0, 59.5]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/71065_exterior_image_1_left#0.jpg", + "gt": "[[318.0, 31.5], [282.0, 73.5], [281.0, 90.5], [271.0, 104.5], [271.0, 114.5], [266.0, 116.5], [274.0, 78.5], [280.0, 63.5], [289.0, 55.5], [288.0, 59.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0037_user_0014_scene_0001_cfg_0001_750612070851#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'pick up the first block from the table, transfer the first block from the table to the position above the second block, place the first block on top of the second block.'\nStart at [315, 161]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[315, 161], [341, 178], [372, 251], [372, 194], [419, 170], [446, 174], [448, 184], [452, 169], [435, 164], [378, 193]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0037_user_0014_scene_0001_cfg_0001_750612070851#0.jpg", + "gt": "[[315, 161], [341, 178], [372, 251], [372, 194], [419, 170], [446, 174], [448, 184], [452, 169], [435, 164], [378, 193]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "35872_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the switch of the extension cord', and now you are performing subtask 'press the switch of the extension cord.'\nYou begin at [164, 1]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[164, 1], [156, 15], [155, 10], [145, 23], [115, 32], [113, 29], [102, 31], [97, 26], [125, 29], [126, 24]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/35872_exterior_image_2_left#0.jpg", + "gt": "[[164, 1], [156, 15], [155, 10], [145, 23], [115, 32], [113, 29], [102, 31], [97, 26], [125, 29], [126, 24]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "27705_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the marker inside the mug cup', and now you are performing subtask 'put the marker inside the mug cup.'\nStart at [146, 40]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[146, 40], [138, 67], [142, 75], [139, 78], [145, 89], [144, 97], [151, 69], [160, 59], [162, 74], [162, 66]]}" + } + ], + "images": "27705_exterior_image_2_left#0", + "gt": "[[146, 40], [138, 67], [142, 75], [139, 78], [145, 89], [144, 97], [151, 69], [160, 59], [162, 74], [162, 66]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0034_user_0007_scene_0005_cfg_0005_036422060215#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the squares in a row', and now you are performing subtask 'pick up the third square from the table.'\nWith start location [259, 154], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[259, 154], [271, 148], [331, 155], [357, 165], [353, 171], [346, 172], [346, 177], [342, 168], [306, 146], [306, 156]]}" + } + ], + "images": "RH20T_cfg5_task_0034_user_0007_scene_0005_cfg_0005_036422060215#608", + "gt": "[[259, 154], [271, 148], [331, 155], [357, 165], [353, 171], [346, 172], [346, 177], [342, 168], [306, 146], [306, 156]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "50790_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the white mug to the right side of the table', and now you are performing subtask 'move the white mug to the right side of the table.'\nBegin at [152, 13] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[152, 13], [144, 50], [155, 99], [150, 116], [145, 114], [160, 99], [155, 110], [177, 110], [183, 129], [181, 95]]}" + } + ], + "images": "50790_exterior_image_2_left#0", + "gt": "[[152, 13], [144, 50], [155, 99], [150, 116], [145, 114], [160, 99], [155, 110], [177, 110], [183, 129], [181, 95]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "62326_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close the right door of the cabinet', and now you are performing subtask 'close the right door of the cabinet.'\nWith start location [95, 5], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[95, 5], [174, 137], [177, 138], [184, 135], [182, 127], [184, 111], [160, 128], [168, 127], [163, 128], [163, 128]]}" + } + ], + "images": "62326_exterior_image_1_left#0", + "gt": "[[95, 5], [174, 137], [177, 138], [184, 135], [182, 127], [184, 111], [160, 128], [168, 127], [163, 128], [163, 128]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "65111_exterior_image_2_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pour the contents from the blue cup and the orange cup into the plate', and now you are performing subtask 'transfer the orange cup from the table to the plate.'\nYour initial coordinate is [196, 82]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[196, 82], [181, 84], [171, 100], [210, 91], [210, 65], [202, 81], [172, 93], [173, 103], [187, 73], [173, 69]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/65111_exterior_image_2_left#380.jpg", + "gt": "[[196, 82], [181, 84], [171, 100], [210, 91], [210, 65], [202, 81], [172, 93], [173, 103], [187, 73], [173, 69]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0038_user_0016_scene_0009_cfg_0001_819112070044#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the cup', and now you are performing subtask 'pick up the cup.'\nWith start location [400, 168], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[400, 168], [399, 170], [401, 170], [400, 166], [393, 153], [394, 165], [388, 170], [389, 176], [397, 161], [401, 141]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0038_user_0016_scene_0009_cfg_0001_819112070044#0.jpg", + "gt": "[[400, 168], [399, 170], [401, 170], [400, 166], [393, 153], [394, 165], [388, 170], [389, 176], [397, 161], [401, 141]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "72827_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'a folded cloth', and now you are performing subtask 'a folded cloth.'\nBegin at [190.0, 122.5] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[190.0, 122.5], [195.0, 144.5], [187.0, 146.5], [199.0, 130.5], [194.0, 114.5], [177.0, 106.5], [161.0, 105.5], [154.0, 110.5], [161.0, 109.5], [148.0, 106.5]]}" + } + ], + "images": "72827_exterior_image_1_left#0", + "gt": "[[190.0, 122.5], [195.0, 144.5], [187.0, 146.5], [199.0, 130.5], [194.0, 114.5], [177.0, 106.5], [161.0, 105.5], [154.0, 110.5], [161.0, 109.5], [148.0, 106.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0072_user_0010_scene_0010_cfg_0001_819112070044#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'drop a coin into the piggy bank', and now you are performing subtask 'pick up the coin from the surface.'\nStart at [400, 168]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[400, 168], [414, 166], [406, 152], [426, 159], [427, 139], [454, 120], [431, 140], [431, 131], [421, 135], [428, 143]]}" + } + ], + "images": "RH20T_cfg1_task_0072_user_0010_scene_0010_cfg_0001_819112070044#0", + "gt": "[[400, 168], [414, 166], [406, 152], [426, 159], [427, 139], [454, 120], [431, 140], [431, 131], [421, 135], [428, 143]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0037_user_0020_scene_0004_cfg_0006_104122061330#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'place the block on the other block, pick up the block on the surface, transfer the block from the surface to the other block, place the block on the other block.'\nFrom start point [335, 113], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[335, 113], [344, 112], [350, 123], [351, 143], [343, 117], [328, 105], [320, 112], [307, 103], [289, 107], [302, 113]]}" + } + ], + "images": "RH20T_cfg6_task_0037_user_0020_scene_0004_cfg_0006_104122061330#739", + "gt": "[[335, 113], [344, 112], [350, 123], [351, 143], [343, 117], [328, 105], [320, 112], [307, 103], [289, 107], [302, 113]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "13967_exterior_image_2_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the lid and pick up the object from the pot and put it in the white bowl', and now you are performing subtask 'place the object in the white bowl.'\nThe trajectory starts at [197, 77]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[197, 77], [187, 77], [183, 103], [191, 114], [193, 94], [201, 93], [208, 107], [221, 107], [215, 120], [210, 99]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/13967_exterior_image_2_left#223.jpg", + "gt": "[[197, 77], [187, 77], [183, 103], [191, 114], [193, 94], [201, 93], [208, 107], [221, 107], [215, 120], [210, 99]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0037_user_0014_scene_0010_cfg_0001_819112070044#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'place the block from the table onto the two blocks standing upright, pick up the block from the table, transfer the block from the table to the three blocks standing upright, place the block from the table onto the three blocks standing upright.'\nStarting at [322, 181], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[322, 181], [320, 184], [319, 178], [312, 177], [299, 185], [288, 210], [296, 196], [311, 183], [323, 177], [323, 177]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0037_user_0014_scene_0010_cfg_0001_819112070044#208.jpg", + "gt": "[[322, 181], [320, 184], [319, 178], [312, 177], [299, 185], [288, 210], [296, 196], [311, 183], [323, 177], [323, 177]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0119_user_0007_scene_0002_cfg_0005_104122063678#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn off the water tap', and now you are performing subtask 'turn off the water tap.'\nYour initial coordinate is [213, 120]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[213, 120], [215, 83], [195, 93], [193, 103], [212, 104], [224, 117], [224, 95], [231, 109], [241, 111], [241, 124]]}" + } + ], + "images": "RH20T_cfg5_task_0119_user_0007_scene_0002_cfg_0005_104122063678#0", + "gt": "[[213, 120], [215, 83], [195, 93], [193, 103], [212, 104], [224, 117], [224, 95], [231, 109], [241, 111], [241, 124]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg2_task_0010_user_0003_scene_0002_cfg_0002_036422060215#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'place the handset of the telephone on the corresponding phone cradle', and now you are performing subtask 'place the handset of the telephone on the corresponding phone cradle.'\nWith start location [348, 267], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[348, 267], [274, 229], [278, 274], [294, 265], [286, 278], [274, 264], [310, 241], [374, 247], [366, 261], [426, 251]]}" + } + ], + "images": "RH20T_cfg2_task_0010_user_0003_scene_0002_cfg_0002_036422060215#0", + "gt": "[[348, 267], [274, 229], [278, 274], [294, 265], [286, 278], [274, 264], [310, 241], [374, 247], [366, 261], [426, 251]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "33072_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn off the left light switch', and now you are performing subtask 'turn off the left light switch.'\nStart at [212, 88]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[212, 88], [196, 88], [180, 75], [173, 79], [165, 74], [156, 59], [159, 54], [140, 56], [146, 71], [158, 73]]}" + } + ], + "images": "33072_exterior_image_1_left#0", + "gt": "[[212, 88], [196, 88], [180, 75], [173, 79], [165, 74], [156, 59], [159, 54], [140, 56], [146, 71], [158, 73]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0003_user_0008_scene_0002_cfg_0001_038522063145#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press three buttons from left to right in sequence', and now you are performing subtask 'press the first button on the desk, press the second button on the desk.'\nYour initial coordinate is [547, 167]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[547, 167], [550, 162], [532, 138], [486, 113], [460, 101], [450, 116], [437, 112], [432, 118], [436, 107], [436, 107]]}" + } + ], + "images": "RH20T_cfg1_task_0003_user_0008_scene_0002_cfg_0001_038522063145#131", + "gt": "[[547, 167], [550, 162], [532, 138], [486, 113], [460, 101], [450, 116], [437, 112], [432, 118], [436, 107], [436, 107]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "61768_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the marker out of the pot and put it on the table', and now you are performing subtask 'take the marker out of the pot and put it on the table.'\nThe trajectory starts at [203, 2]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[203, 2], [192, 27], [188, 61], [189, 63], [200, 37], [194, 64], [201, 51], [198, 53], [198, 51], [200, 51]]}" + } + ], + "images": "61768_exterior_image_2_left#0", + "gt": "[[203, 2], [192, 27], [188, 61], [189, 63], [200, 37], [194, 64], [201, 51], [198, 53], [198, 51], [200, 51]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg3_task_0008_user_0016_scene_0009_cfg_0003_036422060909#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'grab the block and place it at the designated location', and now you are performing subtask 'grab the block and place it at the designated location.'\nYou begin at [336, 88]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[336, 88], [359, 132], [329, 74], [286, 80], [227, 65], [207, 95], [217, 146], [232, 117], [315, 125], [309, 98]]}" + } + ], + "images": "RH20T_cfg3_task_0008_user_0016_scene_0009_cfg_0003_036422060909#0", + "gt": "[[336, 88], [359, 132], [329, 74], [286, 80], [227, 65], [207, 95], [217, 146], [232, 117], [315, 125], [309, 98]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0081_user_0007_scene_0004_cfg_0004_104422070011#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the leg of the glasses (with one hand)', and now you are performing subtask 'transfer the glasses from the patterned blanket to the vertical position, manipulate the leg of the glasses to unfold it.'\nYour starting position is [306, 132]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[306, 132], [331, 136], [335, 138], [336, 144], [332, 145], [319, 140], [306, 129], [297, 126], [293, 126], [311, 127]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg4_task_0081_user_0007_scene_0004_cfg_0004_104422070011#257.jpg", + "gt": "[[306, 132], [331, 136], [335, 138], [336, 144], [332, 145], [319, 140], [306, 129], [297, 126], [293, 126], [311, 127]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "91297_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the screwdriver on the tray', and now you are performing subtask 'put the screwdriver on the tray.'\nWith start location [199, 5], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[199, 5], [180, 79], [177, 140], [161, 165], [165, 179], [159, 180], [150, 127], [124, 124], [110, 144], [137, 114]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/91297_exterior_image_2_left#0.jpg", + "gt": "[[199, 5], [180, 79], [177, 140], [161, 165], [165, 179], [159, 180], [150, 127], [124, 124], [110, 144], [137, 114]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg2_task_0011_user_0013_scene_0001_cfg_0002_104122061850#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the watering can to the center of the table', and now you are performing subtask 'move the watering can to the center of the table.'\nWith start location [337, 109], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[337, 109], [343, 91], [403, 20], [418, 13], [430, 45], [411, 92], [389, 113], [395, 117], [424, 33], [427, 40]]}" + } + ], + "images": "RH20T_cfg2_task_0011_user_0013_scene_0001_cfg_0002_104122061850#0", + "gt": "[[337, 109], [343, 91], [403, 20], [418, 13], [430, 45], [411, 92], [389, 113], [395, 117], [424, 33], [427, 40]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg2_task_0003_user_0006_scene_0007_cfg_0002_104122063678#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the three buttons in sequence', and now you are performing subtask 'press the gray base red button, press the yellow base green button.'\nWith start location [286, 216], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[286, 216], [295, 191], [291, 172], [297, 169], [299, 181], [294, 185], [281, 164], [271, 168], [259, 191], [263, 196]]}" + } + ], + "images": "RH20T_cfg2_task_0003_user_0006_scene_0007_cfg_0002_104122063678#280", + "gt": "[[286, 216], [295, 191], [291, 172], [297, 169], [299, 181], [294, 185], [281, 164], [271, 168], [259, 191], [263, 196]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0017_user_0014_scene_0002_cfg_0006_104122064161#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the pen into the pen holder', and now you are performing subtask 'pick up the pen from the table.'\nThe trajectory starts at [338, 110]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[338, 110], [340, 117], [338, 124], [316, 181], [313, 183], [323, 135], [321, 119], [293, 72], [287, 75], [295, 96]]}" + } + ], + "images": "RH20T_cfg6_task_0017_user_0014_scene_0002_cfg_0006_104122064161#0", + "gt": "[[338, 110], [340, 117], [338, 124], [316, 181], [313, 183], [323, 135], [321, 119], [293, 72], [287, 75], [295, 96]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "42894_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pull the white bowl to the left, take out the fork and the spoon from the bowl, then place them on the table, move the white cup to the left', and now you are performing subtask 'pick up the spoon from the white bowl.'\nYour starting position is [121, 90]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[121, 90], [125, 118], [132, 110], [129, 119], [133, 105], [116, 115], [135, 125], [134, 139], [138, 115], [130, 117]]}" + } + ], + "images": "42894_exterior_image_1_left#141", + "gt": "[[121, 90], [125, 118], [132, 110], [129, 119], [133, 105], [116, 115], [135, 125], [134, 139], [138, 115], [130, 117]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg2_task_0077_user_0014_scene_0006_cfg_0002_105422061350#TrajectoryPrediction_Task#8", + "task": "TrajectoryPrediction_Task", + "p_index": 8, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stacking blocks (small Lego) randomly one at a time', and now you are performing subtask 'place the purple block on the yellow block, pick up the green block on the table, transfer the green block from the table to the purple block, place the green block on the purple block.'\nYou start from [194, 94]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[194, 94], [191, 81], [198, 90], [149, 92], [144, 117], [159, 95], [193, 93], [208, 99], [206, 107], [206, 107]]}" + } + ], + "images": "RH20T_cfg2_task_0077_user_0014_scene_0006_cfg_0002_105422061350#914", + "gt": "[[194, 94], [191, 81], [198, 90], [149, 92], [144, 117], [159, 95], [193, 93], [208, 99], [206, 107], [206, 107]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "70471_exterior_image_2_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the white and black mugs from the drawer, push the drawer closed, close the open bottom cabinet', and now you are performing subtask 'push the drawer closed.'\nYour initial coordinate is [158, 101]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[158, 101], [149, 105], [144, 99], [111, 125], [109, 135], [114, 139], [113, 143], [130, 135], [147, 120], [133, 128]]}" + } + ], + "images": "70471_exterior_image_2_left#600", + "gt": "[[158, 101], [149, 105], [144, 99], [111, 125], [109, 135], [114, 139], [113, 143], [130, 135], [147, 120], [133, 128]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "47386_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the object from the blue plate and place it on the table, then pick up another object from the plate and place it on the table, and then slide the towel to the left', and now you are performing subtask 'pick up the object from the plate.'\nYou start from [183, 2]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[183, 2], [150, 39], [147, 51], [156, 59], [150, 37], [168, 34], [170, 41], [136, 37], [144, 63], [149, 52]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/47386_exterior_image_1_left#0.jpg", + "gt": "[[183, 2], [150, 39], [147, 51], [156, 59], [150, 37], [168, 34], [170, 41], [136, 37], [144, 63], [149, 52]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0037_user_0020_scene_0009_cfg_0006_104122061330#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'place the first block on the second block, pick up the third block from the table, transfer the third block from the table to the first block, place the third block on the first block, pick up the fourth block from the table.'\nYour initial coordinate is [299, 154]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[299, 154], [322, 107], [382, 73], [372, 101], [371, 81], [336, 90], [293, 127], [296, 140], [352, 96], [375, 165]]}" + } + ], + "images": "RH20T_cfg6_task_0037_user_0020_scene_0009_cfg_0006_104122061330#459", + "gt": "[[299, 154], [322, 107], [382, 73], [372, 101], [371, 81], [336, 90], [293, 127], [296, 140], [352, 96], [375, 165]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "77695_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the watermelon plush toy from the table and move it to the box', and now you are performing subtask 'pick up the watermelon plush toy from the table and move it to the box.'\nYour starting position is [295, 74]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[295, 74], [250, 59], [271, 48], [247, 61], [271, 57], [245, 65], [258, 77], [250, 83], [234, 59], [225, 61]]}" + } + ], + "images": "77695_exterior_image_1_left#0", + "gt": "[[295, 74], [250, 59], [271, 48], [247, 61], [271, 57], [245, 65], [258, 77], [250, 83], [234, 59], [225, 61]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "30832_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the fruits from the glass bowl and place them on the countertop', and now you are performing subtask 'pick up the fruit from the glass bowl.'\nWith start location [238, 86], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[238, 86], [211, 93], [207, 117], [220, 82], [229, 77], [235, 86], [222, 102], [221, 78], [214, 86], [214, 86]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/30832_exterior_image_1_left#251.jpg", + "gt": "[[238, 86], [211, 93], [207, 117], [220, 82], [229, 77], [235, 86], [222, 102], [221, 78], [214, 86], [214, 86]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0011_user_0014_scene_0007_cfg_0006_104122064161#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'water the plant', and now you are performing subtask 'water the plant.'\nYour initial coordinate is [338, 110]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[338, 110], [347, 168], [324, 62], [357, 88], [330, 150], [346, 162], [356, 152], [351, 119], [326, 89], [331, 59]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg6_task_0011_user_0014_scene_0007_cfg_0006_104122064161#0.jpg", + "gt": "[[338, 110], [347, 168], [324, 62], [357, 88], [330, 150], [346, 162], [356, 152], [351, 119], [326, 89], [331, 59]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "49916_exterior_image_2_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the lemon from the white plate and put it on the nightstand', and now you are performing subtask 'transfer the lemon from the white plate to the nightstand.'\nYou start from [113, 91]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[113, 91], [116, 91], [115, 90], [115, 92], [113, 84], [106, 76], [97, 76], [97, 83], [100, 83], [100, 83]]}" + } + ], + "images": "49916_exterior_image_2_left#102", + "gt": "[[113, 91], [116, 91], [115, 90], [115, 92], [113, 84], [106, 76], [97, 76], [97, 83], [100, 83], [100, 83]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0066_user_0014_scene_0007_cfg_0007_104122064161#TrajectoryPrediction_Task#10", + "task": "TrajectoryPrediction_Task", + "p_index": 10, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with large Megabloks for the nth time with n blocks', and now you are performing subtask 'place the building blocks on the pile of building blocks on the building board, pick up the building blocks on the table, transfer the building blocks from the desktop to the pile of building blocks on the building board, place the building blocks on the pile of building blocks on the building board.'\nYour starting position is [371, 173]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[371, 173], [388, 147], [414, 137], [427, 154], [427, 139], [373, 138], [356, 153], [341, 152], [344, 163], [350, 145]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg7_task_0066_user_0014_scene_0007_cfg_0007_104122064161#709.jpg", + "gt": "[[371, 173], [388, 147], [414, 137], [427, 154], [427, 139], [373, 138], [356, 153], [341, 152], [344, 163], [350, 145]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "49875_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the lid and put it on the pot', and now you are performing subtask 'pick up the lid and put it on the pot.'\nYou start from [295, 54]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[295, 54], [233, 76], [232, 64], [214, 98], [184, 103], [150, 89], [178, 59], [190, 61], [188, 76], [180, 64]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/49875_exterior_image_1_left#0.jpg", + "gt": "[[295, 54], [233, 76], [232, 64], [214, 98], [184, 103], [150, 89], [178, 59], [190, 61], [188, 76], [180, 64]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "91433_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'slide the green cloth backwards', and now you are performing subtask 'slide the green cloth backwards.'\nYou start from [83, 0]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[83, 0], [109, 73], [129, 77], [144, 89], [151, 82], [155, 69], [154, 60], [148, 56], [156, 61], [152, 57]]}" + } + ], + "images": "91433_exterior_image_1_left#0", + "gt": "[[83, 0], [109, 73], [129, 77], [144, 89], [151, 82], [155, 69], [154, 60], [148, 56], [156, 61], [152, 57]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0015_user_0014_scene_0005_cfg_0006_104122061018#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'play the drum', and now you are performing subtask 'play the drum.'\nYour starting position is [367, 28]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[367, 28], [274, 64], [252, 118], [259, 134], [324, 72], [351, 91], [360, 124], [330, 120], [366, 92], [366, 92]]}" + } + ], + "images": "RH20T_cfg6_task_0015_user_0014_scene_0005_cfg_0006_104122061018#0", + "gt": "[[367, 28], [274, 64], [252, 118], [259, 134], [324, 72], [351, 91], [360, 124], [330, 120], [366, 92], [366, 92]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "72195_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the toy box closer to you', and now you are performing subtask 'move the toy box closer to you.'\nYour starting position is [82, 32]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[82, 32], [157, 86], [159, 106], [166, 106], [161, 90], [190, 88], [187, 103], [178, 90], [129, 126], [155, 94]]}" + } + ], + "images": "72195_exterior_image_1_left#0", + "gt": "[[82, 32], [157, 86], [159, 106], [166, 106], [161, 90], [190, 88], [187, 103], [178, 90], [129, 126], [155, 94]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0101_user_0007_scene_0010_cfg_0005_104122063678#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'clean the table with a cloth', and now you are performing subtask 'clean the table with a cloth.'\nBegin at [323, 132] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[323, 132], [346, 151], [363, 206], [366, 264], [354, 275], [356, 228], [368, 282], [359, 212], [340, 172], [328, 174]]}" + } + ], + "images": "RH20T_cfg5_task_0101_user_0007_scene_0010_cfg_0005_104122063678#0", + "gt": "[[323, 132], [346, 151], [363, 206], [366, 264], [354, 275], [356, 228], [368, 282], [359, 212], [340, 172], [328, 174]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0029_user_0001_scene_0004_cfg_0001_038522062547#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'grasp the handle and open the drawer', and now you are performing subtask 'grasp the handle and open the drawer.'\nYou start from [403, 134]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[403, 134], [437, 119], [489, 66], [514, 49], [504, 72], [462, 96], [448, 94], [520, 76], [506, 70], [481, 79]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0029_user_0001_scene_0004_cfg_0001_038522062547#0.jpg", + "gt": "[[403, 134], [437, 119], [489, 66], [514, 49], [504, 72], [462, 96], [448, 94], [520, 76], [506, 70], [481, 79]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0034_user_0014_scene_0001_cfg_0007_104122064161#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the squares into a pyramid shape', and now you are performing subtask 'pick up the square, place the square on the table, pick up the square.'\nYou begin at [364, 204]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[364, 204], [371, 213], [369, 232], [365, 238], [365, 235], [358, 223], [359, 222], [354, 206], [370, 215], [373, 213]]}" + } + ], + "images": "RH20T_cfg7_task_0034_user_0014_scene_0001_cfg_0007_104122064161#189", + "gt": "[[364, 204], [371, 213], [369, 232], [365, 238], [365, 235], [358, 223], [359, 222], [354, 206], [370, 215], [373, 213]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0037_user_0014_scene_0001_cfg_0007_037522061512#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line', and now you are performing subtask 'transfer the first block from the table to the stacking position, place the first block at the stacking position, pick up the second block from the table, transfer the second block from the table to the stacking position.'\nYou start from [289, 115]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[289, 115], [282, 110], [270, 111], [264, 115], [262, 124], [263, 124], [263, 110], [271, 96], [277, 93], [287, 102]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg7_task_0037_user_0014_scene_0001_cfg_0007_037522061512#178.jpg", + "gt": "[[289, 115], [282, 110], [270, 111], [264, 115], [262, 124], [263, 124], [263, 110], [271, 96], [277, 93], [287, 102]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "51023_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the rectangular block on the table', and now you are performing subtask 'put the rectangular block on the table.'\nStarting at [196, 2], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[196, 2], [185, 36], [193, 58], [186, 63], [183, 47], [165, 42], [147, 55], [143, 67], [146, 39], [146, 39]]}" + } + ], + "images": "51023_exterior_image_2_left#0", + "gt": "[[196, 2], [185, 36], [193, 58], [186, 63], [183, 47], [165, 42], [147, 55], [143, 67], [146, 39], [146, 39]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0002_user_0014_scene_0004_cfg_0001_750612070853#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pull out a napkin', and now you are performing subtask 'pull out a napkin.'\nYour initial coordinate is [339, 64]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[339, 64], [332, 0], [320, 0], [280, 152], [334, 53], [370, 80], [363, 99], [457, 142], [567, 212], [567, 228]]}" + } + ], + "images": "RH20T_cfg1_task_0002_user_0014_scene_0004_cfg_0001_750612070853#0", + "gt": "[[339, 64], [332, 0], [320, 0], [280, 152], [334, 53], [370, 80], [363, 99], [457, 142], [567, 212], [567, 228]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "63555_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the lid and close the pot', and now you are performing subtask 'pick up the lid and close the pot.'\nStarting at [259, 1], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[259, 1], [235, 41], [221, 49], [209, 71], [210, 58], [212, 72], [200, 55], [195, 72], [203, 73], [202, 60]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/63555_exterior_image_2_left#0.jpg", + "gt": "[[259, 1], [235, 41], [221, 49], [209, 71], [210, 58], [212, 72], [200, 55], [195, 72], [203, 73], [202, 60]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "13938_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the object in the pot that is in the sink', and now you are performing subtask 'put the object in the pot that is in the sink.'\nStart at [182, 0]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[182, 0], [183, 39], [176, 82], [171, 93], [158, 99], [170, 108], [149, 121], [151, 126], [179, 102], [180, 80]]}" + } + ], + "images": "13938_exterior_image_2_left#0", + "gt": "[[182, 0], [183, 39], [176, 82], [171, 93], [158, 99], [170, 108], [149, 121], [151, 126], [179, 102], [180, 80]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0079_user_0015_scene_0003_cfg_0001_819112070044#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the microwave door', and now you are performing subtask 'pull the handle of the microwave door to open the door.'\nYour initial coordinate is [400, 168]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[400, 168], [404, 142], [412, 136], [410, 150], [401, 156], [404, 146], [400, 161], [352, 171], [357, 193], [346, 182]]}" + } + ], + "images": "RH20T_cfg1_task_0079_user_0015_scene_0003_cfg_0001_819112070044#0", + "gt": "[[400, 168], [404, 142], [412, 136], [410, 150], [401, 156], [404, 146], [400, 161], [352, 171], [357, 193], [346, 182]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0096_user_0007_scene_0003_cfg_0005_036422060215#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the drawer and place the cube on the table', and now you are performing subtask 'pull the handle of the drawer to pull open the drawer, pick up the block from the drawer, transfer the block from the drawer to the table, place the block on the table.'\nFrom start point [259, 101], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[259, 101], [272, 90], [295, 104], [292, 151], [291, 91], [280, 85], [239, 88], [228, 138], [236, 104], [249, 89]]}" + } + ], + "images": "RH20T_cfg5_task_0096_user_0007_scene_0003_cfg_0005_036422060215#335", + "gt": "[[259, 101], [272, 90], [295, 104], [292, 151], [291, 91], [280, 85], [239, 88], [228, 138], [236, 104], [249, 89]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "42132_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pour the beans from the cup into the bowl', and now you are performing subtask 'pour the beans from the cup into the bowl.'\nFrom start point [179, 101], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[179, 101], [168, 109], [165, 121], [162, 125], [160, 123], [160, 112], [166, 100], [170, 97], [169, 99], [171, 101]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/42132_exterior_image_1_left#0.jpg", + "gt": "[[179, 101], [168, 109], [165, 121], [162, 125], [160, 123], [160, 112], [166, 100], [170, 97], [169, 99], [171, 101]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0042_user_0007_scene_0003_cfg_0005_104122063678#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'screw on the lid (requires rotation)', and now you are performing subtask 'twist the lid clockwise onto the bottle.'\nYour initial coordinate is [327, 216]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[327, 216], [325, 215], [326, 213], [331, 213], [335, 217], [325, 223], [324, 217], [331, 215], [335, 218], [330, 221]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0042_user_0007_scene_0003_cfg_0005_104122063678#686.jpg", + "gt": "[[327, 216], [325, 215], [326, 213], [331, 213], [335, 217], [325, 223], [324, 217], [331, 215], [335, 218], [330, 221]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0031_user_0020_scene_0007_cfg_0007_104122061602#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'cover the box', and now you are performing subtask 'cover the box.'\nStarting at [448, 116], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[448, 116], [462, 158], [496, 185], [497, 217], [507, 187], [499, 151], [445, 111], [431, 120], [455, 103], [449, 95]]}" + } + ], + "images": "RH20T_cfg7_task_0031_user_0020_scene_0007_cfg_0007_104122061602#0", + "gt": "[[448, 116], [462, 158], [496, 185], [497, 217], [507, 187], [499, 151], [445, 111], [431, 120], [455, 103], [449, 95]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "19949_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the orange marker in the clear cup', and now you are performing subtask 'put the orange marker in the clear cup.'\nStarting at [225, 0], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[225, 0], [179, 67], [190, 43], [167, 50], [175, 36], [130, 39], [114, 52], [134, 47], [148, 20], [170, 17]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/19949_exterior_image_2_left#0.jpg", + "gt": "[[225, 0], [179, 67], [190, 43], [167, 50], [175, 36], [130, 39], [114, 52], [134, 47], [148, 20], [170, 17]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "15693_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the metal can into the sink', and now you are performing subtask 'put the metal can into the sink.'\nBegin at [223, 86] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[223, 86], [203, 90], [202, 121], [183, 130], [183, 120], [206, 112], [214, 113], [220, 140], [215, 120], [229, 129]]}" + } + ], + "images": "15693_exterior_image_2_left#0", + "gt": "[[223, 86], [203, 90], [202, 121], [183, 130], [183, 120], [206, 112], [214, 113], [220, 140], [215, 120], [229, 129]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "33918_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the mug cup to the right', and now you are performing subtask 'move the mug cup to the right.'\nThe trajectory starts at [104.5, 1.5]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[104.5, 1.5], [132.5, 23.5], [144.5, 39.5], [144.5, 85.5], [158.5, 94.5], [161.5, 102.5], [165.5, 84.5], [162.5, 81.5], [159.5, 89.5], [162.5, 68.5]]}" + } + ], + "images": "33918_exterior_image_1_left#0", + "gt": "[[104.5, 1.5], [132.5, 23.5], [144.5, 39.5], [144.5, 85.5], [158.5, 94.5], [161.5, 102.5], [165.5, 84.5], [162.5, 81.5], [159.5, 89.5], [162.5, 68.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "63266_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the sauce bottle from the sink and put it on the stove', and now you are performing subtask 'pick up the sauce bottle from the sink and put it on the stove.'\nFrom start point [317, 19], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[317, 19], [304, 22], [249, 50], [229, 70], [225, 84], [224, 57], [225, 77], [215, 86], [220, 75], [248, 49]]}" + } + ], + "images": "63266_exterior_image_2_left#0", + "gt": "[[317, 19], [304, 22], [249, 50], [229, 70], [225, 84], [224, 57], [225, 77], [215, 86], [220, 75], [248, 49]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0025_user_0020_scene_0008_cfg_0007_104122061330#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold a piece of paper that has been folded once (one end is pressed down by a weight)', and now you are performing subtask 'unfold a piece of paper that has been folded once (one end is pressed down by a weight).'\nYour initial coordinate is [266, 103]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[266, 103], [293, 143], [321, 162], [327, 180], [343, 94], [317, 78], [323, 61], [379, 111], [340, 75], [327, 74]]}" + } + ], + "images": "RH20T_cfg7_task_0025_user_0020_scene_0008_cfg_0007_104122061330#0", + "gt": "[[266, 103], [293, 143], [321, 162], [327, 180], [343, 94], [317, 78], [323, 61], [379, 111], [340, 75], [327, 74]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0033_user_0020_scene_0001_cfg_0007_104122061602#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pushing another small block to the designated position while grasping one small block', and now you are performing subtask 'transfer the front square from the position to the position aligned with the second square, place the front square in the position aligned with the second square, push the front square to move the second square to the position on the black dot on the cardboard.'\nBegin at [417, 113] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[417, 113], [428, 127], [440, 133], [483, 202], [472, 188], [476, 162], [464, 129], [466, 125], [455, 119], [460, 119]]}" + } + ], + "images": "RH20T_cfg7_task_0033_user_0020_scene_0001_cfg_0007_104122061602#265", + "gt": "[[417, 113], [428, 127], [440, 133], [483, 202], [472, 188], [476, 162], [464, 129], [466, 125], [455, 119], [460, 119]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0110_user_0015_scene_0003_cfg_0001_819112070044#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the pencil out from the pencil sharpener', and now you are performing subtask 'take the pencil out from the pencil sharpener.'\nStarting at [398, 168], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[398, 168], [343, 198], [348, 215], [322, 188], [311, 189], [301, 214], [284, 223], [288, 230], [338, 209], [338, 209]]}" + } + ], + "images": "RH20T_cfg1_task_0110_user_0015_scene_0003_cfg_0001_819112070044#0", + "gt": "[[398, 168], [343, 198], [348, 215], [322, 188], [311, 189], [301, 214], [284, 223], [288, 230], [338, 209], [338, 209]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0003_user_0010_scene_0001_cfg_0005_036422060215#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press three buttons from left to right in sequence', and now you are performing subtask 'press the red button in the middle.'\nStart at [294, 123]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[294, 123], [281, 135], [269, 138], [265, 148], [269, 133], [267, 128], [261, 126], [253, 131], [253, 133], [227, 143]]}" + } + ], + "images": "RH20T_cfg5_task_0003_user_0010_scene_0001_cfg_0005_036422060215#224", + "gt": "[[294, 123], [281, 135], [269, 138], [265, 148], [269, 133], [267, 128], [261, 126], [253, 131], [253, 133], [227, 143]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "44385_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the egg toy into the cup', and now you are performing subtask 'put the egg toy into the cup.'\nFrom start point [238, 39], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[238, 39], [247, 45], [235, 50], [241, 39], [215, 52], [197, 111], [196, 125], [214, 150], [190, 110], [173, 100]]}" + } + ], + "images": "44385_exterior_image_2_left#0", + "gt": "[[238, 39], [247, 45], [235, 50], [241, 39], [215, 52], [197, 111], [196, 125], [214, 150], [190, 110], [173, 100]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg3_task_0026_user_0010_scene_0001_cfg_0003_104122063550#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'use the gripper to push and close the drawer', and now you are performing subtask 'use the gripper to push and close the drawer.'\nYour initial coordinate is [287, 188]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[287, 188], [264, 212], [267, 215], [261, 209], [260, 185], [246, 156], [240, 129], [244, 139], [253, 149], [278, 157]]}" + } + ], + "images": "RH20T_cfg3_task_0026_user_0010_scene_0001_cfg_0003_104122063550#0", + "gt": "[[287, 188], [264, 212], [267, 215], [261, 209], [260, 185], [246, 156], [240, 129], [244, 139], [253, 149], [278, 157]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "90036_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'place the white cloth from the glass panel onto the table', and now you are performing subtask 'place the white cloth from the glass panel onto the table.'\nStart at [109, 30]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[109, 30], [106, 48], [112, 56], [96, 65], [98, 78], [95, 90], [99, 91], [101, 88], [103, 89], [100, 90]]}" + } + ], + "images": "90036_exterior_image_2_left#0", + "gt": "[[109, 30], [106, 48], [112, 56], [96, 65], [98, 78], [95, 90], [99, 91], [101, 88], [103, 89], [100, 90]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "70655_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the yellow mug to the center of the table', and now you are performing subtask 'move the yellow mug to the center of the table.'\nYou start from [32, 107]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[32, 107], [159, 109], [153, 115], [166, 119], [169, 109], [160, 117], [169, 132], [142, 124], [135, 110], [135, 110]]}" + } + ], + "images": "70655_exterior_image_2_left#0", + "gt": "[[32, 107], [159, 109], [153, 115], [166, 119], [169, 109], [160, 117], [169, 132], [142, 124], [135, 110], [135, 110]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg2_task_0077_user_0014_scene_0006_cfg_0002_037522062165#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stacking blocks (small Lego) randomly one at a time', and now you are performing subtask 'place the blue block at the grid center, pick up the red block on the table, transfer the red block from the table to the top of the blue block, place the red block on the blue block.'\nYou begin at [195, 304]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[195, 304], [145, 326], [115, 304], [135, 317], [182, 295], [195, 303], [205, 298], [203, 309], [196, 299], [196, 299]]}" + } + ], + "images": "RH20T_cfg2_task_0077_user_0014_scene_0006_cfg_0002_037522062165#276", + "gt": "[[195, 304], [145, 326], [115, 304], [135, 317], [182, 295], [195, 303], [205, 298], [203, 309], [196, 299], [196, 299]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "57664_exterior_image_2_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the spoon out of the cup, place it on the table, and pour the contents of the cup into another cup', and now you are performing subtask 'place the cup on the table.'\nYour starting position is [152, 48]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[152, 48], [162, 54], [154, 38], [153, 49], [141, 56], [146, 51], [150, 62], [158, 53], [158, 65], [154, 44]]}" + } + ], + "images": "57664_exterior_image_2_left#231", + "gt": "[[152, 48], [162, 54], [154, 38], [153, 49], [141, 56], [146, 51], [150, 62], [158, 53], [158, 65], [154, 44]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "48974_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn on the first switch from the right', and now you are performing subtask 'turn on the first switch from the right.'\nFrom start point [125, 45], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[125, 45], [157, 34], [185, 19], [174, 26], [183, 23], [191, 33], [193, 73], [197, 78], [197, 84], [197, 56]]}" + } + ], + "images": "48974_exterior_image_2_left#0", + "gt": "[[125, 45], [157, 34], [185, 19], [174, 26], [183, 23], [191, 33], [193, 73], [197, 78], [197, 84], [197, 56]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0096_user_0014_scene_0001_cfg_0001_038522062547#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take something out of a drawer', and now you are performing subtask 'pull the drawer handle to the outside of the table, pick up the object from the drawer, transfer the object from the drawer to the top of the table, place the object on the table.'\nWith start location [392, 31], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[392, 31], [382, 31], [383, 40], [372, 49], [371, 35], [393, 20], [415, 66], [417, 113], [396, 132], [391, 74]]}" + } + ], + "images": "RH20T_cfg1_task_0096_user_0014_scene_0001_cfg_0001_038522062547#168", + "gt": "[[392, 31], [382, 31], [383, 40], [372, 49], [371, 35], [393, 20], [415, 66], [417, 113], [396, 132], [391, 74]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg2_task_0073_user_0014_scene_0003_cfg_0002_036422060215#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the block in the drawer, close the drawer', and now you are performing subtask 'pick up the square on the fabric, transfer the square from the fabric to the drawer, place the square in the drawer.'\nYour initial coordinate is [295, 162]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[295, 162], [285, 182], [283, 206], [275, 202], [276, 191], [282, 179], [296, 171], [296, 163], [343, 153], [344, 158]]}" + } + ], + "images": "RH20T_cfg2_task_0073_user_0014_scene_0003_cfg_0002_036422060215#0", + "gt": "[[295, 162], [285, 182], [283, 206], [275, 202], [276, 191], [282, 179], [296, 171], [296, 163], [343, 153], [344, 158]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0077_user_0015_scene_0009_cfg_0004_104122062823#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the first Lego block at the top left corner of the table to the top left corner of the gray base plate', and now you are performing subtask 'move the first Lego block at the top left corner of the table to the top left corner of the gray base plate.'\nStarting at [290, 0], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[290, 0], [260, 0], [248, 24], [229, 29], [226, 55], [230, 45], [312, 66], [309, 83], [311, 62], [315, 63]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg4_task_0077_user_0015_scene_0009_cfg_0004_104122062823#0.jpg", + "gt": "[[290, 0], [260, 0], [248, 24], [229, 29], [226, 55], [230, 45], [312, 66], [309, 83], [311, 62], [315, 63]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0001_user_0001_scene_0002_cfg_0001_819112070044#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the button from top to bottom', and now you are performing subtask 'press the button from top to bottom.'\nYou begin at [389, 108]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[389, 108], [381, 116], [384, 118], [373, 114], [382, 124], [378, 124], [378, 140], [374, 143], [377, 147], [391, 135]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0001_user_0001_scene_0002_cfg_0001_819112070044#0.jpg", + "gt": "[[389, 108], [381, 116], [384, 118], [373, 114], [382, 124], [378, 124], [378, 140], [374, 143], [377, 147], [391, 135]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "87466_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the packet from the sink and place it on the left side of the counter', and now you are performing subtask 'remove the packet from the sink and place it on the left side of the counter.'\nWith start location [105, 102], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[105, 102], [118, 107], [141, 133], [137, 166], [136, 135], [122, 127], [108, 126], [100, 136], [102, 118], [96, 108]]}" + } + ], + "images": "87466_exterior_image_1_left#0", + "gt": "[[105, 102], [118, 107], [141, 133], [137, 166], [136, 135], [122, 127], [108, 126], [100, 136], [102, 118], [96, 108]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "44725_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the marker from the mug and put it on the table', and now you are performing subtask 'remove the marker from the mug and put it on the table.'\nFrom start point [235, 55], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[235, 55], [178, 95], [176, 122], [166, 124], [157, 144], [201, 100], [203, 92], [194, 93], [194, 125], [205, 88]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/44725_exterior_image_2_left#0.jpg", + "gt": "[[235, 55], [178, 95], [176, 122], [166, 124], [157, 144], [201, 100], [203, 92], [194, 93], [194, 125], [205, 88]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0110_user_0015_scene_0003_cfg_0001_038522062547#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the pencil out from the pencil sharpener', and now you are performing subtask 'take the pencil out from the pencil sharpener.'\nYou begin at [406, 132]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[406, 132], [413, 98], [406, 113], [440, 106], [453, 95], [443, 78], [422, 71], [424, 64], [416, 69], [419, 114]]}" + } + ], + "images": "RH20T_cfg1_task_0110_user_0015_scene_0003_cfg_0001_038522062547#0", + "gt": "[[406, 132], [413, 98], [406, 113], [440, 106], [453, 95], [443, 78], [422, 71], [424, 64], [416, 69], [419, 114]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "92033_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open and close the cup lid', and now you are performing subtask 'push the cup lid to close it.'\nYour starting position is [239, 0]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[239, 0], [246, 10], [247, 20], [241, 37], [238, 64], [233, 68], [237, 70], [232, 67], [246, 38], [247, 57]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/92033_exterior_image_1_left#0.jpg", + "gt": "[[239, 0], [246, 10], [247, 20], [241, 37], [238, 64], [233, 68], [237, 70], [232, 67], [246, 38], [247, 57]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "45947_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the tap nozzle to the left', and now you are performing subtask 'twist the tap clockwise.'\nThe trajectory starts at [185, 61]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[185, 61], [186, 67], [176, 58], [177, 46], [176, 49], [170, 50], [165, 42], [145, 33], [157, 36], [149, 33]]}" + } + ], + "images": "45947_exterior_image_1_left#79", + "gt": "[[185, 61], [186, 67], [176, 58], [177, 46], [176, 49], [170, 50], [165, 42], [145, 33], [157, 36], [149, 33]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0210_user_0015_scene_0008_cfg_0001_819112070044#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'chop the onions', and now you are performing subtask 'pick up the knife on the knife rack, transfer the knife from the knife rack to the cutting board, press the knife down to chop the onions, press the knife down to chop the onions.'\nFrom start point [399, 169], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[399, 169], [329, 194], [284, 229], [276, 250], [284, 272], [288, 234], [319, 200], [371, 181], [376, 187], [372, 210]]}" + } + ], + "images": "RH20T_cfg1_task_0210_user_0015_scene_0008_cfg_0001_819112070044#0", + "gt": "[[399, 169], [329, 194], [284, 229], [276, 250], [284, 272], [288, 234], [319, 200], [371, 181], [376, 187], [372, 210]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "39414_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the button on the handle of the kettle', and now you are performing subtask 'press the button on the handle of the kettle.'\nStarting at [117, 51], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[117, 51], [169, 60], [218, 88], [236, 109], [238, 118], [232, 118], [217, 142], [211, 143], [221, 127], [218, 113]]}" + } + ], + "images": "39414_exterior_image_2_left#0", + "gt": "[[117, 51], [169, 60], [218, 88], [236, 109], [238, 118], [232, 118], [217, 142], [211, 143], [221, 127], [218, 113]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "951_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the drawer, then put the pineapple and banana plush toys in the drawer, then close the drawer', and now you are performing subtask 'transfer the banana plush toy from the countertop to the drawer.'\nYour initial coordinate is [128.0, 55.5]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[128.0, 55.5], [124.0, 58.5], [133.0, 63.5], [122.0, 62.5], [125.0, 66.5], [124.0, 68.5], [122.0, 56.5], [124.0, 53.5], [129.0, 50.5], [153.0, 60.5]]}" + } + ], + "images": "951_exterior_image_1_left#313", + "gt": "[[128.0, 55.5], [124.0, 58.5], [133.0, 63.5], [122.0, 62.5], [125.0, 66.5], [124.0, 68.5], [122.0, 56.5], [124.0, 53.5], [129.0, 50.5], [153.0, 60.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "39944_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the mug to the left, then to the right, then back to the left', and now you are performing subtask 'push the cup to the right.'\nStart at [164, 30]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[164, 30], [166, 27], [173, 34], [159, 44], [159, 52], [156, 51], [154, 56], [162, 70], [162, 57], [167, 50]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/39944_exterior_image_1_left#190.jpg", + "gt": "[[164, 30], [166, 27], [173, 34], [159, 44], [159, 52], [156, 51], [154, 56], [162, 70], [162, 57], [167, 50]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0037_user_0016_scene_0009_cfg_0001_038522063145#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'place the third block on top of the second block, pick up the fourth block from the surface, transfer the fourth block from the desktop to the second position above the third block, place the fourth block on top of the third block.'\nYou begin at [459, 52]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[459, 52], [454, 24], [467, 15], [432, 96], [443, 43], [433, 7], [458, 10], [467, 36], [474, 16], [474, 16]]}" + } + ], + "images": "RH20T_cfg1_task_0037_user_0016_scene_0009_cfg_0001_038522063145#524", + "gt": "[[459, 52], [454, 24], [467, 15], [432, 96], [443, 43], [433, 7], [458, 10], [467, 36], [474, 16], [474, 16]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "66066_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the fabric', and now you are performing subtask 'pick up the fabric on the table.'\nBegin at [217, 46] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[217, 46], [222, 51], [226, 58], [226, 60], [227, 60], [227, 63], [226, 63], [222, 55], [211, 42], [198, 35]]}" + } + ], + "images": "66066_exterior_image_1_left#83", + "gt": "[[217, 46], [222, 51], [226, 58], [226, 60], [227, 60], [227, 63], [226, 63], [222, 55], [211, 42], [198, 35]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "15615_exterior_image_2_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the marker in the cup then put it back on the table', and now you are performing subtask 'place the marker back on the table.'\nYou begin at [181, 51]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[181, 51], [183, 53], [180, 62], [174, 65], [179, 72], [178, 66], [182, 61], [172, 98], [172, 80], [169, 82]]}" + } + ], + "images": "15615_exterior_image_2_left#213", + "gt": "[[181, 51], [183, 53], [180, 62], [174, 65], [179, 72], [178, 66], [182, 61], [172, 98], [172, 80], [169, 82]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0034_user_0015_scene_0008_cfg_0001_038522062547#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the squares into a pyramid shape', and now you are performing subtask 'place the first block in front of the table, pick up the second block from the table, transfer the second block from the table to beside the first block, place the second block beside the first block.'\nStart at [384, 194]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[384, 194], [390, 189], [391, 164], [375, 118], [360, 108], [345, 118], [383, 118], [391, 124], [393, 147], [383, 161]]}" + } + ], + "images": "RH20T_cfg1_task_0034_user_0015_scene_0008_cfg_0001_038522062547#208", + "gt": "[[384, 194], [390, 189], [391, 164], [375, 118], [360, 108], [345, 118], [383, 118], [391, 124], [393, 147], [383, 161]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0126_user_0014_scene_0006_cfg_0006_104122064161#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'plug in the power cord to the socket', and now you are performing subtask 'plug in the power cord to the socket.'\nThe trajectory starts at [338, 111]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[338, 111], [364, 107], [379, 122], [414, 137], [416, 161], [408, 152], [393, 186], [404, 164], [406, 141], [400, 132]]}" + } + ], + "images": "RH20T_cfg6_task_0126_user_0014_scene_0006_cfg_0006_104122064161#0", + "gt": "[[338, 111], [364, 107], [379, 122], [414, 137], [416, 161], [408, 152], [393, 186], [404, 164], [406, 141], [400, 132]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0073_user_0007_scene_0009_cfg_0005_104122063678#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the left block in the drawer', and now you are performing subtask 'pull the drawer open, pick up the block on the left side of the table.'\nStart at [323, 132]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[323, 132], [343, 130], [364, 147], [370, 163], [381, 177], [382, 181], [378, 192], [374, 184], [375, 164], [390, 147]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0073_user_0007_scene_0009_cfg_0005_104122063678#0.jpg", + "gt": "[[323, 132], [343, 130], [364, 147], [370, 163], [381, 177], [382, 181], [378, 192], [374, 184], [375, 164], [390, 147]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "64889_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the lid on the bottle', and now you are performing subtask 'put the lid on the bottle.'\nThe trajectory starts at [140, 35]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[140, 35], [150, 17], [167, 12], [158, 22], [169, 57], [165, 42], [144, 31], [126, 47], [141, 48], [141, 48]]}" + } + ], + "images": "64889_exterior_image_2_left#0", + "gt": "[[140, 35], [150, 17], [167, 12], [158, 22], [169, 57], [165, 42], [144, 31], [126, 47], [141, 48], [141, 48]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg3_task_0003_user_0016_scene_0003_cfg_0003_104122062823#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the three buttons in sequence', and now you are performing subtask 'press the yellow base green button, press the orange base red button.'\nBegin at [275, 73] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[275, 73], [250, 62], [230, 68], [236, 62], [200, 47], [192, 50], [198, 56], [200, 29], [212, 27], [218, 39]]}" + } + ], + "images": "RH20T_cfg3_task_0003_user_0016_scene_0003_cfg_0003_104122062823#279", + "gt": "[[275, 73], [250, 62], [230, 68], [236, 62], [200, 47], [192, 50], [198, 56], [200, 29], [212, 27], [218, 39]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0094_user_0014_scene_0010_cfg_0001_819112070044#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open a box', and now you are performing subtask 'fold the third lid on the box on the table, fold the fourth lid on the box on the table.'\nYou begin at [449, 188]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[449, 188], [454, 182], [457, 211], [453, 212], [455, 222], [454, 216], [461, 202], [461, 181], [446, 174], [446, 174]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0094_user_0014_scene_0010_cfg_0001_819112070044#154.jpg", + "gt": "[[449, 188], [454, 182], [457, 211], [453, 212], [455, 222], [454, 216], [461, 202], [461, 181], [446, 174], [446, 174]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "20007_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the drawer on the right, take out three mugs and place them on the countertop', and now you are performing subtask 'pick up the first cup from the right drawer.'\nBegin at [239, 105] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[239, 105], [198, 112], [204, 132], [232, 143], [241, 144], [230, 123], [219, 115], [226, 127], [216, 120], [214, 142]]}" + } + ], + "images": "20007_exterior_image_1_left#0", + "gt": "[[239, 105], [198, 112], [204, 132], [232, 143], [241, 144], [230, 123], [219, 115], [226, 127], [216, 120], [214, 142]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0085_user_0007_scene_0002_cfg_0005_037522062165#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the bubble ring from the assembled bubble ring and ball', and now you are performing subtask 'remove the bubble ring from the assembled bubble ring and ball.'\nYour initial coordinate is [289, 152]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[289, 152], [298, 203], [295, 260], [286, 286], [282, 292], [278, 282], [277, 290], [286, 276], [281, 229], [291, 223]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0085_user_0007_scene_0002_cfg_0005_037522062165#0.jpg", + "gt": "[[289, 152], [298, 203], [295, 260], [286, 286], [282, 292], [278, 282], [277, 290], [286, 276], [281, 229], [291, 223]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "41945_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'throw the bottle cap on the table', and now you are performing subtask 'throw the bottle cap on the table.'\nThe trajectory starts at [120, 29]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[120, 29], [121, 27], [120, 29], [115, 30], [113, 29], [111, 32], [111, 31], [122, 32], [131, 48], [131, 48]]}" + } + ], + "images": "41945_exterior_image_2_left#0", + "gt": "[[120, 29], [121, 27], [120, 29], [115, 30], [113, 29], [111, 32], [111, 31], [122, 32], [131, 48], [131, 48]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "20220_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the tap', and now you are performing subtask 'move the tap.'\nYou begin at [217, 0]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[217, 0], [233, 28], [238, 53], [247, 56], [230, 51], [223, 54], [240, 61], [216, 58], [204, 59], [211, 61]]}" + } + ], + "images": "20220_exterior_image_1_left#0", + "gt": "[[217, 0], [233, 28], [238, 53], [247, 56], [230, 51], [223, 54], [240, 61], [216, 58], [204, 59], [211, 61]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "12617_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take out the bag and the plastic container from the box and then put them on the countertop', and now you are performing subtask 'pick up the plastic container from the box.'\nThe trajectory starts at [162.0, 90.5]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[162.0, 90.5], [198.0, 84.5], [212.0, 104.5], [188.0, 62.5], [174.0, 58.5], [167.0, 82.5], [163.0, 72.5], [179.0, 67.5], [202.0, 80.5], [202.0, 80.5]]}" + } + ], + "images": "12617_exterior_image_1_left#0", + "gt": "[[162.0, 90.5], [198.0, 84.5], [212.0, 104.5], [188.0, 62.5], [174.0, 58.5], [167.0, 82.5], [163.0, 72.5], [179.0, 67.5], [202.0, 80.5], [202.0, 80.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "60705_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the table cloth', and now you are performing subtask 'transfer the tablecloth from the table to the flat position above the table.'\nYou start from [277, 79]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[277, 79], [224, 76], [232, 78], [217, 78], [198, 93], [205, 89], [194, 73], [206, 84], [200, 68], [196, 71]]}" + } + ], + "images": "60705_exterior_image_1_left#0", + "gt": "[[277, 79], [224, 76], [232, 78], [217, 78], [198, 93], [205, 89], [194, 73], [206, 84], [200, 68], [196, 71]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0064_user_0016_scene_0003_cfg_0004_104122062823#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the roll of paper down from the shelf', and now you are performing subtask 'pick up the roll of paper from the shelf, transfer the roll of paper from the shelf to the workspace, place the roll of paper in the workspace.'\nYour initial coordinate is [396, 43]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[396, 43], [403, 42], [403, 58], [395, 75], [388, 62], [331, 21], [336, 25], [353, 6], [370, 4], [369, 9]]}" + } + ], + "images": "RH20T_cfg4_task_0064_user_0016_scene_0003_cfg_0004_104122062823#163", + "gt": "[[396, 43], [403, 42], [403, 58], [395, 75], [388, 62], [331, 21], [336, 25], [353, 6], [370, 4], [369, 9]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0105_user_0020_scene_0007_cfg_0006_104122063633#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the object on the shelf', and now you are performing subtask 'pick up the object from the table, transfer the object from the table to the shelf, place the object on the shelf.'\nYou begin at [232, 119]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[232, 119], [221, 138], [171, 161], [153, 194], [155, 200], [151, 178], [161, 176], [157, 191], [184, 220], [194, 251]]}" + } + ], + "images": "RH20T_cfg6_task_0105_user_0020_scene_0007_cfg_0006_104122063633#0", + "gt": "[[232, 119], [221, 138], [171, 161], [153, 194], [155, 200], [151, 178], [161, 176], [157, 191], [184, 220], [194, 251]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0016_user_0016_scene_0005_cfg_0004_036422060909#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'hit the pool ball', and now you are performing subtask 'hit the pool ball.'\nBegin at [337, 78] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[337, 78], [298, 72], [270, 87], [296, 84], [241, 75], [246, 100], [226, 91], [217, 98], [265, 121], [238, 75]]}" + } + ], + "images": "RH20T_cfg4_task_0016_user_0016_scene_0005_cfg_0004_036422060909#0", + "gt": "[[337, 78], [298, 72], [270, 87], [296, 84], [241, 75], [246, 100], [226, 91], [217, 98], [265, 121], [238, 75]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0066_user_0014_scene_0007_cfg_0007_104122061018#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with large Megabloks for the nth time with n blocks', and now you are performing subtask 'pick up the building blocks on the table, transfer the building blocks from the desktop to the building board, place the building blocks on the building board, pick up the building blocks on the table.'\nFrom start point [363, 31], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[363, 31], [291, 31], [250, 15], [216, 40], [218, 86], [225, 64], [268, 48], [296, 60], [299, 96], [247, 57]]}" + } + ], + "images": "RH20T_cfg7_task_0066_user_0014_scene_0007_cfg_0007_104122061018#0", + "gt": "[[363, 31], [291, 31], [250, 15], [216, 40], [218, 86], [225, 64], [268, 48], [296, 60], [299, 96], [247, 57]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "67544_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close the left cabinet's drawer', and now you are performing subtask 'close the left cabinet's drawer.'\nStarting at [220, 154], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[220, 154], [211, 137], [203, 115], [194, 98], [178, 100], [164, 96], [160, 96], [160, 95], [159, 96], [160, 96]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/67544_exterior_image_1_left#0.jpg", + "gt": "[[220, 154], [211, 137], [203, 115], [194, 98], [178, 100], [164, 96], [160, 96], [160, 95], [159, 96], [160, 96]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg3_task_0073_user_0010_scene_0010_cfg_0003_104122062823#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the things in the drawer', and now you are performing subtask 'pick up the small square from the table, transfer the small square from the table to the open drawer, place the small square in the drawer.'\nFrom start point [246, 0], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[246, 0], [354, 0], [348, 54], [329, 60], [366, 141], [348, 154], [339, 211], [316, 104], [277, 39], [277, 39]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg3_task_0073_user_0010_scene_0010_cfg_0003_104122062823#0.jpg", + "gt": "[[246, 0], [354, 0], [348, 54], [329, 60], [366, 141], [348, 154], [339, 211], [316, 104], [277, 39], [277, 39]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "86272_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the white bowl and place the white bowl on the right side of the table', and now you are performing subtask 'pick up the white bowl and place the white bowl on the right side of the table.'\nFrom start point [242, 0], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[242, 0], [211, 44], [205, 70], [224, 51], [257, 49], [284, 62], [283, 79], [262, 96], [274, 69], [255, 18]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/86272_exterior_image_1_left#0.jpg", + "gt": "[[242, 0], [211, 44], [205, 70], [224, 51], [257, 49], [284, 62], [283, 79], [262, 96], [274, 69], [255, 18]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0025_user_0020_scene_0008_cfg_0007_104122064161#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold a piece of paper that has been folded once (one end is pressed down by a weight)', and now you are performing subtask 'unfold a piece of paper that has been folded once (one end is pressed down by a weight).'\nYou start from [337, 115]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[337, 115], [345, 156], [366, 173], [366, 189], [360, 117], [333, 102], [335, 90], [378, 129], [375, 136], [351, 96]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg7_task_0025_user_0020_scene_0008_cfg_0007_104122064161#0.jpg", + "gt": "[[337, 115], [345, 156], [366, 173], [366, 189], [360, 117], [333, 102], [335, 90], [378, 129], [375, 136], [351, 96]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0066_user_0016_scene_0003_cfg_0004_104422070011#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'building blocks', and now you are performing subtask 'place the green block on the block board, pick up the red block from the table, transfer the red block from the table to the block board, place the red block on the block board.'\nYour starting position is [249, 216]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[249, 216], [279, 294], [294, 219], [278, 206], [280, 196], [292, 204], [282, 191], [276, 197], [291, 192], [316, 207]]}" + } + ], + "images": "RH20T_cfg4_task_0066_user_0016_scene_0003_cfg_0004_104422070011#150", + "gt": "[[249, 216], [279, 294], [294, 219], [278, 206], [280, 196], [292, 204], [282, 191], [276, 197], [291, 192], [316, 207]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0058_user_0015_scene_0003_cfg_0001_750612070851#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn off the power strips', and now you are performing subtask 'press the first button on the power socket, press the second button on the power socket, press the third button on the power socket.'\nYou start from [125, 186]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[125, 186], [138, 194], [142, 202], [138, 203], [140, 205], [136, 204], [136, 192], [138, 193], [144, 203], [151, 208]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0058_user_0015_scene_0003_cfg_0001_750612070851#177.jpg", + "gt": "[[125, 186], [138, 194], [142, 202], [138, 203], [140, 205], [136, 204], [136, 192], [138, 193], [144, 203], [151, 208]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0073_user_0014_scene_0001_cfg_0007_037522061512#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the things in the drawer, close the drawer', and now you are performing subtask 'place the item in the drawer, pick up the round object from the table, place the prototype object in the drawer, pick up the square object from the table.'\nThe trajectory starts at [224, 102]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[224, 102], [179, 162], [172, 192], [179, 214], [210, 106], [209, 91], [221, 75], [253, 60], [227, 62], [187, 127]]}" + } + ], + "images": "RH20T_cfg7_task_0073_user_0014_scene_0001_cfg_0007_037522061512#208", + "gt": "[[224, 102], [179, 162], [172, 192], [179, 214], [210, 106], [209, 91], [221, 75], [253, 60], [227, 62], [187, 127]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0003_user_0010_scene_0001_cfg_0005_037522062165#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press three buttons from left to right in sequence', and now you are performing subtask 'press the red button in the middle, press the green button on the left.'\nStart at [258, 230]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[258, 230], [261, 213], [273, 214], [345, 260], [337, 281], [342, 259], [330, 244], [330, 182], [275, 159], [265, 135]]}" + } + ], + "images": "RH20T_cfg5_task_0003_user_0010_scene_0001_cfg_0005_037522062165#271", + "gt": "[[258, 230], [261, 213], [273, 214], [345, 260], [337, 281], [342, 259], [330, 244], [330, 182], [275, 159], [265, 135]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "80390_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'the towel on the folding table', and now you are performing subtask 'fold the towel on the table one more time.'\nYou start from [178, 91]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[178, 91], [172, 123], [162, 105], [191, 89], [185, 82], [179, 83], [208, 74], [236, 85], [262, 86], [302, 117]]}" + } + ], + "images": "80390_exterior_image_1_left#169", + "gt": "[[178, 91], [172, 123], [162, 105], [191, 89], [185, 82], [179, 83], [208, 74], [236, 85], [262, 86], [302, 117]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "55585_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the black object from the right side of the table to the left side of the table', and now you are performing subtask 'move the black object from the right side of the table to the left side of the table.'\nBegin at [236, 49] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[236, 49], [128, 72], [125, 80], [110, 67], [75, 70], [41, 84], [34, 95], [39, 109], [32, 73], [49, 84]]}" + } + ], + "images": "55585_exterior_image_2_left#0", + "gt": "[[236, 49], [128, 72], [125, 80], [110, 67], [75, 70], [41, 84], [34, 95], [39, 109], [32, 73], [49, 84]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "4759_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the blue block on the orange plate', and now you are performing subtask 'pick up the block from the table.'\nYou start from [89, 2]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[89, 2], [122, 51], [106, 43], [109, 51], [143, 90], [146, 101], [141, 94], [146, 98], [141, 101], [141, 101]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/4759_exterior_image_1_left#0.jpg", + "gt": "[[89, 2], [122, 51], [106, 43], [109, 51], [143, 90], [146, 101], [141, 94], [146, 98], [141, 101], [141, 101]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0047_user_0007_scene_0009_cfg_0005_104422070044#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the cup off the cup rack', and now you are performing subtask 'take the cup off the cup rack.'\nStart at [374, 132]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[374, 132], [370, 122], [368, 124], [358, 111], [361, 113], [362, 94], [376, 92], [391, 117], [397, 133], [396, 143]]}" + } + ], + "images": "RH20T_cfg5_task_0047_user_0007_scene_0009_cfg_0005_104422070044#0", + "gt": "[[374, 132], [370, 122], [368, 124], [358, 111], [361, 113], [362, 94], [376, 92], [391, 117], [397, 133], [396, 143]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "66631_exterior_image_1_left#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'use the towel to wipe the table', and now you are performing subtask 'wipe the table.'\nStarting at [226, 55], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[226, 55], [220, 64], [224, 105], [214, 102], [207, 86], [193, 90], [213, 115], [259, 139], [252, 112], [238, 93]]}" + } + ], + "images": "66631_exterior_image_1_left#308", + "gt": "[[226, 55], [220, 64], [224, 105], [214, 102], [207, 86], [193, 90], [213, 115], [259, 139], [252, 112], [238, 93]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "54639_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'place the small blue building block from the right on the blue building block in the middle of the desk', and now you are performing subtask 'place the small blue building block on top of the blue building block in the middle of the desk.'\nYou start from [157, 92]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[157, 92], [146, 111], [151, 89], [137, 87], [131, 79], [136, 71], [140, 104], [132, 69], [137, 64], [143, 68]]}" + } + ], + "images": "54639_exterior_image_1_left#320", + "gt": "[[157, 92], [146, 111], [151, 89], [137, 87], [131, 79], [136, 71], [140, 104], [132, 69], [137, 64], [143, 68]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0034_user_0014_scene_0007_cfg_0007_104122064161#TrajectoryPrediction_Task#8", + "task": "TrajectoryPrediction_Task", + "p_index": 8, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the squares into a pyramid shape', and now you are performing subtask 'place the fourth block on top of the right block, pick up the fifth block from the desktop, transfer the fifth block from the desktop to the top of the right block, place the fifth block on top of the right block.'\nYour starting position is [339, 276]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[339, 276], [357, 222], [339, 199], [358, 169], [366, 177], [358, 207], [343, 210], [379, 212], [388, 252], [378, 273]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg7_task_0034_user_0014_scene_0007_cfg_0007_104122064161#561.jpg", + "gt": "[[339, 276], [357, 222], [339, 199], [358, 169], [366, 177], [358, 207], [343, 210], [379, 212], [388, 252], [378, 273]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "26228_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the drawer, place the orange cup inside the drawer, close the drawer', and now you are performing subtask 'pull the drawer handle to open the drawer.'\nYour starting position is [95, 69]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[95, 69], [165, 122], [169, 159], [176, 155], [185, 164], [173, 173], [160, 170], [168, 143], [175, 145], [175, 145]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/26228_exterior_image_2_left#0.jpg", + "gt": "[[95, 69], [165, 122], [169, 159], [176, 155], [185, 164], [173, 173], [160, 170], [168, 143], [175, 145], [175, 145]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0003_user_0010_scene_0001_cfg_0005_104122063678#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press three buttons from left to right in sequence', and now you are performing subtask 'press the green button on the left.'\nBegin at [331, 142] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[331, 142], [322, 130], [331, 129], [327, 143], [332, 120], [338, 118], [326, 98], [339, 129], [339, 139], [332, 140]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0003_user_0010_scene_0001_cfg_0005_104122063678#406.jpg", + "gt": "[[331, 142], [322, 130], [331, 129], [327, 143], [332, 120], [338, 118], [326, 98], [339, 129], [339, 139], [332, 140]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg2_task_0037_user_0007_scene_0007_cfg_0002_037522062165#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'pick up the second block from the surface, transfer the second block from the surface to the top of the first block, place the second block on top of the first block, pick up the third block from the surface.'\nYour starting position is [253, 264]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[253, 264], [239, 259], [238, 263], [240, 260], [267, 264], [270, 267], [271, 262], [269, 269], [257, 281], [257, 281]]}" + } + ], + "images": "RH20T_cfg2_task_0037_user_0007_scene_0007_cfg_0002_037522062165#311", + "gt": "[[253, 264], [239, 259], [238, 263], [240, 260], [267, 264], [270, 267], [271, 262], [269, 269], [257, 281], [257, 281]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "70084_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the button on the container lid, then take off the lid and place it on the table', and now you are performing subtask 'press the button on the container lid, then take off the lid and place it on the table.'\nStarting at [79, 53], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[79, 53], [164, 59], [152, 61], [184, 75], [168, 94], [183, 100], [174, 112], [183, 60], [136, 99], [128, 79]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/70084_exterior_image_2_left#0.jpg", + "gt": "[[79, 53], [164, 59], [152, 61], [184, 75], [168, 94], [183, 100], [174, 112], [183, 60], [136, 99], [128, 79]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg3_task_0005_user_0016_scene_0003_cfg_0003_104122062823#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'approach and touch the side of the small block', and now you are performing subtask 'approach and touch the side of the small block.'\nYou begin at [242, 0]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[242, 0], [232, 0], [251, 0], [256, 10], [244, 13], [256, 25], [267, 71], [291, 83], [289, 64], [302, 67]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg3_task_0005_user_0016_scene_0003_cfg_0003_104122062823#0.jpg", + "gt": "[[242, 0], [232, 0], [251, 0], [256, 10], [244, 13], [256, 25], [267, 71], [291, 83], [289, 64], [302, 67]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "57262_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'use the towel to wipe the desk', and now you are performing subtask 'use the towel to wipe the desk.'\nYour initial coordinate is [71, 25]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[71, 25], [158, 67], [139, 86], [136, 117], [158, 126], [149, 80], [104, 80], [171, 95], [117, 98], [105, 67]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/57262_exterior_image_1_left#0.jpg", + "gt": "[[71, 25], [158, 67], [139, 86], [136, 117], [158, 126], [149, 80], [104, 80], [171, 95], [117, 98], [105, 67]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "24199_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'use the towel to wipe the pan', and now you are performing subtask 'use the towel to wipe the pan.'\nYour starting position is [108.5, 28.5]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[108.5, 28.5], [215.5, 99.5], [219.5, 134.5], [211.5, 101.5], [194.5, 95.5], [202.5, 120.5], [189.5, 104.5], [194.5, 89.5], [216.5, 137.5], [186.5, 102.5]]}" + } + ], + "images": "24199_exterior_image_1_left#0", + "gt": "[[108.5, 28.5], [215.5, 99.5], [219.5, 134.5], [211.5, 101.5], [194.5, 95.5], [202.5, 120.5], [189.5, 104.5], [194.5, 89.5], [216.5, 137.5], [186.5, 102.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "51271_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the marker in the cup', and now you are performing subtask 'put the marker in the cup.'\nYou start from [120.0, 94.0]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[120.0, 94.0], [140.0, 89.0], [143.0, 78.0], [158.0, 87.0], [151.0, 97.0], [161.0, 103.0], [167.0, 83.0], [186.0, 79.0], [180.0, 126.0], [175.0, 86.0]]}" + } + ], + "images": "51271_exterior_image_1_left#0", + "gt": "[[120.0, 94.0], [140.0, 89.0], [143.0, 78.0], [158.0, 87.0], [151.0, 97.0], [161.0, 103.0], [167.0, 83.0], [186.0, 79.0], [180.0, 126.0], [175.0, 86.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "9116_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the marker in the cup', and now you are performing subtask 'put the marker in the cup.'\nYour initial coordinate is [180, 71]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[180, 71], [214, 80], [211, 102], [219, 98], [214, 92], [204, 105], [224, 114], [229, 130], [229, 92], [229, 92]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/9116_exterior_image_1_left#0.jpg", + "gt": "[[180, 71], [214, 80], [211, 102], [219, 98], [214, 92], [204, 105], [224, 114], [229, 130], [229, 92], [229, 92]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0003_user_0010_scene_0001_cfg_0005_104122061850#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press three buttons from left to right in sequence', and now you are performing subtask 'press the yellow button on the right, press the red button in the middle.'\nYour initial coordinate is [324, 159]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[324, 159], [331, 137], [331, 124], [336, 118], [338, 121], [342, 117], [342, 122], [347, 125], [343, 122], [341, 116]]}" + } + ], + "images": "RH20T_cfg5_task_0003_user_0010_scene_0001_cfg_0005_104122061850#217", + "gt": "[[324, 159], [331, 137], [331, 124], [336, 118], [338, 121], [342, 117], [342, 122], [347, 125], [343, 122], [341, 116]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "21098_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pour the contents in the cup into the bowl', and now you are performing subtask 'pour the contents in the cup into the bowl.'\nBegin at [167, 99] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[167, 99], [163, 97], [155, 98], [142, 106], [138, 113], [138, 94], [140, 91], [144, 91], [147, 95], [144, 93]]}" + } + ], + "images": "21098_exterior_image_1_left#0", + "gt": "[[167, 99], [163, 97], [155, 98], [142, 106], [138, 113], [138, 94], [140, 91], [144, 91], [147, 95], [144, 93]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "38503_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the cloth off the glass then put it back', and now you are performing subtask 'place the cloth on the table.'\nYou begin at [247, 54]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[247, 54], [213, 54], [182, 64], [166, 64], [160, 67], [159, 78], [166, 84], [186, 98], [186, 96], [193, 93]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/38503_exterior_image_1_left#0.jpg", + "gt": "[[247, 54], [213, 54], [182, 64], [166, 64], [160, 67], [159, 78], [166, 84], [186, 98], [186, 96], [193, 93]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0064_user_0015_scene_0008_cfg_0001_038522062547#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the roll of paper to the shelf', and now you are performing subtask 'pick up the roll of paper from the desktop, transfer the roll of paper from the desktop to the shelf, place the roll of paper on the shelf.'\nWith start location [406, 134], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[406, 134], [346, 94], [333, 68], [335, 72], [318, 78], [354, 66], [374, 69], [393, 83], [446, 89], [450, 76]]}" + } + ], + "images": "RH20T_cfg1_task_0064_user_0015_scene_0008_cfg_0001_038522062547#0", + "gt": "[[406, 134], [346, 94], [333, 68], [335, 72], [318, 78], [354, 66], [374, 69], [393, 83], [446, 89], [450, 76]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0062_user_0014_scene_0003_cfg_0006_104122060811#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the toilet paper on its holder', and now you are performing subtask 'put the toilet paper on its holder.'\nYou start from [387, 129]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[387, 129], [383, 130], [394, 109], [403, 113], [404, 120], [402, 115], [386, 125], [365, 161], [368, 152], [387, 129]]}" + } + ], + "images": "RH20T_cfg6_task_0062_user_0014_scene_0003_cfg_0006_104122060811#0", + "gt": "[[387, 129], [383, 130], [394, 109], [403, 113], [404, 120], [402, 115], [386, 125], [365, 161], [368, 152], [387, 129]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0090_user_0007_scene_0001_cfg_0001_035622060973#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the wooden block', and now you are performing subtask 'press the wooden block.'\nBegin at [245, 130] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[245, 130], [241, 118], [242, 102], [237, 105], [233, 97], [227, 98], [229, 95], [236, 108], [241, 111], [241, 111]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0090_user_0007_scene_0001_cfg_0001_035622060973#0.jpg", + "gt": "[[245, 130], [241, 118], [242, 102], [237, 105], [233, 97], [227, 98], [229, 95], [236, 108], [241, 111], [241, 111]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "22217_exterior_image_2_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close the lid of the bowl', and now you are performing subtask 'pull the packaging box to the closed position.'\nYour starting position is [107, 92]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[107, 92], [108, 102], [110, 99], [114, 102], [114, 85], [127, 65], [153, 68], [139, 67], [133, 61], [145, 58]]}" + } + ], + "images": "22217_exterior_image_2_left#168", + "gt": "[[107, 92], [108, 102], [110, 99], [114, 102], [114, 85], [127, 65], [153, 68], [139, 67], [133, 61], [145, 58]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "79943_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the glass lid on the pot', and now you are performing subtask 'put the glass lid on the pot.'\nFrom start point [44.5, 23.5], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[44.5, 23.5], [125.5, 76.5], [139.5, 92.5], [137.5, 100.5], [135.5, 77.5], [144.5, 76.5], [164.5, 91.5], [164.5, 101.5], [158.5, 102.5], [156.5, 90.5]]}" + } + ], + "images": "79943_exterior_image_1_left#0", + "gt": "[[44.5, 23.5], [125.5, 76.5], [139.5, 92.5], [137.5, 100.5], [135.5, 77.5], [144.5, 76.5], [164.5, 91.5], [164.5, 101.5], [158.5, 102.5], [156.5, 90.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "83829_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the green block from the blue table and place it on the green block', and now you are performing subtask 'move the green block from the blue table and place it on the green block.'\nWith start location [67, 22], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[67, 22], [101, 105], [112, 75], [128, 80], [138, 68], [176, 75], [163, 53], [154, 51], [145, 58], [145, 58]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/83829_exterior_image_1_left#0.jpg", + "gt": "[[67, 22], [101, 105], [112, 75], [128, 80], [138, 68], [176, 75], [163, 53], [154, 51], [145, 58], [145, 58]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0037_user_0020_scene_0004_cfg_0006_104122063633#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'place the block on the other block, pick up the block on the surface, transfer the block from the surface to the other block, place the block on the other block.'\nWith start location [184, 162], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[184, 162], [182, 171], [194, 166], [185, 164], [191, 174], [201, 157], [225, 158], [238, 173], [226, 146], [205, 135]]}" + } + ], + "images": "RH20T_cfg6_task_0037_user_0020_scene_0004_cfg_0006_104122063633#997", + "gt": "[[184, 162], [182, 171], [194, 166], [185, 164], [191, 174], [201, 157], [225, 158], [238, 173], [226, 146], [205, 135]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "33844_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the button atop the flask', and now you are performing subtask 'press the button atop the flask.'\nYour initial coordinate is [121, 76]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[121, 76], [134, 76], [137, 81], [122, 83], [114, 95], [113, 105], [119, 113], [107, 102], [105, 111], [106, 75]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/33844_exterior_image_2_left#0.jpg", + "gt": "[[121, 76], [134, 76], [137, 81], [122, 83], [114, 95], [113, 105], [119, 113], [107, 102], [105, 111], [106, 75]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "66631_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'use the towel to wipe the table', and now you are performing subtask 'fold the towel.'\nBegin at [216, 72] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[216, 72], [197, 76], [194, 83], [204, 40], [202, 13], [200, 42], [206, 72], [204, 74], [207, 77], [220, 66]]}" + } + ], + "images": "66631_exterior_image_1_left#155", + "gt": "[[216, 72], [197, 76], [194, 83], [204, 40], [202, 13], [200, 42], [206, 72], [204, 74], [207, 77], [220, 66]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0073_user_0001_scene_0003_cfg_0001_819112070044#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the things in the drawer', and now you are performing subtask 'pick up the block on the drawer, transfer the block from above the drawer to inside the drawer, place the block in the drawer.'\nWith start location [400, 167], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[400, 167], [406, 142], [469, 129], [483, 119], [480, 136], [476, 131], [435, 145], [428, 179], [431, 161], [422, 163]]}" + } + ], + "images": "RH20T_cfg1_task_0073_user_0001_scene_0003_cfg_0001_819112070044#0", + "gt": "[[400, 167], [406, 142], [469, 129], [483, 119], [480, 136], [476, 131], [435, 145], [428, 179], [431, 161], [422, 163]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "44145_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the purple object in the bowl', and now you are performing subtask 'put the purple object in the bowl.'\nWith start location [229, 69], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[229, 69], [191, 72], [182, 81], [181, 101], [170, 53], [166, 52], [160, 62], [160, 76], [165, 71], [161, 54]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/44145_exterior_image_1_left#0.jpg", + "gt": "[[229, 69], [191, 72], [182, 81], [181, 101], [170, 53], [166, 52], [160, 62], [160, 76], [165, 71], [161, 54]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0083_user_0007_scene_0010_cfg_0005_104422070044#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'swat with a flyswatter', and now you are performing subtask 'swat with a flyswatter.'\nYour starting position is [374, 132]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[374, 132], [385, 170], [382, 199], [370, 161], [381, 240], [412, 182], [434, 169], [454, 172], [422, 172], [403, 182]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0083_user_0007_scene_0010_cfg_0005_104422070044#0.jpg", + "gt": "[[374, 132], [385, 170], [382, 199], [370, 161], [381, 240], [412, 182], [434, 169], [454, 172], [422, 172], [403, 182]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "54536_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'fold the green towel', and now you are performing subtask 'fold the green towel.'\nYou begin at [256, 5]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[256, 5], [232, 44], [223, 87], [202, 108], [202, 90], [179, 81], [160, 93], [157, 100], [161, 77], [157, 78]]}" + } + ], + "images": "54536_exterior_image_2_left#0", + "gt": "[[256, 5], [232, 44], [223, 87], [202, 108], [202, 90], [179, 81], [160, 93], [157, 100], [161, 77], [157, 78]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "81663_exterior_image_2_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the cup and put it on top of the table, then pick up the cloth and put it in the bowl and close the drawer', and now you are performing subtask 'place the cloth into the bowl.'\nThe trajectory starts at [146, 102]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[146, 102], [143, 95], [137, 106], [142, 130], [144, 107], [173, 117], [189, 130], [182, 117], [167, 117], [167, 117]]}" + } + ], + "images": "81663_exterior_image_2_left#146", + "gt": "[[146, 102], [143, 95], [137, 106], [142, 130], [144, 107], [173, 117], [189, 130], [182, 117], [167, 117], [167, 117]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0096_user_0015_scene_0006_cfg_0004_036422060909#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take something out of a drawer', and now you are performing subtask 'pull handle to open drawer, pull handle to open drawer.'\nYour starting position is [334, 80]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[334, 80], [325, 76], [326, 68], [319, 77], [322, 112], [339, 104], [342, 83], [302, 91], [302, 105], [352, 88]]}" + } + ], + "images": "RH20T_cfg4_task_0096_user_0015_scene_0006_cfg_0004_036422060909#0", + "gt": "[[334, 80], [325, 76], [326, 68], [319, 77], [322, 112], [339, 104], [342, 83], [302, 91], [302, 105], [352, 88]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "21585_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the green cloth to the left side of the table', and now you are performing subtask 'slide the green cloth to the left side of the table.'\nYour initial coordinate is [125, 81]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[125, 81], [127, 87], [137, 95], [145, 96], [141, 90], [133, 86], [128, 88], [121, 80], [114, 78], [101, 69]]}" + } + ], + "images": "21585_exterior_image_1_left#96", + "gt": "[[125, 81], [127, 87], [137, 95], [145, 96], [141, 90], [133, 86], [128, 88], [121, 80], [114, 78], [101, 69]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "69906_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the drawer, take out the black object, and place it on the countertop, pick up the pen on the countertop, put it back in the drawer, close the drawer', and now you are performing subtask 'place the black object on the countertop.'\nYour starting position is [91, 149]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[91, 149], [85, 143], [83, 131], [96, 114], [128, 105], [156, 103], [170, 104], [187, 109], [190, 113], [178, 105]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/69906_exterior_image_1_left#311.jpg", + "gt": "[[91, 149], [85, 143], [83, 131], [96, 114], [128, 105], [156, 103], [170, 104], [187, 109], [190, 113], [178, 105]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "66357_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the spoon out of the bowl and put it into the cup, then slightly move the two cups to the left side of the bowl', and now you are performing subtask 'pick up the second cup from the tabletop.'\nYour starting position is [165, 126]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[165, 126], [182, 122], [203, 127], [193, 143], [155, 138], [188, 125], [188, 133], [175, 131], [181, 147], [181, 147]]}" + } + ], + "images": "66357_exterior_image_1_left#245", + "gt": "[[165, 126], [182, 122], [203, 127], [193, 143], [155, 138], [188, 125], [188, 133], [175, 131], [181, 147], [181, 147]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "951_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the drawer, then put the pineapple and banana plush toys in the drawer, then close the drawer', and now you are performing subtask 'pick up the pineapple plush toy from the countertop.'\nStarting at [218.0, 124.5], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[218.0, 124.5], [159.0, 74.5], [158.0, 57.5], [171.0, 86.5], [158.0, 96.5], [186.0, 99.5], [190.0, 87.5], [176.0, 84.5], [158.0, 52.5], [132.0, 47.5]]}" + } + ], + "images": "951_exterior_image_1_left#0", + "gt": "[[218.0, 124.5], [159.0, 74.5], [158.0, 57.5], [171.0, 86.5], [158.0, 96.5], [186.0, 99.5], [190.0, 87.5], [176.0, 84.5], [158.0, 52.5], [132.0, 47.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "76141_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn off the light switch', and now you are performing subtask 'turn off the light switch.'\nYour starting position is [164.0, 79.5]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[164.0, 79.5], [198.0, 77.5], [205.0, 89.5], [211.0, 91.5], [212.0, 88.5], [206.0, 87.5], [218.0, 86.5], [210.0, 90.5], [204.0, 89.5], [204.0, 89.5]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/76141_exterior_image_1_left#0.jpg", + "gt": "[[164.0, 79.5], [198.0, 77.5], [205.0, 89.5], [211.0, 91.5], [212.0, 88.5], [206.0, 87.5], [218.0, 86.5], [210.0, 90.5], [204.0, 89.5], [204.0, 89.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0016_user_0014_scene_0001_cfg_0001_038522062547#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'hit the pool ball', and now you are performing subtask 'pick up the pool ball from the surface.'\nStart at [391, 51]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[391, 51], [390, 54], [390, 57], [388, 63], [388, 62], [390, 62], [390, 61], [392, 61], [392, 60], [392, 61]]}" + } + ], + "images": "RH20T_cfg1_task_0016_user_0014_scene_0001_cfg_0001_038522062547#409", + "gt": "[[391, 51], [390, 54], [390, 57], [388, 63], [388, 62], [390, 62], [390, 61], [392, 61], [392, 60], [392, 61]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "558_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'use the object to mix the contents in the bowl', and now you are performing subtask 'use the object to mix the contents in the bowl.'\nYour initial coordinate is [140, 99]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[140, 99], [146, 84], [142, 91], [161, 85], [184, 99], [179, 85], [169, 85], [176, 84], [169, 93], [152, 86]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/558_exterior_image_2_left#0.jpg", + "gt": "[[140, 99], [146, 84], [142, 91], [161, 85], [184, 99], [179, 85], [169, 85], [176, 84], [169, 93], [152, 86]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "15487_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the pen out of the mug and put it on the table', and now you are performing subtask 'take the pen out of the mug and put it on the table.'\nYour starting position is [270.5, 19.0]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[270.5, 19.0], [240.5, 63.0], [221.5, 70.0], [181.5, 116.0], [184.5, 74.0], [201.5, 91.0], [184.5, 121.0], [175.5, 79.0], [211.5, 124.0], [195.5, 95.0]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/15487_exterior_image_1_left#0.jpg", + "gt": "[[270.5, 19.0], [240.5, 63.0], [221.5, 70.0], [181.5, 116.0], [184.5, 74.0], [201.5, 91.0], [184.5, 121.0], [175.5, 79.0], [211.5, 124.0], [195.5, 95.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "71329_exterior_image_2_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the marker in the mug and then remove it and put it back on the table', and now you are performing subtask 'place the marker in the mug.'\nWith start location [78, 122], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[78, 122], [80, 105], [94, 82], [100, 64], [107, 60], [124, 66], [129, 71], [130, 76], [129, 71], [129, 71]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/71329_exterior_image_2_left#121.jpg", + "gt": "[[78, 122], [80, 105], [94, 82], [100, 64], [107, 60], [124, 66], [129, 71], [130, 76], [129, 71], [129, 71]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0013_user_0020_scene_0004_cfg_0007_104122061602#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'place the block on the scale', and now you are performing subtask 'place the block on the scale.'\nYou start from [448, 116]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[448, 116], [441, 133], [424, 127], [428, 154], [463, 163], [511, 218], [501, 229], [509, 196], [489, 162], [456, 152]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg7_task_0013_user_0020_scene_0004_cfg_0007_104122061602#0.jpg", + "gt": "[[448, 116], [441, 133], [424, 127], [428, 154], [463, 163], [511, 218], [501, 229], [509, 196], [489, 162], [456, 152]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "3613_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the brown object from the pot', and now you are performing subtask 'remove the brown object from the pot.'\nYour starting position is [243, 2]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[243, 2], [206, 18], [205, 41], [194, 59], [191, 54], [198, 45], [204, 77], [197, 82], [192, 75], [192, 75]]}" + } + ], + "images": "3613_exterior_image_1_left#0", + "gt": "[[243, 2], [206, 18], [205, 41], [194, 59], [191, 54], [198, 45], [204, 77], [197, 82], [192, 75], [192, 75]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "62926_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn off the switch on the adapter', and now you are performing subtask 'turn off the switch on the adapter.'\nYour starting position is [159, 2]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[159, 2], [184, 62], [183, 91], [198, 115], [192, 112], [188, 122], [185, 118], [174, 90], [165, 46], [169, 44]]}" + } + ], + "images": "62926_exterior_image_2_left#0", + "gt": "[[159, 2], [184, 62], [183, 91], [198, 115], [192, 112], [188, 122], [185, 118], [174, 90], [165, 46], [169, 44]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "15615_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the marker in the cup then put it back on the table', and now you are performing subtask 'pick up the marker from the cup.'\nBegin at [41.0, 34.0] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[41.0, 34.0], [142.0, 86.0], [187.0, 146.0], [191.0, 139.0], [166.0, 111.0], [194.0, 91.0], [229.0, 106.0], [237.0, 136.0], [220.0, 98.0], [207.0, 113.0]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/15615_exterior_image_1_left#0.jpg", + "gt": "[[41.0, 34.0], [142.0, 86.0], [187.0, 146.0], [191.0, 139.0], [166.0, 111.0], [194.0, 91.0], [229.0, 106.0], [237.0, 136.0], [220.0, 98.0], [207.0, 113.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0094_user_0007_scene_0002_cfg_0005_104122063678#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open a box', and now you are performing subtask 'push the second box lid, push the third box lid.'\nYour initial coordinate is [353, 128]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[353, 128], [349, 129], [347, 135], [341, 142], [345, 149], [347, 147], [355, 167], [349, 173], [352, 158], [345, 138]]}" + } + ], + "images": "RH20T_cfg5_task_0094_user_0007_scene_0002_cfg_0005_104122063678#325", + "gt": "[[353, 128], [349, 129], [347, 135], [341, 142], [345, 149], [347, 147], [355, 167], [349, 173], [352, 158], [345, 138]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0125_user_0007_scene_0004_cfg_0004_104122062823#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pull up the lever', and now you are performing subtask 'pull up the lever.'\nThe trajectory starts at [289, 0]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[289, 0], [291, 91], [293, 31], [277, 35], [222, 6], [294, 41], [237, 25], [187, 34], [276, 7], [290, 28]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg4_task_0125_user_0007_scene_0004_cfg_0004_104122062823#0.jpg", + "gt": "[[289, 0], [291, 91], [293, 31], [277, 35], [222, 6], [294, 41], [237, 25], [187, 34], [276, 7], [290, 28]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg2_task_0057_user_0016_scene_0006_cfg_0002_037522062165#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn on the power strips', and now you are performing subtask 'press the button on the second socket.'\nYour starting position is [247, 246]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[247, 246], [240, 249], [245, 253], [242, 257], [245, 263], [251, 262], [253, 257], [248, 261], [243, 256], [253, 257]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg2_task_0057_user_0016_scene_0006_cfg_0002_037522062165#243.jpg", + "gt": "[[247, 246], [240, 249], [245, 253], [242, 257], [245, 263], [251, 262], [253, 257], [248, 261], [243, 256], [253, 257]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "56609_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the landfill bin to the right', and now you are performing subtask 'move the landfill bin to the right.'\nYour starting position is [94.5, 49.5]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[94.5, 49.5], [103.5, 35.5], [116.5, 48.5], [103.5, 27.5], [108.5, 20.5], [130.5, 28.5], [183.5, 20.5], [207.5, 40.5], [162.5, 10.5], [136.5, 7.5]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/56609_exterior_image_1_left#0.jpg", + "gt": "[[94.5, 49.5], [103.5, 35.5], [116.5, 48.5], [103.5, 27.5], [108.5, 20.5], [130.5, 28.5], [183.5, 20.5], [207.5, 40.5], [162.5, 10.5], [136.5, 7.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "33652_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'twist the stove knob on the far left to the left then twist it back to the way it was', and now you are performing subtask 'twist the stove knob on the far left to the left then twist it back to the way it was.'\nYou begin at [135, 71]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[135, 71], [153, 85], [150, 95], [140, 105], [145, 104], [145, 144], [154, 169], [152, 163], [170, 135], [184, 91]]}" + } + ], + "images": "33652_exterior_image_1_left#0", + "gt": "[[135, 71], [153, 85], [150, 95], [140, 105], [145, 104], [145, 144], [154, 169], [152, 163], [170, 135], [184, 91]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "23502_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the orange cuboid on the stack', and now you are performing subtask 'put the orange cuboid on the stack.'\nThe trajectory starts at [215.0, 2.0]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[215.0, 2.0], [226.0, 83.0], [247.0, 103.0], [240.0, 112.0], [238.0, 68.0], [210.0, 29.0], [188.0, 20.0], [179.0, 31.0], [182.0, 50.0], [186.0, 8.0]]}" + } + ], + "images": "23502_exterior_image_1_left#0", + "gt": "[[215.0, 2.0], [226.0, 83.0], [247.0, 103.0], [240.0, 112.0], [238.0, 68.0], [210.0, 29.0], [188.0, 20.0], [179.0, 31.0], [182.0, 50.0], [186.0, 8.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0038_user_0007_scene_0009_cfg_0005_104122063678#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the red cup from the cube to the table', and now you are performing subtask 'move the red cup from the cube to the table.'\nYour starting position is [323, 132]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[323, 132], [326, 152], [267, 135], [226, 139], [216, 145], [221, 169], [227, 147], [263, 134], [274, 142], [274, 142]]}" + } + ], + "images": "RH20T_cfg5_task_0038_user_0007_scene_0009_cfg_0005_104122063678#0", + "gt": "[[323, 132], [326, 152], [267, 135], [226, 139], [216, 145], [221, 169], [227, 147], [263, 134], [274, 142], [274, 142]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0066_user_0014_scene_0008_cfg_0001_819112070044#TrajectoryPrediction_Task#8", + "task": "TrajectoryPrediction_Task", + "p_index": 8, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'putting a portion of the Lego blocks on the Lego baseplate', and now you are performing subtask 'insert the orange Lego brick into the Lego base, pick up the second red Lego brick from the table.'\nStarting at [386, 230], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[386, 230], [385, 204], [393, 185], [379, 173], [386, 166], [382, 170], [377, 161], [371, 162], [367, 183], [368, 161]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0066_user_0014_scene_0008_cfg_0001_819112070044#477.jpg", + "gt": "[[386, 230], [385, 204], [393, 185], [379, 173], [386, 166], [382, 170], [377, 161], [371, 162], [367, 183], [368, 161]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0058_user_0015_scene_0003_cfg_0001_035622060973#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn off the power strips', and now you are performing subtask 'press the first button on the power socket.'\nBegin at [246, 130] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[246, 130], [249, 129], [246, 118], [235, 97], [240, 62], [233, 60], [235, 59], [232, 65], [236, 75], [236, 75]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0058_user_0015_scene_0003_cfg_0001_035622060973#0.jpg", + "gt": "[[246, 130], [249, 129], [246, 118], [235, 97], [240, 62], [233, 60], [235, 59], [232, 65], [236, 75], [236, 75]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0070_user_0020_scene_0003_cfg_0006_104122061602#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open a sliding window', and now you are performing subtask 'slide the right window.'\nFrom start point [477, 202], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[477, 202], [460, 198], [447, 201], [464, 205], [452, 204], [457, 202], [465, 181], [464, 166], [458, 157], [464, 156]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg6_task_0070_user_0020_scene_0003_cfg_0006_104122061602#528.jpg", + "gt": "[[477, 202], [460, 198], [447, 201], [464, 205], [452, 204], [457, 202], [465, 181], [464, 166], [458, 157], [464, 156]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg2_task_0037_user_0007_scene_0006_cfg_0002_105422061350#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'pick up the first block on the table, transfer the first block from the table to the top of the second block, place the first block on the second block, pick up the second block on the table.'\nBegin at [385, 157] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[385, 157], [340, 126], [334, 133], [324, 120], [331, 141], [324, 132], [319, 142], [322, 166], [316, 167], [316, 153]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg2_task_0037_user_0007_scene_0006_cfg_0002_105422061350#0.jpg", + "gt": "[[385, 157], [340, 126], [334, 133], [324, 120], [331, 141], [324, 132], [319, 142], [322, 166], [316, 167], [316, 153]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0048_user_0020_scene_0004_cfg_0007_104122064161#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'rotate the steering wheel clockwise', and now you are performing subtask 'twist the steering wheel clockwise, twist the steering wheel clockwise.'\nWith start location [393, 200], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[393, 200], [393, 206], [391, 210], [391, 212], [389, 213], [389, 210], [394, 192], [393, 193], [394, 197], [395, 198]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg7_task_0048_user_0020_scene_0004_cfg_0007_104122064161#225.jpg", + "gt": "[[393, 200], [393, 206], [391, 210], [391, 212], [389, 213], [389, 210], [394, 192], [393, 193], [394, 197], [395, 198]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg2_task_0077_user_0014_scene_0006_cfg_0002_105422061350#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stacking blocks (small Lego) randomly one at a time', and now you are performing subtask 'pick up the blue block on the table, transfer the blue block from the table to the grid center, place the blue block at the grid center.'\nYour initial coordinate is [306, 99]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[306, 99], [318, 108], [308, 113], [248, 103], [185, 83], [165, 62], [171, 76], [203, 98], [200, 104], [200, 104]]}" + } + ], + "images": "RH20T_cfg2_task_0077_user_0014_scene_0006_cfg_0002_105422061350#0", + "gt": "[[306, 99], [318, 108], [308, 113], [248, 103], [185, 83], [165, 62], [171, 76], [203, 98], [200, 104], [200, 104]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "68447_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'transfer the lid from the black pot to the blue pot', and now you are performing subtask 'transfer the lid from the black pot to the blue pot.'\nYou begin at [294.5, 97.5]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[294.5, 97.5], [290.5, 120.5], [276.5, 137.5], [222.5, 148.5], [189.5, 174.5], [187.5, 152.5], [196.5, 136.5], [190.5, 125.5], [229.5, 128.5], [241.5, 116.5]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/68447_exterior_image_1_left#0.jpg", + "gt": "[[294.5, 97.5], [290.5, 120.5], [276.5, 137.5], [222.5, 148.5], [189.5, 174.5], [187.5, 152.5], [196.5, 136.5], [190.5, 125.5], [229.5, 128.5], [241.5, 116.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0029_user_0020_scene_0010_cfg_0007_104122064161#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'grasp the handle and open the drawer', and now you are performing subtask 'grasp the handle and open the drawer.'\nYour initial coordinate is [337, 115]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[337, 115], [357, 133], [347, 130], [348, 134], [351, 128], [363, 123], [389, 133], [385, 199], [373, 111], [368, 105]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg7_task_0029_user_0020_scene_0010_cfg_0007_104122064161#0.jpg", + "gt": "[[337, 115], [357, 133], [347, 130], [348, 134], [351, 128], [363, 123], [389, 133], [385, 199], [373, 111], [368, 105]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0039_user_0007_scene_0003_cfg_0005_104122061850#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pour the water from one cup into another empty cup', and now you are performing subtask 'pour the water from one cup into another empty cup.'\nYour initial coordinate is [305, 50]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[305, 50], [340, 46], [361, 60], [365, 99], [357, 69], [366, 62], [347, 139], [345, 58], [372, 69], [374, 97]]}" + } + ], + "images": "RH20T_cfg5_task_0039_user_0007_scene_0003_cfg_0005_104122061850#0", + "gt": "[[305, 50], [340, 46], [361, 60], [365, 99], [357, 69], [366, 62], [347, 139], [345, 58], [372, 69], [374, 97]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0130_user_0014_scene_0004_cfg_0006_104122064161#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'plug in the bulb holder with a bulb to the socket and turn on the switch of the bulb', and now you are performing subtask 'insert the lamp holder into the socket, press the lamp holder button to turn on the light.'\nStarting at [373, 164], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[373, 164], [358, 182], [374, 157], [380, 137], [381, 124], [379, 113], [377, 110], [368, 104], [366, 104], [371, 107]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg6_task_0130_user_0014_scene_0004_cfg_0006_104122064161#287.jpg", + "gt": "[[373, 164], [358, 182], [374, 157], [380, 137], [381, 124], [379, 113], [377, 110], [368, 104], [366, 104], [371, 107]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "44324_exterior_image_2_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unstack the cans and put them beside each other', and now you are performing subtask 'place the second can next to the other cans.'\nThe trajectory starts at [143, 108]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[143, 108], [149, 106], [151, 109], [161, 96], [161, 99], [154, 101], [148, 97], [135, 99], [130, 99], [132, 97]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/44324_exterior_image_2_left#331.jpg", + "gt": "[[143, 108], [149, 106], [151, 109], [161, 96], [161, 99], [154, 101], [148, 97], [135, 99], [130, 99], [132, 97]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "84410_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'use a marker to write on the board', and now you are performing subtask 'use a marker to write on the board.'\nWith start location [160.5, 79.0], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[160.5, 79.0], [149.5, 95.0], [164.5, 134.0], [178.5, 89.0], [202.5, 80.0], [202.5, 71.0], [205.5, 78.0], [168.5, 97.0], [165.5, 131.0], [154.5, 114.0]]}" + } + ], + "images": "84410_exterior_image_1_left#0", + "gt": "[[160.5, 79.0], [149.5, 95.0], [164.5, 134.0], [178.5, 89.0], [202.5, 80.0], [202.5, 71.0], [205.5, 78.0], [168.5, 97.0], [165.5, 131.0], [154.5, 114.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0129_user_0020_scene_0009_cfg_0006_104122063633#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'plug in the bulb holder with a bulb to the socket', and now you are performing subtask 'plug in the bulb holder with a bulb to the socket.'\nStarting at [232, 119], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[232, 119], [216, 151], [220, 172], [182, 225], [139, 219], [154, 244], [143, 206], [151, 133], [182, 131], [200, 152]]}" + } + ], + "images": "RH20T_cfg6_task_0129_user_0020_scene_0009_cfg_0006_104122063633#0", + "gt": "[[232, 119], [216, 151], [220, 172], [182, 225], [139, 219], [154, 244], [143, 206], [151, 133], [182, 131], [200, 152]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0066_user_0014_scene_0005_cfg_0001_038522063145#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with large Megabloks for the nth time with n blocks', and now you are performing subtask 'place the second Megablock on the green base, pick up the third Megablock from the left side of the table, place the third Megablock on the green base.'\nStart at [437, 152]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[437, 152], [441, 139], [470, 129], [493, 129], [495, 142], [477, 105], [437, 100], [421, 111], [412, 139], [412, 139]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0066_user_0014_scene_0005_cfg_0001_038522063145#329.jpg", + "gt": "[[437, 152], [441, 139], [470, 129], [493, 129], [495, 142], [477, 105], [437, 100], [421, 111], [412, 139], [412, 139]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0002_user_0014_scene_0006_cfg_0006_104122061602#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pull out a napkin', and now you are performing subtask 'pick up a napkin from the surface, throw the toilet paper at the table.'\nYou start from [478, 160]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[478, 160], [480, 148], [479, 139], [483, 132], [491, 127], [489, 125], [490, 120], [493, 122], [491, 119], [489, 121]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg6_task_0002_user_0014_scene_0006_cfg_0006_104122061602#215.jpg", + "gt": "[[478, 160], [480, 148], [479, 139], [483, 132], [491, 127], [489, 125], [490, 120], [493, 122], [491, 119], [489, 121]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0010_user_0007_scene_0003_cfg_0005_105422061350#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'place the handset of the telephone on the corresponding phone cradle', and now you are performing subtask 'place the handset of the telephone on the corresponding phone cradle.'\nBegin at [273, 51] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[273, 51], [228, 123], [197, 141], [191, 218], [197, 138], [208, 113], [239, 85], [257, 93], [219, 117], [235, 89]]}" + } + ], + "images": "RH20T_cfg5_task_0010_user_0007_scene_0003_cfg_0005_105422061350#0", + "gt": "[[273, 51], [228, 123], [197, 141], [191, 218], [197, 138], [208, 113], [239, 85], [257, 93], [219, 117], [235, 89]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0013_user_0020_scene_0010_cfg_0007_104122061602#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'place the block on the scale', and now you are performing subtask 'place the big block on the scale, pick up the small block from the table, transfer the small block from the table to the big block, place the small block on the big block.'\nThe trajectory starts at [473, 171]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[473, 171], [492, 167], [501, 188], [502, 214], [489, 229], [503, 207], [504, 187], [482, 163], [507, 168], [504, 176]]}" + } + ], + "images": "RH20T_cfg7_task_0013_user_0020_scene_0010_cfg_0007_104122061602#248", + "gt": "[[473, 171], [492, 167], [501, 188], [502, 214], [489, 229], [503, 207], [504, 187], [482, 163], [507, 168], [504, 176]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0045_user_0014_scene_0007_cfg_0004_104122062823#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the brush from the table and place it on the pen rack', and now you are performing subtask 'pick up the brush from the table and place it on the pen rack.'\nYour initial coordinate is [243, 0]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[243, 0], [229, 1], [253, 47], [245, 67], [233, 74], [258, 87], [316, 0], [430, 0], [367, 0], [367, 0]]}" + } + ], + "images": "RH20T_cfg4_task_0045_user_0014_scene_0007_cfg_0004_104122062823#0", + "gt": "[[243, 0], [229, 1], [253, 47], [245, 67], [233, 74], [258, 87], [316, 0], [430, 0], [367, 0], [367, 0]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "78920_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close the top drawer', and now you are performing subtask 'close the top drawer.'\nStarting at [226, 157], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[226, 157], [222, 149], [220, 139], [220, 112], [222, 106], [226, 102], [228, 97], [226, 96], [222, 98], [215, 98]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/78920_exterior_image_1_left#0.jpg", + "gt": "[[226, 157], [222, 149], [220, 139], [220, 112], [222, 106], [226, 102], [228, 97], [226, 96], [222, 98], [215, 98]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "4818_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the cup slightly backward and to the right', and now you are performing subtask 'move the cup slightly backward and to the right.'\nStart at [144, 0]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[144, 0], [174, 42], [168, 56], [160, 44], [140, 58], [127, 81], [166, 86], [164, 76], [124, 9], [130, 12]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/4818_exterior_image_1_left#0.jpg", + "gt": "[[144, 0], [174, 42], [168, 56], [160, 44], [140, 58], [127, 81], [166, 86], [164, 76], [124, 9], [130, 12]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "35291_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the top drawer of the bottom cabinet', and now you are performing subtask 'open the top drawer of the bottom cabinet.'\nThe trajectory starts at [132, 95]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[132, 95], [114, 98], [62, 122], [59, 130], [62, 148], [96, 148], [61, 173], [53, 165], [50, 152], [81, 122]]}" + } + ], + "images": "35291_exterior_image_1_left#0", + "gt": "[[132, 95], [114, 98], [62, 122], [59, 130], [62, 148], [96, 148], [61, 173], [53, 165], [50, 152], [81, 122]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0096_user_0014_scene_0008_cfg_0004_038522062288#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take something out of a drawer', and now you are performing subtask 'pull the drawer handle to open the drawer, pull the drawer handle to open the drawer.'\nYour initial coordinate is [235, 120]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[235, 120], [240, 101], [172, 104], [190, 99], [189, 134], [256, 149], [230, 149], [238, 166], [264, 172], [234, 126]]}" + } + ], + "images": "RH20T_cfg4_task_0096_user_0014_scene_0008_cfg_0004_038522062288#0", + "gt": "[[235, 120], [240, 101], [172, 104], [190, 99], [189, 134], [256, 149], [230, 149], [238, 166], [264, 172], [234, 126]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg3_task_0003_user_0016_scene_0002_cfg_0003_104122062295#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the three buttons in sequence', and now you are performing subtask 'press the green button on the right, press the green button in the middle.'\nYour initial coordinate is [162, 86]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[162, 86], [181, 94], [211, 119], [214, 119], [210, 126], [229, 134], [244, 145], [245, 152], [239, 177], [244, 149]]}" + } + ], + "images": "RH20T_cfg3_task_0003_user_0016_scene_0002_cfg_0003_104122062295#152", + "gt": "[[162, 86], [181, 94], [211, 119], [214, 119], [210, 126], [229, 134], [244, 145], [245, 152], [239, 177], [244, 149]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "55114_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'fold the cloth, turn the faucet counterclockwise', and now you are performing subtask 'fold the cloth on the cloth.'\nYou begin at [96.0, 5.0]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[96.0, 5.0], [139.0, 86.0], [134.0, 87.0], [136.0, 92.0], [149.0, 108.0], [137.0, 96.0], [127.0, 100.0], [129.0, 110.0], [123.0, 105.0], [153.0, 105.0]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/55114_exterior_image_1_left#0.jpg", + "gt": "[[96.0, 5.0], [139.0, 86.0], [134.0, 87.0], [136.0, 92.0], [149.0, 108.0], [137.0, 96.0], [127.0, 100.0], [129.0, 110.0], [123.0, 105.0], [153.0, 105.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "16021_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the white lid from the container and put it on the table', and now you are performing subtask 'remove the white lid from the container and put it on the table.'\nStarting at [64, 53], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[64, 53], [155, 75], [144, 107], [140, 89], [152, 93], [138, 64], [121, 70], [114, 91], [125, 106], [114, 78]]}" + } + ], + "images": "16021_exterior_image_2_left#0", + "gt": "[[64, 53], [155, 75], [144, 107], [140, 89], [152, 93], [138, 64], [121, 70], [114, 91], [125, 106], [114, 78]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "70193_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the lid from the blue pot and place it on the table', and now you are performing subtask 'remove the lid from the blue pot and place it on the table.'\nFrom start point [237.0, 27.0], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[237.0, 27.0], [196.0, 18.0], [185.0, 9.0], [167.0, 32.0], [174.0, 45.0], [159.0, 63.0], [149.0, 65.0], [155.0, 58.0], [172.0, 59.0], [194.0, 30.0]]}" + } + ], + "images": "70193_exterior_image_1_left#0", + "gt": "[[237.0, 27.0], [196.0, 18.0], [185.0, 9.0], [167.0, 32.0], [174.0, 45.0], [159.0, 63.0], [149.0, 65.0], [155.0, 58.0], [172.0, 59.0], [194.0, 30.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0013_user_0010_scene_0002_cfg_0004_036422060909#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'place the block on the scale', and now you are performing subtask 'place the block on the scale.'\nFrom start point [337, 78], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[337, 78], [317, 106], [243, 128], [179, 171], [178, 189], [228, 157], [325, 158], [316, 133], [282, 121], [301, 121]]}" + } + ], + "images": "RH20T_cfg4_task_0013_user_0010_scene_0002_cfg_0004_036422060909#0", + "gt": "[[337, 78], [317, 106], [243, 128], [179, 171], [178, 189], [228, 157], [325, 158], [316, 133], [282, 121], [301, 121]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0096_user_0007_scene_0003_cfg_0005_036422060215#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the drawer and place the cube on the table', and now you are performing subtask 'pull the handle of the drawer to pull open the drawer.'\nYour starting position is [286, 108]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[286, 108], [287, 105], [290, 108], [292, 107], [285, 114], [287, 136], [285, 140], [281, 133], [260, 115], [259, 101]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0096_user_0007_scene_0003_cfg_0005_036422060215#0.jpg", + "gt": "[[286, 108], [287, 105], [290, 108], [292, 107], [285, 114], [287, 136], [285, 140], [281, 133], [260, 115], [259, 101]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "72764_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the switch on the breakfast machine', and now you are performing subtask 'press the switch on the breakfast machine.'\nYou begin at [156, 77]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[156, 77], [160, 82], [192, 96], [189, 93], [190, 95], [199, 91], [211, 93], [235, 90], [215, 84], [206, 68]]}" + } + ], + "images": "72764_exterior_image_2_left#0", + "gt": "[[156, 77], [160, 82], [192, 96], [189, 93], [190, 95], [199, 91], [211, 93], [235, 90], [215, 84], [206, 68]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0003_user_0014_scene_0010_cfg_0006_104122063633#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press three buttons from left to right in sequence', and now you are performing subtask 'press the green button in the middle, press the yellow button at the top.'\nYou begin at [193, 135]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[193, 135], [185, 135], [180, 143], [180, 151], [175, 172], [173, 160], [176, 149], [180, 149], [180, 148], [178, 151]]}" + } + ], + "images": "RH20T_cfg6_task_0003_user_0014_scene_0010_cfg_0006_104122063633#178", + "gt": "[[193, 135], [185, 135], [180, 143], [180, 151], [175, 172], [173, 160], [176, 149], [180, 149], [180, 148], [178, 151]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0118_user_0010_scene_0004_cfg_0005_104122063678#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn the water tap handle counterclockwise', and now you are performing subtask 'turn the water tap handle counterclockwise.'\nStarting at [213, 120], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[213, 120], [256, 155], [261, 186], [299, 193], [291, 230], [267, 241], [261, 255], [267, 286], [272, 196], [263, 150]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0118_user_0010_scene_0004_cfg_0005_104122063678#0.jpg", + "gt": "[[213, 120], [256, 155], [261, 186], [299, 193], [291, 230], [267, 241], [261, 255], [267, 286], [272, 196], [263, 150]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0129_user_0020_scene_0009_cfg_0006_104122064161#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'plug in the bulb holder with a bulb to the socket', and now you are performing subtask 'plug in the bulb holder with a bulb to the socket.'\nFrom start point [338, 111], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[338, 111], [351, 89], [364, 102], [384, 94], [396, 99], [385, 129], [395, 87], [414, 179], [414, 129], [365, 126]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg6_task_0129_user_0020_scene_0009_cfg_0006_104122064161#0.jpg", + "gt": "[[338, 111], [351, 89], [364, 102], [384, 94], [396, 99], [385, 129], [395, 87], [414, 179], [414, 129], [365, 126]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0015_user_0007_scene_0006_cfg_0005_104122061850#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'play the drum', and now you are performing subtask 'play the drum.'\nThe trajectory starts at [311, 50]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[311, 50], [332, 52], [347, 73], [359, 156], [352, 138], [381, 151], [394, 132], [387, 112], [366, 163], [369, 93]]}" + } + ], + "images": "RH20T_cfg5_task_0015_user_0007_scene_0006_cfg_0005_104122061850#0", + "gt": "[[311, 50], [332, 52], [347, 73], [359, 156], [352, 138], [381, 151], [394, 132], [387, 112], [366, 163], [369, 93]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "24049_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'fold the green towel', and now you are performing subtask 'fold the green towel.'\nStarting at [277, 2], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[277, 2], [268, 42], [252, 74], [235, 81], [240, 92], [229, 74], [230, 62], [239, 67], [227, 79], [220, 58]]}" + } + ], + "images": "24049_exterior_image_2_left#0", + "gt": "[[277, 2], [268, 42], [252, 74], [235, 81], [240, 92], [229, 74], [230, 62], [239, 67], [227, 79], [220, 58]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "2362_exterior_image_2_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the wallet from the table and put it in the black bag', and now you are performing subtask 'place the wallet in the black bag.'\nYour initial coordinate is [191, 130]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[191, 130], [181, 123], [185, 138], [171, 139], [182, 73], [165, 47], [182, 51], [174, 64], [168, 43], [178, 66]]}" + } + ], + "images": "2362_exterior_image_2_left#473", + "gt": "[[191, 130], [181, 123], [185, 138], [171, 139], [182, 73], [165, 47], [182, 51], [174, 64], [168, 43], [178, 66]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "66471_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pull the towel onto the table, pick up the towel from the table and put it on the tripod', and now you are performing subtask 'pull the towel to the table.'\nBegin at [320, 38] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[320, 38], [278, 44], [249, 67], [249, 74], [256, 57], [261, 53], [270, 53], [285, 60], [276, 97], [286, 80]]}" + } + ], + "images": "66471_exterior_image_2_left#0", + "gt": "[[320, 38], [278, 44], [249, 67], [249, 74], [256, 57], [261, 53], [270, 53], [285, 60], [276, 97], [286, 80]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "1294_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the snack from the sink and place it on the counter', and now you are performing subtask 'pick up the snack from the sink and place it on the counter.'\nYour initial coordinate is [225, 84]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[225, 84], [233, 94], [230, 116], [234, 131], [223, 138], [216, 111], [200, 127], [196, 138], [200, 117], [215, 107]]}" + } + ], + "images": "1294_exterior_image_2_left#0", + "gt": "[[225, 84], [233, 94], [230, 116], [234, 131], [223, 138], [216, 111], [200, 127], [196, 138], [200, 117], [215, 107]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0009_user_0010_scene_0004_cfg_0004_038522062288#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take out a Hanoi block and place it on the table', and now you are performing subtask 'take out a Hanoi block and place it on the table.'\nYou begin at [232, 120]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[232, 120], [214, 125], [240, 151], [200, 191], [219, 190], [212, 182], [218, 183], [272, 219], [194, 197], [152, 217]]}" + } + ], + "images": "RH20T_cfg4_task_0009_user_0010_scene_0004_cfg_0004_038522062288#0", + "gt": "[[232, 120], [214, 125], [240, 151], [200, 191], [219, 190], [212, 182], [218, 183], [272, 219], [194, 197], [152, 217]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "15165_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'push in the first rod on the foosball table', and now you are performing subtask 'push in the first rod on the foosball table.'\nYour starting position is [206, 54]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[206, 54], [161, 78], [167, 77], [149, 104], [154, 106], [153, 108], [154, 101], [142, 85], [155, 59], [163, 50]]}" + } + ], + "images": "15165_exterior_image_2_left#0", + "gt": "[[206, 54], [161, 78], [167, 77], [149, 104], [154, 106], [153, 108], [154, 101], [142, 85], [155, 59], [163, 50]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0096_user_0015_scene_0005_cfg_0001_038522062547#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the block out of the drawer and put it on the table', and now you are performing subtask 'pull the drawer handle to open the drawer, pick up the block from the drawer, transfer the block from the drawer to the tabletop, place the block on the tabletop.'\nFrom start point [504, 58], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[504, 58], [496, 52], [476, 60], [459, 86], [485, 58], [482, 46], [494, 82], [500, 146], [480, 201], [480, 201]]}" + } + ], + "images": "RH20T_cfg1_task_0096_user_0015_scene_0005_cfg_0001_038522062547#267", + "gt": "[[504, 58], [496, 52], [476, 60], [459, 86], [485, 58], [482, 46], [494, 82], [500, 146], [480, 201], [480, 201]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "29854_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the black drawer', and now you are performing subtask 'open the black drawer.'\nWith start location [138, 150], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[138, 150], [162, 120], [191, 97], [195, 84], [205, 93], [201, 83], [210, 96], [178, 110], [180, 87], [172, 93]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/29854_exterior_image_2_left#0.jpg", + "gt": "[[138, 150], [162, 120], [191, 97], [195, 84], [205, 93], [201, 83], [210, 96], [178, 110], [180, 87], [172, 93]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "85110_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the black button on the right side of the board', and now you are performing subtask 'press the black button on the right side of the board.'\nWith start location [150, 1], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[150, 1], [206, 33], [198, 68], [219, 85], [234, 140], [247, 142], [232, 141], [238, 150], [253, 113], [239, 79]]}" + } + ], + "images": "85110_exterior_image_1_left#0", + "gt": "[[150, 1], [206, 33], [198, 68], [219, 85], [234, 140], [247, 142], [232, 141], [238, 150], [253, 113], [239, 79]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "42322_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the pen from the cup and put it on the table', and now you are performing subtask 'remove the pen from the cup and put it on the table.'\nYou begin at [4.5, 41.5]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[4.5, 41.5], [114.5, 62.5], [140.5, 83.5], [137.5, 87.5], [133.5, 59.5], [141.5, 45.5], [153.5, 41.5], [162.5, 51.5], [158.5, 79.5], [158.5, 79.5]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/42322_exterior_image_1_left#0.jpg", + "gt": "[[4.5, 41.5], [114.5, 62.5], [140.5, 83.5], [137.5, 87.5], [133.5, 59.5], [141.5, 45.5], [153.5, 41.5], [162.5, 51.5], [158.5, 79.5], [158.5, 79.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "69043_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the green pen from the maroon mug', and now you are performing subtask 'remove the green pen from the maroon mug.'\nStart at [70, 0]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[70, 0], [120, 32], [138, 55], [151, 62], [162, 87], [153, 54], [136, 50], [132, 75], [136, 86], [140, 39]]}" + } + ], + "images": "69043_exterior_image_1_left#0", + "gt": "[[70, 0], [120, 32], [138, 55], [151, 62], [162, 87], [153, 54], [136, 50], [132, 75], [136, 86], [140, 39]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "40510_exterior_image_2_left#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the glue stick from the cup, place it on the box, then on the table, back into the cup, and lastly on the table', and now you are performing subtask 'twist glue stick clockwise and place it on the table.'\nStart at [182, 89]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[182, 89], [189, 83], [183, 87], [184, 95], [192, 74], [181, 68], [175, 67], [178, 68], [175, 68], [175, 86]]}" + } + ], + "images": "40510_exterior_image_2_left#290", + "gt": "[[182, 89], [189, 83], [183, 87], [184, 95], [192, 74], [181, 68], [175, 67], [178, 68], [175, 68], [175, 86]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "17495_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the plastic to the top part of the table', and now you are performing subtask 'move the plastic to the top part of the table.'\nWith start location [128, 102], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[128, 102], [162, 129], [150, 149], [148, 115], [167, 106], [174, 111], [173, 102], [116, 115], [109, 122], [109, 122]]}" + } + ], + "images": "17495_exterior_image_2_left#0", + "gt": "[[128, 102], [162, 129], [150, 149], [148, 115], [167, 106], [174, 111], [173, 102], [116, 115], [109, 122], [109, 122]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0023_user_0014_scene_0002_cfg_0001_035622060973#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn on the power strip by pressing the button', and now you are performing subtask 'turn on the power strip by pressing the button.'\nStart at [246, 130]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[246, 130], [248, 148], [249, 145], [270, 154], [272, 172], [279, 180], [276, 180], [282, 180], [278, 177], [274, 161]]}" + } + ], + "images": "RH20T_cfg1_task_0023_user_0014_scene_0002_cfg_0001_035622060973#0", + "gt": "[[246, 130], [248, 148], [249, 145], [270, 154], [272, 172], [279, 180], [276, 180], [282, 180], [278, 177], [274, 161]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "24671_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'rotate the tap nozzle clockwise', and now you are performing subtask 'rotate the tap nozzle clockwise.'\nThe trajectory starts at [223, 2]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[223, 2], [237, 61], [221, 68], [230, 61], [216, 58], [213, 45], [217, 43], [197, 44], [187, 47], [193, 49]]}" + } + ], + "images": "24671_exterior_image_1_left#0", + "gt": "[[223, 2], [237, 61], [221, 68], [230, 61], [216, 58], [213, 45], [217, 43], [197, 44], [187, 47], [193, 49]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "16095_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pour the contents in the red bowl into the silver bowl', and now you are performing subtask 'pour the contents in the red bowl into the silver bowl.'\nWith start location [135, 0], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[135, 0], [143, 102], [145, 89], [174, 73], [213, 72], [196, 57], [138, 93], [156, 98], [150, 62], [163, 41]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/16095_exterior_image_1_left#0.jpg", + "gt": "[[135, 0], [143, 102], [145, 89], [174, 73], [213, 72], [196, 57], [138, 93], [156, 98], [150, 62], [163, 41]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0071_user_0020_scene_0007_cfg_0006_104122063633#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close a sliding window', and now you are performing subtask 'push the handle of the sliding window to close the lower window.'\nYour starting position is [217, 134]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[217, 134], [221, 153], [229, 157], [216, 144], [210, 145], [222, 153], [219, 135], [238, 138], [239, 132], [239, 132]]}" + } + ], + "images": "RH20T_cfg6_task_0071_user_0020_scene_0007_cfg_0006_104122063633#316", + "gt": "[[217, 134], [221, 153], [229, 157], [216, 144], [210, 145], [222, 153], [219, 135], [238, 138], [239, 132], [239, 132]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "21108_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the cloth on the table', and now you are performing subtask 'put the cloth on the table.'\nYou begin at [85, 68]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[85, 68], [128, 67], [139, 70], [140, 73], [138, 81], [115, 77], [106, 91], [99, 98], [93, 101], [97, 92]]}" + } + ], + "images": "21108_exterior_image_2_left#0", + "gt": "[[85, 68], [128, 67], [139, 70], [140, 73], [138, 81], [115, 77], [106, 91], [99, 98], [93, 101], [97, 92]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0009_user_0010_scene_0006_cfg_0004_104122062823#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take out a Hanoi block and throw it aside', and now you are performing subtask 'take out a Hanoi block and throw it aside.'\nBegin at [243, 0] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[243, 0], [269, 0], [247, 10], [274, 25], [280, 66], [279, 0], [227, 31], [224, 55], [243, 14], [305, 0]]}" + } + ], + "images": "RH20T_cfg4_task_0009_user_0010_scene_0006_cfg_0004_104122062823#0", + "gt": "[[243, 0], [269, 0], [247, 10], [274, 25], [280, 66], [279, 0], [227, 31], [224, 55], [243, 14], [305, 0]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "16826_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'sliding cover', and now you are performing subtask 'sliding cover.'\nWith start location [93, 76], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[93, 76], [161, 31], [190, 19], [183, 28], [199, 36], [208, 74], [203, 106], [198, 109], [202, 95], [197, 69]]}" + } + ], + "images": "16826_exterior_image_2_left#0", + "gt": "[[93, 76], [161, 31], [190, 19], [183, 28], [199, 36], [208, 74], [203, 106], [198, 109], [202, 95], [197, 69]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0067_user_0007_scene_0004_cfg_0004_104122062823#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press a button from top to bottom', and now you are performing subtask 'press a button from top to bottom.'\nYou start from [291, 0]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[291, 0], [256, 2], [245, 41], [272, 56], [244, 38], [263, 53], [252, 65], [260, 58], [267, 68], [255, 59]]}" + } + ], + "images": "RH20T_cfg4_task_0067_user_0007_scene_0004_cfg_0004_104122062823#0", + "gt": "[[291, 0], [256, 2], [245, 41], [272, 56], [244, 38], [263, 53], [252, 65], [260, 58], [267, 68], [255, 59]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "20709_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pour the contents of the cup into the bowl', and now you are performing subtask 'pour the contents of the cup into the bowl.'\nStart at [171, 150]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[171, 150], [173, 125], [151, 93], [123, 83], [133, 106], [153, 117], [145, 131], [128, 124], [130, 112], [140, 123]]}" + } + ], + "images": "20709_exterior_image_2_left#0", + "gt": "[[171, 150], [173, 125], [151, 93], [123, 83], [133, 106], [153, 117], [145, 131], [128, 124], [130, 112], [140, 123]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0057_user_0007_scene_0002_cfg_0005_037522062165#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press a row of four power strip buttons to turn on the power strips', and now you are performing subtask 'press the third button on the power socket, press the fourth button on the power socket.'\nThe trajectory starts at [265, 201]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[265, 201], [258, 198], [254, 199], [255, 203], [257, 198], [271, 186], [269, 187], [274, 177], [275, 172], [270, 148]]}" + } + ], + "images": "RH20T_cfg5_task_0057_user_0007_scene_0002_cfg_0005_037522062165#587", + "gt": "[[265, 201], [258, 198], [254, 199], [255, 203], [257, 198], [271, 186], [269, 187], [274, 177], [275, 172], [270, 148]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg2_task_0096_user_0007_scene_0005_cfg_0002_104422070044#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take something out of the drawer, put it on the table', and now you are performing subtask 'take something out of the drawer, put it on the table.'\nWith start location [271, 189], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[271, 189], [316, 179], [308, 171], [288, 169], [279, 176], [279, 185], [285, 161], [309, 181], [317, 218], [317, 198]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg2_task_0096_user_0007_scene_0005_cfg_0002_104422070044#0.jpg", + "gt": "[[271, 189], [316, 179], [308, 171], [288, 169], [279, 176], [279, 185], [285, 161], [309, 181], [317, 218], [317, 198]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "6570_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the top right cabinet door', and now you are performing subtask 'open the top right cabinet door.'\nBegin at [165.0, 127.5] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[165.0, 127.5], [144.0, 75.5], [145.0, 55.5], [138.0, 35.5], [144.0, 18.5], [165.0, 18.5], [161.0, 20.5], [154.0, 14.5], [152.0, 26.5], [160.0, 49.5]]}" + } + ], + "images": "6570_exterior_image_1_left#0", + "gt": "[[165.0, 127.5], [144.0, 75.5], [145.0, 55.5], [138.0, 35.5], [144.0, 18.5], [165.0, 18.5], [161.0, 20.5], [154.0, 14.5], [152.0, 26.5], [160.0, 49.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0081_user_0010_scene_0001_cfg_0001_035622060973#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the leg of the glasses (with one hand)', and now you are performing subtask 'pull the leg of the glasses outward.'\nBegin at [242, 133] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[242, 133], [249, 151], [262, 161], [269, 182], [273, 179], [275, 183], [273, 176], [269, 175], [266, 178], [268, 176]]}" + } + ], + "images": "RH20T_cfg1_task_0081_user_0010_scene_0001_cfg_0001_035622060973#0", + "gt": "[[242, 133], [249, 151], [262, 161], [269, 182], [273, 179], [275, 183], [273, 176], [269, 175], [266, 178], [268, 176]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0092_user_0010_scene_0009_cfg_0001_038522062547#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn the hands of a clock', and now you are performing subtask 'turn the hands of a clock.'\nYou start from [404, 127]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[404, 127], [392, 110], [399, 119], [432, 111], [442, 127], [432, 132], [389, 127], [375, 99], [423, 116], [432, 108]]}" + } + ], + "images": "RH20T_cfg1_task_0092_user_0010_scene_0009_cfg_0001_038522062547#0", + "gt": "[[404, 127], [392, 110], [399, 119], [432, 111], [442, 127], [432, 132], [389, 127], [375, 99], [423, 116], [432, 108]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "24360_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the marker in the mug', and now you are performing subtask 'put the marker in the mug.'\nBegin at [164, 2] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[164, 2], [154, 40], [179, 88], [174, 99], [217, 39], [223, 44], [211, 59], [220, 73], [210, 73], [210, 51]]}" + } + ], + "images": "24360_exterior_image_1_left#0", + "gt": "[[164, 2], [154, 40], [179, 88], [174, 99], [217, 39], [223, 44], [211, 59], [220, 73], [210, 73], [210, 51]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0066_user_0014_scene_0005_cfg_0001_038522062547#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with large Megabloks for the nth time with n blocks', and now you are performing subtask 'place the third Megablock on the green base, pick up the nth Megablock from the left side of the table, place the nth Megablock on the green base.'\nStarting at [384, 155], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[384, 155], [387, 147], [379, 136], [458, 184], [457, 178], [451, 182], [442, 150], [403, 109], [365, 105], [358, 117]]}" + } + ], + "images": "RH20T_cfg1_task_0066_user_0014_scene_0005_cfg_0001_038522062547#462", + "gt": "[[384, 155], [387, 147], [379, 136], [458, 184], [457, 178], [451, 182], [442, 150], [403, 109], [365, 105], [358, 117]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0105_user_0007_scene_0014_cfg_0004_104122062823#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the object from the table and move it upward', and now you are performing subtask 'pick up the object from the table.'\nYou begin at [279, 50]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[279, 50], [287, 70], [278, 82], [279, 115], [289, 122], [289, 83], [248, 14], [248, 0], [57, 0], [256, 0]]}" + } + ], + "images": "RH20T_cfg4_task_0105_user_0007_scene_0014_cfg_0004_104122062823#128", + "gt": "[[279, 50], [287, 70], [278, 82], [279, 115], [289, 122], [289, 83], [248, 14], [248, 0], [57, 0], [256, 0]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "39383_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the mug forward', and now you are performing subtask 'move the mug forward.'\nBegin at [192, 2] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[192, 2], [189, 9], [195, 6], [193, 12], [178, 22], [168, 38], [166, 63], [159, 36], [150, 47], [150, 34]]}" + } + ], + "images": "39383_exterior_image_1_left#0", + "gt": "[[192, 2], [189, 9], [195, 6], [193, 12], [178, 22], [168, 38], [166, 63], [159, 36], [150, 47], [150, 34]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "57480_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the cup backwards, empty the bowl then sweep the table', and now you are performing subtask 'place the bowl on the countertop.'\nBegin at [196, 90] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[196, 90], [191, 114], [212, 116], [209, 101], [185, 90], [198, 99], [211, 94], [215, 103], [198, 89], [172, 99]]}" + } + ], + "images": "57480_exterior_image_1_left#139", + "gt": "[[196, 90], [191, 114], [212, 116], [209, 101], [185, 90], [198, 99], [211, 94], [215, 103], [198, 89], [172, 99]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "67833_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the cylindrical object inside the box', and now you are performing subtask 'place the cylindrical object into the box.'\nYour starting position is [143, 84]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[143, 84], [142, 68], [149, 58], [171, 68], [176, 83], [165, 95], [151, 73], [139, 91], [137, 76], [143, 69]]}" + } + ], + "images": "67833_exterior_image_1_left#109", + "gt": "[[143, 84], [142, 68], [149, 58], [171, 68], [176, 83], [165, 95], [151, 73], [139, 91], [137, 76], [143, 69]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg2_task_0041_user_0007_scene_0009_cfg_0002_036422060215#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'clean the tabletop with a sponge', and now you are performing subtask 'clean the tabletop with a sponge.'\nYou start from [349, 255]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[349, 255], [368, 263], [374, 226], [396, 214], [437, 241], [437, 253], [423, 246], [424, 257], [411, 250], [358, 266]]}" + } + ], + "images": "RH20T_cfg2_task_0041_user_0007_scene_0009_cfg_0002_036422060215#0", + "gt": "[[349, 255], [368, 263], [374, 226], [396, 214], [437, 241], [437, 253], [423, 246], [424, 257], [411, 250], [358, 266]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "35690_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the black and yellow bottle to the left, move the water bottle to the right, then move the black and yellow bottle closer to the water bottle', and now you are performing subtask 'push the black and yellow bottle next to the water bottle.'\nThe trajectory starts at [142, 115]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[142, 115], [149, 91], [163, 85], [188, 92], [195, 102], [178, 106], [204, 104], [196, 105], [201, 75], [176, 82]]}" + } + ], + "images": "35690_exterior_image_1_left#262", + "gt": "[[142, 115], [149, 91], [163, 85], [188, 92], [195, 102], [178, 106], [204, 104], [196, 105], [201, 75], [176, 82]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0035_user_0016_scene_0001_cfg_0004_104122063550#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up a small block', and now you are performing subtask 'pick up a small block.'\nBegin at [280, 185] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[280, 185], [310, 196], [332, 212], [316, 217], [311, 229], [343, 228], [346, 230], [341, 231], [337, 223], [336, 227]]}" + } + ], + "images": "RH20T_cfg4_task_0035_user_0016_scene_0001_cfg_0004_104122063550#0", + "gt": "[[280, 185], [310, 196], [332, 212], [316, 217], [311, 229], [343, 228], [346, 230], [341, 231], [337, 223], [336, 227]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0041_user_0007_scene_0006_cfg_0005_037522062165#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'clean the tabletop with a sponge', and now you are performing subtask 'pick up the sponge on the tabletop, slide the sponge on the tabletop to clean the surface.'\nYou begin at [289, 152]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[289, 152], [307, 213], [306, 248], [290, 292], [298, 307], [301, 300], [248, 257], [240, 228], [243, 240], [260, 246]]}" + } + ], + "images": "RH20T_cfg5_task_0041_user_0007_scene_0006_cfg_0005_037522062165#0", + "gt": "[[289, 152], [307, 213], [306, 248], [290, 292], [298, 307], [301, 300], [248, 257], [240, 228], [243, 240], [260, 246]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "48516_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the pen in the cup', and now you are performing subtask 'put the pen in the cup.'\nYour initial coordinate is [222, 83]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[222, 83], [208, 78], [205, 89], [207, 98], [217, 104], [216, 115], [243, 100], [231, 99], [228, 114], [223, 107]]}" + } + ], + "images": "48516_exterior_image_2_left#0", + "gt": "[[222, 83], [208, 78], [205, 89], [207, 98], [217, 104], [216, 115], [243, 100], [231, 99], [228, 114], [223, 107]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "45188_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'fold the white towel once', and now you are performing subtask 'press the towel on the tabletop.'\nStart at [190, 124]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[190, 124], [187, 125], [180, 133], [175, 148], [182, 141], [192, 135], [194, 132], [194, 128], [192, 124], [194, 127]]}" + } + ], + "images": "45188_exterior_image_1_left#161", + "gt": "[[190, 124], [187, 125], [180, 133], [175, 148], [182, 141], [192, 135], [194, 132], [194, 128], [192, 124], [194, 127]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0005_user_0004_scene_0007_cfg_0001_039422060546#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'push the wooden block to the left side of the table', and now you are performing subtask 'push the wooden block to the left side of the table.'\nYour starting position is [255, 127]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[255, 127], [273, 139], [261, 139], [329, 153], [323, 157], [337, 171], [375, 179], [375, 187], [352, 181], [380, 185]]}" + } + ], + "images": "RH20T_cfg1_task_0005_user_0004_scene_0007_cfg_0001_039422060546#0", + "gt": "[[255, 127], [273, 139], [261, 139], [329, 153], [323, 157], [337, 171], [375, 179], [375, 187], [352, 181], [380, 185]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0039_user_0014_scene_0008_cfg_0007_104122064161#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pour the water from one cup into another empty cup', and now you are performing subtask 'pour the water from one cup into another empty cup.'\nWith start location [337, 115], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[337, 115], [365, 154], [377, 219], [369, 226], [364, 118], [336, 81], [327, 83], [330, 114], [331, 93], [343, 96]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg7_task_0039_user_0014_scene_0008_cfg_0007_104122064161#0.jpg", + "gt": "[[337, 115], [365, 154], [377, 219], [369, 226], [364, 118], [336, 81], [327, 83], [330, 114], [331, 93], [343, 96]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "11748_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the white plate from the dishwasher and place it on top of the white plates on the counter', and now you are performing subtask 'remove the white plate from the dishwasher and place it on top of the white plates on the counter.'\nWith start location [187, 53], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[187, 53], [124, 83], [100, 137], [115, 152], [133, 99], [142, 90], [142, 101], [143, 81], [139, 99], [122, 98]]}" + } + ], + "images": "11748_exterior_image_1_left#0", + "gt": "[[187, 53], [124, 83], [100, 137], [115, 152], [133, 99], [142, 90], [142, 101], [143, 81], [139, 99], [122, 98]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "14324_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the black masking tape on the cream plate', and now you are performing subtask 'put the black masking tape on the cream plate.'\nYour starting position is [154.0, 1.0]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[154.0, 1.0], [161.0, 52.0], [169.0, 67.0], [162.0, 53.0], [146.0, 48.0], [97.0, 82.0], [91.0, 82.0], [93.0, 78.0], [109.0, 78.0], [108.0, 74.0]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/14324_exterior_image_1_left#0.jpg", + "gt": "[[154.0, 1.0], [161.0, 52.0], [169.0, 67.0], [162.0, 53.0], [146.0, 48.0], [97.0, 82.0], [91.0, 82.0], [93.0, 78.0], [109.0, 78.0], [108.0, 74.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0064_user_0015_scene_0008_cfg_0001_035622060973#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the roll of paper to the shelf', and now you are performing subtask 'move the roll of paper to the shelf.'\nThe trajectory starts at [246, 130]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[246, 130], [329, 181], [336, 173], [309, 188], [234, 204], [235, 194], [242, 206], [200, 219], [209, 202], [186, 150]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0064_user_0015_scene_0008_cfg_0001_035622060973#0.jpg", + "gt": "[[246, 130], [329, 181], [336, 173], [309, 188], [234, 204], [235, 194], [242, 206], [200, 219], [209, 202], [186, 150]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "9787_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the pencil to the left side of the table', and now you are performing subtask 'move the pencil to the left side of the table.'\nYour starting position is [155.0, 1.5]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[155.0, 1.5], [163.0, 10.5], [173.0, 31.5], [183.0, 88.5], [172.0, 69.5], [164.0, 65.5], [151.0, 72.5], [152.0, 79.5], [150.0, 63.5], [152.0, 66.5]]}" + } + ], + "images": "9787_exterior_image_1_left#0", + "gt": "[[155.0, 1.5], [163.0, 10.5], [173.0, 31.5], [183.0, 88.5], [172.0, 69.5], [164.0, 65.5], [151.0, 72.5], [152.0, 79.5], [150.0, 63.5], [152.0, 66.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "81862_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stretch out the ends of the charger at opposite sides', and now you are performing subtask 'pull the charger to the left.'\nThe trajectory starts at [307, 0]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[307, 0], [273, 9], [163, 76], [168, 84], [189, 69], [225, 77], [219, 63], [209, 64], [214, 86], [199, 90]]}" + } + ], + "images": "81862_exterior_image_1_left#0", + "gt": "[[307, 0], [273, 9], [163, 76], [168, 84], [189, 69], [225, 77], [219, 63], [209, 64], [214, 86], [199, 90]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "79133_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the blocks one on top of the other', and now you are performing subtask 'put the blocks one on top of the other.'\nBegin at [183, 58] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[183, 58], [182, 101], [180, 104], [175, 106], [175, 112], [175, 89], [179, 84], [182, 85], [180, 92], [180, 89]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/79133_exterior_image_1_left#0.jpg", + "gt": "[[183, 58], [182, 101], [180, 104], [175, 106], [175, 112], [175, 89], [179, 84], [182, 85], [180, 92], [180, 89]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "47683_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'arrange the small pillows on the right side of the couch', and now you are performing subtask 'pick up another pillow from above.'\nYour initial coordinate is [211, 113]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[211, 113], [203, 103], [185, 96], [175, 103], [210, 107], [200, 104], [196, 99], [205, 103], [198, 95], [198, 95]]}" + } + ], + "images": "47683_exterior_image_1_left#200", + "gt": "[[211, 113], [203, 103], [185, 96], [175, 103], [210, 107], [200, 104], [196, 99], [205, 103], [198, 95], [198, 95]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "79712_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the marker in the mug cup', and now you are performing subtask 'put the marker in the mug cup.'\nStarting at [124.5, 46.5], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[124.5, 46.5], [150.5, 64.5], [156.5, 78.5], [153.5, 91.5], [163.5, 106.5], [163.5, 95.5], [172.5, 85.5], [168.5, 90.5], [172.5, 102.5], [161.5, 85.5]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/79712_exterior_image_1_left#0.jpg", + "gt": "[[124.5, 46.5], [150.5, 64.5], [156.5, 78.5], [153.5, 91.5], [163.5, 106.5], [163.5, 95.5], [172.5, 85.5], [168.5, 90.5], [172.5, 102.5], [161.5, 85.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "10503_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the white towel then set it down again', and now you are performing subtask 'place the white towel back on the table.'\nWith start location [225, 36], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[225, 36], [185, 49], [168, 72], [172, 80], [153, 84], [141, 107], [152, 47], [133, 104], [141, 113], [142, 94]]}" + } + ], + "images": "10503_exterior_image_2_left#0", + "gt": "[[225, 36], [185, 49], [168, 72], [172, 80], [153, 84], [141, 107], [152, 47], [133, 104], [141, 113], [142, 94]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0066_user_0014_scene_0008_cfg_0001_038522063145#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'putting a portion of the Lego blocks on the Lego baseplate', and now you are performing subtask 'pick up the red Lego brick from the table, transfer the red Lego brick from the table to the Lego base, insert the red Lego brick into the Lego base.'\nWith start location [441, 97], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[441, 97], [536, 150], [551, 179], [553, 169], [540, 181], [550, 172], [550, 158], [499, 148], [482, 170], [506, 144]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0066_user_0014_scene_0008_cfg_0001_038522063145#0.jpg", + "gt": "[[441, 97], [536, 150], [551, 179], [553, 169], [540, 181], [550, 172], [550, 158], [499, 148], [482, 170], [506, 144]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "36525_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'use the towel to wipe the left side of the armrest', and now you are performing subtask 'use the towel to wipe the left side of the armrest.'\nStart at [198, 68]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[198, 68], [164, 88], [151, 140], [199, 175], [156, 151], [184, 169], [160, 150], [179, 165], [173, 140], [173, 140]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/36525_exterior_image_1_left#0.jpg", + "gt": "[[198, 68], [164, 88], [151, 140], [199, 175], [156, 151], [184, 169], [160, 150], [179, 165], [173, 140], [173, 140]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0037_user_0007_scene_0010_cfg_0005_037522062165#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'place the first block on top of the second block, pick up the third block on the table, transfer the third block from the table to the position above the first block, place the third block on top of the first block, pick up the fourth block on the table.'\nThe trajectory starts at [195, 203]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[195, 203], [180, 239], [183, 259], [171, 230], [172, 199], [192, 187], [196, 177], [189, 178], [214, 205], [222, 231]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0037_user_0007_scene_0010_cfg_0005_037522062165#344.jpg", + "gt": "[[195, 203], [180, 239], [183, 259], [171, 230], [172, 199], [192, 187], [196, 177], [189, 178], [214, 205], [222, 231]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "87769_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the green packaging bag from the sink and put it on the countertop', and now you are performing subtask 'remove the green packaging bag from the sink and put it on the countertop.'\nYou begin at [185, 85]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[185, 85], [220, 89], [214, 116], [222, 137], [215, 144], [209, 124], [186, 140], [186, 129], [200, 137], [200, 125]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/87769_exterior_image_2_left#0.jpg", + "gt": "[[185, 85], [220, 89], [214, 116], [222, 137], [215, 144], [209, 124], [186, 140], [186, 129], [200, 137], [200, 125]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "22217_exterior_image_2_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close the lid of the bowl', and now you are performing subtask 'pull the packaging box to the closed position.'\nYour initial coordinate is [104, 109]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[104, 109], [106, 112], [105, 97], [108, 90], [101, 92], [105, 99], [103, 92], [104, 98], [106, 98], [107, 92]]}" + } + ], + "images": "22217_exterior_image_2_left#115", + "gt": "[[104, 109], [106, 112], [105, 97], [108, 90], [101, 92], [105, 99], [103, 92], [104, 98], [106, 98], [107, 92]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0014_user_0014_scene_0008_cfg_0006_104122060811#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the object from the scale', and now you are performing subtask 'remove the object from the scale.'\nFrom start point [385, 127], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[385, 127], [367, 129], [360, 137], [358, 149], [389, 153], [421, 178], [407, 162], [395, 156], [369, 158], [368, 163]]}" + } + ], + "images": "RH20T_cfg6_task_0014_user_0014_scene_0008_cfg_0006_104122060811#0", + "gt": "[[385, 127], [367, 129], [360, 137], [358, 149], [389, 153], [421, 178], [407, 162], [395, 156], [369, 158], [368, 163]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0037_user_0014_scene_0008_cfg_0006_104122064161#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'pick up the block on the table, transfer the block from the table to the stacked blocks, place the block on the stacked blocks.'\nYour initial coordinate is [353, 101]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[353, 101], [359, 143], [352, 155], [360, 125], [350, 65], [328, 22], [305, 22], [308, 37], [317, 23], [327, 31]]}" + } + ], + "images": "RH20T_cfg6_task_0037_user_0014_scene_0008_cfg_0006_104122064161#366", + "gt": "[[353, 101], [359, 143], [352, 155], [360, 125], [350, 65], [328, 22], [305, 22], [308, 37], [317, 23], [327, 31]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "31502_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the green object into the silver pot in the sink', and now you are performing subtask 'put the green object into the silver pot in the sink.'\nWith start location [161, 34], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[161, 34], [148, 49], [167, 63], [174, 90], [157, 103], [169, 94], [172, 108], [198, 119], [203, 109], [185, 118]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/31502_exterior_image_1_left#0.jpg", + "gt": "[[161, 34], [148, 49], [167, 63], [174, 90], [157, 103], [169, 94], [172, 108], [198, 119], [203, 109], [185, 118]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0015_user_0014_scene_0008_cfg_0007_104122061602#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'play the drum', and now you are performing subtask 'play the drum.'\nYour initial coordinate is [448, 116]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[448, 116], [491, 142], [520, 186], [512, 233], [494, 129], [449, 110], [466, 110], [477, 127], [459, 181], [467, 124]]}" + } + ], + "images": "RH20T_cfg7_task_0015_user_0014_scene_0008_cfg_0007_104122061602#0", + "gt": "[[448, 116], [491, 142], [520, 186], [512, 233], [494, 129], [449, 110], [466, 110], [477, 127], [459, 181], [467, 124]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0069_user_0015_scene_0001_cfg_0004_104122062823#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'assemble one piece of a puzzle', and now you are performing subtask 'throw the puzzle piece, pick up the puzzle piece from the table.'\nYou begin at [348, 99]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[348, 99], [344, 94], [377, 84], [378, 75], [390, 86], [397, 83], [396, 77], [397, 85], [395, 75], [402, 83]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg4_task_0069_user_0015_scene_0001_cfg_0004_104122062823#224.jpg", + "gt": "[[348, 99], [344, 94], [377, 84], [378, 75], [390, 86], [397, 83], [396, 77], [397, 85], [395, 75], [402, 83]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "22767_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the lid and put it on the open cup', and now you are performing subtask 'pick up the lid and put it on the open cup.'\nYou begin at [220, 99]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[220, 99], [203, 107], [203, 125], [212, 121], [197, 159], [192, 158], [195, 142], [179, 155], [185, 164], [197, 132]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/22767_exterior_image_2_left#0.jpg", + "gt": "[[220, 99], [203, 107], [203, 125], [212, 121], [197, 159], [192, 158], [195, 142], [179, 155], [185, 164], [197, 132]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "66412_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the strawberry plushie from the box', and now you are performing subtask 'remove the strawberry plushie from the box.'\nStarting at [245, 28], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[245, 28], [157, 46], [136, 80], [164, 65], [181, 76], [156, 80], [153, 99], [111, 50], [102, 89], [102, 89]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/66412_exterior_image_1_left#0.jpg", + "gt": "[[245, 28], [157, 46], [136, 80], [164, 65], [181, 76], [156, 80], [153, 99], [111, 50], [102, 89], [102, 89]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0039_user_0014_scene_0003_cfg_0006_104122064161#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pour the water from one cup into another empty cup', and now you are performing subtask 'pour the water from one cup into another empty cup.'\nYour initial coordinate is [338, 110]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[338, 110], [328, 102], [344, 121], [335, 115], [351, 153], [344, 102], [333, 102], [331, 116], [331, 103], [318, 107]]}" + } + ], + "images": "RH20T_cfg6_task_0039_user_0014_scene_0003_cfg_0006_104122064161#0", + "gt": "[[338, 110], [328, 102], [344, 121], [335, 115], [351, 153], [344, 102], [333, 102], [331, 116], [331, 103], [318, 107]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "30069_exterior_image_2_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the cloth and the shirt off the back of the chair and put them on the seat', and now you are performing subtask 'throw the shirt on the seat of the chair.'\nWith start location [218, 77], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[218, 77], [229, 75], [241, 105], [250, 110], [252, 97], [247, 69], [239, 54], [232, 50], [216, 74], [217, 59]]}" + } + ], + "images": "30069_exterior_image_2_left#113", + "gt": "[[218, 77], [229, 75], [241, 105], [250, 110], [252, 97], [247, 69], [239, 54], [232, 50], [216, 74], [217, 59]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0081_user_0020_scene_0004_cfg_0006_104122060811#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the leg of the glasses (with one hand)', and now you are performing subtask 'fold the leg of the glasses out.'\nFrom start point [385, 127], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[385, 127], [371, 135], [346, 157], [335, 175], [335, 185], [332, 160], [342, 139], [340, 143], [337, 143], [342, 141]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg6_task_0081_user_0020_scene_0004_cfg_0006_104122060811#0.jpg", + "gt": "[[385, 127], [371, 135], [346, 157], [335, 175], [335, 185], [332, 160], [342, 139], [340, 143], [337, 143], [342, 141]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "60705_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the table cloth', and now you are performing subtask 'fold the tablecloth.'\nWith start location [153, 130], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[153, 130], [190, 115], [219, 142], [168, 95], [184, 95], [193, 116], [161, 101], [210, 133], [189, 113], [189, 113]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/60705_exterior_image_2_left#0.jpg", + "gt": "[[153, 130], [190, 115], [219, 142], [168, 95], [184, 95], [193, 116], [161, 101], [210, 133], [189, 113], [189, 113]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "70682_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the yellow plush toy in the silver pot', and now you are performing subtask 'put the yellow plush toy in the silver pot.'\nYour starting position is [254, 2]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[254, 2], [170, 95], [172, 101], [173, 91], [177, 87], [209, 92], [199, 83], [193, 89], [188, 73], [188, 73]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/70682_exterior_image_2_left#0.jpg", + "gt": "[[254, 2], [170, 95], [172, 101], [173, 91], [177, 87], [209, 92], [199, 83], [193, 89], [188, 73], [188, 73]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "1158_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pull out a tissue from the box and put it on the table', and now you are performing subtask 'pull out a tissue from the box and put it on the table.'\nFrom start point [253.0, 145.0], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[253.0, 145.0], [195.0, 146.0], [174.0, 137.0], [182.0, 141.0], [151.0, 145.0], [170.0, 130.0], [187.0, 137.0], [197.0, 159.0], [178.0, 169.0], [165.0, 153.0]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/1158_exterior_image_1_left#0.jpg", + "gt": "[[253.0, 145.0], [195.0, 146.0], [174.0, 137.0], [182.0, 141.0], [151.0, 145.0], [170.0, 130.0], [187.0, 137.0], [197.0, 159.0], [178.0, 169.0], [165.0, 153.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg3_task_0059_user_0010_scene_0002_cfg_0003_104122062823#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn the knob to increase the volume of the speaker', and now you are performing subtask 'turn the knob clockwise to increase the volume, turn the button clockwise.'\nStarting at [265, 141], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[265, 141], [270, 146], [260, 142], [267, 140], [262, 136], [265, 133], [260, 136], [264, 139], [276, 126], [244, 88]]}" + } + ], + "images": "RH20T_cfg3_task_0059_user_0010_scene_0002_cfg_0003_104122062823#194", + "gt": "[[265, 141], [270, 146], [260, 142], [267, 140], [262, 136], [265, 133], [260, 136], [264, 139], [276, 126], [244, 88]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "37401_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'folding the towel on the table', and now you are performing subtask 'pick up the bottom right corner of the towel on the table.'\nYour starting position is [209, 114]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[209, 114], [220, 109], [223, 116], [221, 121], [195, 116], [161, 130], [164, 132], [168, 128], [180, 129], [205, 142]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/37401_exterior_image_1_left#183.jpg", + "gt": "[[209, 114], [220, 109], [223, 116], [221, 121], [195, 116], [161, 130], [164, 132], [168, 128], [180, 129], [205, 142]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "44936_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the water bottle forward', and now you are performing subtask 'pick up the water bottle from the left side of the table.'\nYour initial coordinate is [134, 150]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[134, 150], [134, 155], [134, 147], [136, 150], [148, 133], [163, 142], [165, 156], [160, 148], [141, 143], [132, 146]]}" + } + ], + "images": "44936_exterior_image_1_left#180", + "gt": "[[134, 150], [134, 155], [134, 147], [136, 150], [148, 133], [163, 142], [165, 156], [160, 148], [141, 143], [132, 146]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "58247_exterior_image_1_left#TrajectoryPrediction_Task#12", + "task": "TrajectoryPrediction_Task", + "p_index": 12, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the microwave door, place the bowl inside the microwave', and now you are performing subtask 'place the bowl inside the microwave.'\nThe trajectory starts at [147, 133]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[147, 133], [163, 156], [149, 136], [151, 117], [145, 124], [176, 136], [193, 156], [153, 173], [131, 116], [149, 123]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/58247_exterior_image_1_left#695.jpg", + "gt": "[[147, 133], [163, 156], [149, 136], [151, 117], [145, 124], [176, 136], [193, 156], [153, 173], [131, 116], [149, 123]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0022_user_0014_scene_0007_cfg_0006_104122060811#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'wave the flag', and now you are performing subtask 'wave the flag.'\nBegin at [385, 127] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[385, 127], [373, 116], [356, 147], [333, 154], [357, 149], [385, 122], [376, 136], [426, 124], [410, 120], [386, 130]]}" + } + ], + "images": "RH20T_cfg6_task_0022_user_0014_scene_0007_cfg_0006_104122060811#0", + "gt": "[[385, 127], [373, 116], [356, 147], [333, 154], [357, 149], [385, 122], [376, 136], [426, 124], [410, 120], [386, 130]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "84139_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'hang the cloth on the brown object', and now you are performing subtask 'hang the cloth on the brown object.'\nStarting at [218, 48], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[218, 48], [211, 67], [215, 95], [208, 113], [229, 146], [224, 146], [194, 114], [179, 83], [160, 61], [165, 57]]}" + } + ], + "images": "84139_exterior_image_1_left#0", + "gt": "[[218, 48], [211, 67], [215, 95], [208, 113], [229, 146], [224, 146], [194, 114], [179, 83], [160, 61], [165, 57]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "68725_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close the plastic box on the table', and now you are performing subtask 'close the plastic box on the table.'\nBegin at [126, 3] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[126, 3], [101, 40], [76, 123], [64, 129], [47, 99], [54, 74], [88, 53], [117, 51], [135, 67], [135, 67]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/68725_exterior_image_1_left#0.jpg", + "gt": "[[126, 3], [101, 40], [76, 123], [64, 129], [47, 99], [54, 74], [88, 53], [117, 51], [135, 67], [135, 67]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "63429_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the marker in the cup', and now you are performing subtask 'place the marker in the cup.'\nYour starting position is [112, 102]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[112, 102], [120, 110], [120, 118], [107, 121], [106, 129], [100, 119], [107, 95], [114, 90], [113, 97], [118, 91]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/63429_exterior_image_1_left#73.jpg", + "gt": "[[112, 102], [120, 110], [120, 118], [107, 121], [106, 129], [100, 119], [107, 95], [114, 90], [113, 97], [118, 91]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0037_user_0016_scene_0009_cfg_0001_035622060973#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'pick up the third block from the desktop, transfer the third block from the desktop to the second block above the second position, place the third block on top of the second block.'\nThe trajectory starts at [213, 149]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[213, 149], [251, 152], [292, 182], [295, 195], [286, 212], [281, 209], [283, 184], [267, 151], [249, 140], [214, 147]]}" + } + ], + "images": "RH20T_cfg1_task_0037_user_0016_scene_0009_cfg_0001_035622060973#318", + "gt": "[[213, 149], [251, 152], [292, 182], [295, 195], [286, 212], [281, 209], [283, 184], [267, 151], [249, 140], [214, 147]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "13437_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the door', and now you are performing subtask 'open the door.'\nWith start location [319, 66], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[319, 66], [216, 88], [160, 89], [152, 96], [176, 121], [235, 112], [276, 96], [286, 83], [283, 75], [283, 75]]}" + } + ], + "images": "13437_exterior_image_1_left#0", + "gt": "[[319, 66], [216, 88], [160, 89], [152, 96], [176, 121], [235, 112], [276, 96], [286, 83], [283, 75], [283, 75]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "30037_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the plate to the right side of the table', and now you are performing subtask 'move the plate to the right side of the table.'\nBegin at [260, 66] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[260, 66], [234, 66], [217, 77], [183, 86], [187, 104], [192, 105], [202, 95], [212, 102], [207, 94], [207, 94]]}" + } + ], + "images": "30037_exterior_image_1_left#0", + "gt": "[[260, 66], [234, 66], [217, 77], [183, 86], [187, 104], [192, 105], [202, 95], [212, 102], [207, 94], [207, 94]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "45921_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the white book into the gap between the books on the left side of the bookshelf', and now you are performing subtask 'move the white book into the gap between the books on the left side of the bookshelf.'\nBegin at [211.0, 93.0] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[211.0, 93.0], [219.0, 70.0], [184.0, 17.0], [149.0, 47.0], [180.0, 45.0], [130.0, 30.0], [110.0, 59.0], [132.0, 41.0], [191.0, 74.0], [191.0, 74.0]]}" + } + ], + "images": "45921_exterior_image_1_left#0", + "gt": "[[211.0, 93.0], [219.0, 70.0], [184.0, 17.0], [149.0, 47.0], [180.0, 45.0], [130.0, 30.0], [110.0, 59.0], [132.0, 41.0], [191.0, 74.0], [191.0, 74.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "43469_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'fold the sweatshirt twice', and now you are performing subtask 'fold the sweatshirt in half again.'\nStart at [204, 23]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[204, 23], [192, 41], [192, 43], [197, 46], [197, 47], [194, 47], [193, 45], [195, 45], [194, 46], [195, 46]]}" + } + ], + "images": "43469_exterior_image_1_left#211", + "gt": "[[204, 23], [192, 41], [192, 43], [197, 46], [197, 47], [194, 47], [193, 45], [195, 45], [194, 46], [195, 46]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg3_task_0038_user_0010_scene_0003_cfg_0003_036422060909#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the cup to the top of the cup rack and then place it down', and now you are performing subtask 'pick up the cup from the table.'\nStarting at [340, 88], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[340, 88], [326, 84], [307, 65], [291, 69], [324, 122], [344, 135], [361, 134], [348, 134], [362, 149], [362, 149]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg3_task_0038_user_0010_scene_0003_cfg_0003_036422060909#0.jpg", + "gt": "[[340, 88], [326, 84], [307, 65], [291, 69], [324, 122], [344, 135], [361, 134], [348, 134], [362, 149], [362, 149]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0002_user_0014_scene_0004_cfg_0001_750612070851#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pull out a napkin', and now you are performing subtask 'pull out a napkin.'\nYour initial coordinate is [323, 156]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[323, 156], [320, 93], [296, 238], [313, 178], [344, 154], [394, 163], [408, 177], [473, 173], [532, 184], [532, 184]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0002_user_0014_scene_0004_cfg_0001_750612070851#0.jpg", + "gt": "[[323, 156], [320, 93], [296, 238], [313, 178], [344, 154], [394, 163], [408, 177], [473, 173], [532, 184], [532, 184]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0010_user_0007_scene_0003_cfg_0005_037522062165#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'place the handset of the telephone on the corresponding phone cradle', and now you are performing subtask 'place the handset on the phone cradle.'\nYou start from [248, 210]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[248, 210], [256, 212], [263, 224], [264, 235], [265, 240], [266, 240], [267, 249], [278, 229], [279, 218], [277, 209]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0010_user_0007_scene_0003_cfg_0005_037522062165#365.jpg", + "gt": "[[248, 210], [256, 212], [263, 224], [264, 235], [265, 240], [266, 240], [267, 249], [278, 229], [279, 218], [277, 209]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg2_task_0065_user_0007_scene_0003_cfg_0002_104122063678#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with small Lego blocks for the nth time with n blocks', and now you are performing subtask 'place the black Lego block on the Lego base, pick up the green Lego block from the table, transfer the green Lego block from the table to the Lego base, place the green Lego block on the Lego base.'\nFrom start point [476, 269], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[476, 269], [469, 260], [477, 269], [490, 255], [499, 207], [516, 199], [517, 209], [473, 211], [479, 235], [484, 219]]}" + } + ], + "images": "RH20T_cfg2_task_0065_user_0007_scene_0003_cfg_0002_104122063678#640", + "gt": "[[476, 269], [469, 260], [477, 269], [490, 255], [499, 207], [516, 199], [517, 209], [473, 211], [479, 235], [484, 219]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0015_user_0001_scene_0006_cfg_0001_038522063145#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'play the drum', and now you are performing subtask 'play the drum.'\nStarting at [442, 98], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[442, 98], [428, 114], [403, 117], [397, 131], [391, 100], [398, 87], [447, 62], [464, 71], [445, 80], [447, 112]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0015_user_0001_scene_0006_cfg_0001_038522063145#0.jpg", + "gt": "[[442, 98], [428, 114], [403, 117], [397, 131], [391, 100], [398, 87], [447, 62], [464, 71], [445, 80], [447, 112]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "54397_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'fold the top right corner over the bottom left corner, then fold the bottom right corner over the top left corner', and now you are performing subtask 'pick up the bottom right corner of the cloth on the table.'\nYour starting position is [228, 106]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[228, 106], [227, 88], [180, 83], [187, 85], [166, 92], [166, 78], [173, 74], [202, 106], [199, 85], [199, 85]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/54397_exterior_image_1_left#0.jpg", + "gt": "[[228, 106], [227, 88], [180, 83], [187, 85], [166, 92], [166, 78], [173, 74], [202, 106], [199, 85], [199, 85]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "29717_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the clothes on the chair back', and now you are performing subtask 'put the clothes on the chair back.'\nYou begin at [137, 105]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[137, 105], [133, 126], [134, 103], [170, 67], [185, 82], [197, 68], [200, 109], [135, 146], [126, 164], [166, 101]]}" + } + ], + "images": "29717_exterior_image_2_left#0", + "gt": "[[137, 105], [133, 126], [134, 103], [170, 67], [185, 82], [197, 68], [200, 109], [135, 146], [126, 164], [166, 101]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "32431_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the detergent tray on the second washing machine', and now you are performing subtask 'open the detergent tray on the second washing machine.'\nBegin at [157, 58] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[157, 58], [183, 98], [184, 116], [186, 119], [188, 114], [176, 127], [166, 130], [176, 118], [180, 103], [169, 69]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/32431_exterior_image_1_left#0.jpg", + "gt": "[[157, 58], [183, 98], [184, 116], [186, 119], [188, 114], [176, 127], [166, 130], [176, 118], [180, 103], [169, 69]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg3_task_0043_user_0010_scene_0006_cfg_0003_104122062823#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unscrew the lid from the cup', and now you are performing subtask 'twist the lid counterclockwise to unscrew it from the cup, pick up the lid from the cup on the table, place the lid on the cup.'\nWith start location [286, 65], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[286, 65], [265, 66], [272, 55], [271, 35], [281, 36], [283, 55], [283, 48], [279, 56], [263, 37], [263, 49]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg3_task_0043_user_0010_scene_0006_cfg_0003_104122062823#313.jpg", + "gt": "[[286, 65], [265, 66], [272, 55], [271, 35], [281, 36], [283, 55], [283, 48], [279, 56], [263, 37], [263, 49]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg3_task_0058_user_0010_scene_0006_cfg_0003_036422060909#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn off the power strips', and now you are performing subtask 'press the first button of the power strip, press the second button of the power strip.'\nThe trajectory starts at [337, 88]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[337, 88], [320, 72], [283, 84], [300, 87], [317, 118], [270, 145], [260, 169], [230, 177], [232, 204], [210, 205]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg3_task_0058_user_0010_scene_0006_cfg_0003_036422060909#0.jpg", + "gt": "[[337, 88], [320, 72], [283, 84], [300, 87], [317, 118], [270, 145], [260, 169], [230, 177], [232, 204], [210, 205]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "72204_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'place the green cylindrical object on the left side of the green triangular block on the table', and now you are performing subtask 'place the green cylindrical object on the left side of the green triangular block on the table.'\nYou begin at [0, 24]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[0, 24], [111, 52], [156, 70], [171, 83], [161, 96], [159, 91], [178, 79], [205, 92], [197, 80], [162, 78]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/72204_exterior_image_1_left#0.jpg", + "gt": "[[0, 24], [111, 52], [156, 70], [171, 83], [161, 96], [159, 91], [178, 79], [205, 92], [197, 80], [162, 78]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "30342_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the garlic on the counter into the glass bowl one by one', and now you are performing subtask 'place the first garlic into the glass bowl.'\nFrom start point [131, 32], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[131, 32], [163, 89], [169, 110], [167, 120], [166, 102], [158, 95], [150, 95], [153, 100], [154, 95], [154, 95]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/30342_exterior_image_2_left#0.jpg", + "gt": "[[131, 32], [163, 89], [169, 110], [167, 120], [166, 102], [158, 95], [150, 95], [153, 100], [154, 95], [154, 95]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "49270_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the marker from the cup, move the cup to the left and put the marker in the cup', and now you are performing subtask 'pick up the marker from the table.'\nYou start from [187, 12]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[187, 12], [182, 22], [186, 35], [206, 26], [201, 21], [195, 27], [197, 44], [182, 31], [168, 56], [171, 46]]}" + } + ], + "images": "49270_exterior_image_1_left#179", + "gt": "[[187, 12], [182, 22], [186, 35], [206, 26], [201, 21], [195, 27], [197, 44], [182, 31], [168, 56], [171, 46]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "79987_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the marker out of the cup and put it on the table', and now you are performing subtask 'take the marker out of the cup and put it on the table.'\nYou begin at [113, 4]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[113, 4], [107, 33], [79, 58], [98, 64], [90, 97], [98, 98], [93, 54], [115, 58], [135, 97], [130, 110]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/79987_exterior_image_2_left#0.jpg", + "gt": "[[113, 4], [107, 33], [79, 58], [98, 64], [90, 97], [98, 98], [93, 54], [115, 58], [135, 97], [130, 110]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0096_user_0014_scene_0001_cfg_0001_819112070044#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take something out of a drawer', and now you are performing subtask 'pull the drawer handle to the outside of the table, pick up the object from the drawer, transfer the object from the drawer to the top of the table, place the object on the table.'\nFrom start point [344, 195], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[344, 195], [355, 189], [352, 174], [333, 178], [334, 214], [333, 182], [367, 148], [376, 158], [377, 201], [384, 160]]}" + } + ], + "images": "RH20T_cfg1_task_0096_user_0014_scene_0001_cfg_0001_819112070044#130", + "gt": "[[344, 195], [355, 189], [352, 174], [333, 178], [334, 214], [333, 182], [367, 148], [376, 158], [377, 201], [384, 160]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0001_user_0010_scene_0001_cfg_0005_104122063678#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the button from top to bottom', and now you are performing subtask 'press the button from top to bottom.'\nFrom start point [323, 132], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[323, 132], [332, 147], [332, 156], [327, 195], [320, 213], [313, 220], [316, 223], [313, 223], [331, 195], [331, 187]]}" + } + ], + "images": "RH20T_cfg5_task_0001_user_0010_scene_0001_cfg_0005_104122063678#0", + "gt": "[[323, 132], [332, 147], [332, 156], [327, 195], [320, 213], [313, 220], [316, 223], [313, 223], [331, 195], [331, 187]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0029_user_0001_scene_0004_cfg_0001_750612070853#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'grasp the handle and open the drawer', and now you are performing subtask 'grasp the handle and open the drawer.'\nThe trajectory starts at [292, 115]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[292, 115], [234, 83], [210, 94], [190, 154], [195, 259], [232, 360], [344, 356], [216, 360], [254, 360], [255, 248]]}" + } + ], + "images": "RH20T_cfg1_task_0029_user_0001_scene_0004_cfg_0001_750612070853#0", + "gt": "[[292, 115], [234, 83], [210, 94], [190, 154], [195, 259], [232, 360], [344, 356], [216, 360], [254, 360], [255, 248]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0003_user_0010_scene_0001_cfg_0005_036422060215#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press three buttons from left to right in sequence', and now you are performing subtask 'press the yellow button on the right.'\nThe trajectory starts at [286, 108]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[286, 108], [285, 98], [311, 115], [305, 109], [303, 118], [311, 112], [305, 110], [300, 139], [303, 117], [294, 123]]}" + } + ], + "images": "RH20T_cfg5_task_0003_user_0010_scene_0001_cfg_0005_036422060215#0", + "gt": "[[286, 108], [285, 98], [311, 115], [305, 109], [303, 118], [311, 112], [305, 110], [300, 139], [303, 117], [294, 123]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "71119_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the bulbs of garlic from the glass bowl and place them on the countertop', and now you are performing subtask 'pick up the first bulb of garlic from the glass bowl.'\nYour initial coordinate is [319, 92]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[319, 92], [279, 101], [262, 101], [238, 115], [237, 126], [241, 128], [238, 128], [239, 130], [242, 124], [239, 113]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/71119_exterior_image_1_left#0.jpg", + "gt": "[[319, 92], [279, 101], [262, 101], [238, 115], [237, 126], [241, 128], [238, 128], [239, 130], [242, 124], [239, 113]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0091_user_0007_scene_0004_cfg_0005_104122061850#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move an object from one box to another', and now you are performing subtask 'pick up the block from the pink box, transfer the block from the pink box to the table, throw the block onto the table.'\nBegin at [305, 50] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[305, 50], [312, 73], [323, 79], [327, 86], [345, 143], [371, 172], [374, 185], [372, 195], [374, 168], [362, 98]]}" + } + ], + "images": "RH20T_cfg5_task_0091_user_0007_scene_0004_cfg_0005_104122061850#0", + "gt": "[[305, 50], [312, 73], [323, 79], [327, 86], [345, 143], [371, 172], [374, 185], [372, 195], [374, 168], [362, 98]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg2_task_0062_user_0007_scene_0001_cfg_0002_104122061850#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the toilet paper on its holder', and now you are performing subtask 'put the toilet paper on its holder.'\nStarting at [339, 107], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[339, 107], [438, 151], [441, 176], [431, 137], [404, 103], [394, 111], [377, 71], [396, 103], [398, 125], [398, 125]]}" + } + ], + "images": "RH20T_cfg2_task_0062_user_0007_scene_0001_cfg_0002_104122061850#0", + "gt": "[[339, 107], [438, 151], [441, 176], [431, 137], [404, 103], [394, 111], [377, 71], [396, 103], [398, 125], [398, 125]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0016_user_0020_scene_0004_cfg_0007_104122061330#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'hit the pool ball', and now you are performing subtask 'transfer the cue from the top of the table to the position above the pool ball, strike the pool ball with the cue, place the cue on the pool table.'\nWith start location [379, 133], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[379, 133], [381, 137], [367, 149], [378, 128], [368, 138], [367, 122], [357, 95], [348, 88], [338, 93], [332, 92]]}" + } + ], + "images": "RH20T_cfg7_task_0016_user_0020_scene_0004_cfg_0007_104122061330#275", + "gt": "[[379, 133], [381, 137], [367, 149], [378, 128], [368, 138], [367, 122], [357, 95], [348, 88], [338, 93], [332, 92]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "48447_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unhang the orange towel and put it in the sink', and now you are performing subtask 'unhang the orange towel and put it in the sink.'\nStarting at [91, 11], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[91, 11], [111, 39], [125, 36], [116, 47], [125, 40], [136, 51], [103, 73], [108, 14], [120, 35], [124, 28]]}" + } + ], + "images": "48447_exterior_image_1_left#0", + "gt": "[[91, 11], [111, 39], [125, 36], [116, 47], [125, 40], [136, 51], [103, 73], [108, 14], [120, 35], [124, 28]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "68837_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the marker in the mug', and now you are performing subtask 'put the marker in the mug.'\nStarting at [122.5, 33.5], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[122.5, 33.5], [145.5, 30.5], [180.5, 78.5], [182.5, 40.5], [201.5, 45.5], [199.5, 70.5], [203.5, 75.5], [196.5, 83.5], [199.5, 67.5], [199.5, 67.5]]}" + } + ], + "images": "68837_exterior_image_1_left#0", + "gt": "[[122.5, 33.5], [145.5, 30.5], [180.5, 78.5], [182.5, 40.5], [201.5, 45.5], [199.5, 70.5], [203.5, 75.5], [196.5, 83.5], [199.5, 67.5], [199.5, 67.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "44385_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the egg toy into the cup', and now you are performing subtask 'place the egg toy in the cup.'\nYour starting position is [146, 127]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[146, 127], [147, 125], [142, 127], [152, 116], [180, 104], [178, 106], [210, 102], [225, 104], [223, 109], [223, 109]]}" + } + ], + "images": "44385_exterior_image_1_left#497", + "gt": "[[146, 127], [147, 125], [142, 127], [152, 116], [180, 104], [178, 106], [210, 102], [225, 104], [223, 109], [223, 109]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "48472_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the green plush toy in the drawer', and now you are performing subtask 'put the green plush toy in the drawer.'\nFrom start point [212, 23], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[212, 23], [193, 16], [139, 15], [150, 19], [125, 39], [120, 70], [134, 42], [186, 84], [197, 85], [189, 64]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/48472_exterior_image_1_left#0.jpg", + "gt": "[[212, 23], [193, 16], [139, 15], [150, 19], [125, 39], [120, 70], [134, 42], [186, 84], [197, 85], [189, 64]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0066_user_0014_scene_0007_cfg_0007_104122064161#TrajectoryPrediction_Task#12", + "task": "TrajectoryPrediction_Task", + "p_index": 12, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with large Megabloks for the nth time with n blocks', and now you are performing subtask 'place the building blocks on the pile of building blocks on the building board, pick up the building blocks on the table, transfer the building blocks from the desktop to the pile of building blocks on the building board, place the building blocks on the pile of building blocks on the building board.'\nYour starting position is [350, 145]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[350, 145], [400, 115], [442, 127], [429, 138], [425, 122], [398, 135], [366, 158], [359, 180], [372, 161], [375, 116]]}" + } + ], + "images": "RH20T_cfg7_task_0066_user_0014_scene_0007_cfg_0007_104122064161#825", + "gt": "[[350, 145], [400, 115], [442, 127], [429, 138], [425, 122], [398, 135], [366, 158], [359, 180], [372, 161], [375, 116]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "22984_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the mug cup to the left', and now you are performing subtask 'move the mug cup to the left.'\nFrom start point [203, 5], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[203, 5], [182, 65], [169, 59], [167, 73], [146, 70], [148, 55], [165, 54], [154, 56], [162, 79], [160, 61]]}" + } + ], + "images": "22984_exterior_image_1_left#0", + "gt": "[[203, 5], [182, 65], [169, 59], [167, 73], [146, 70], [148, 55], [165, 54], [154, 56], [162, 79], [160, 61]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0073_user_0007_scene_0001_cfg_0005_104122063678#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the things in the drawer', and now you are performing subtask 'grab the handle to pull the drawer open, pick up the cube on the table, transfer the cube from the table to the drawer, place the cube in the drawer.'\nFrom start point [328, 169], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[328, 169], [333, 160], [352, 164], [359, 171], [356, 192], [362, 163], [351, 152], [345, 183], [329, 192], [328, 213]]}" + } + ], + "images": "RH20T_cfg5_task_0073_user_0007_scene_0001_cfg_0005_104122063678#539", + "gt": "[[328, 169], [333, 160], [352, 164], [359, 171], [356, 192], [362, 163], [351, 152], [345, 183], [329, 192], [328, 213]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "30469_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the drawer, then take out a plush toy from the drawer, then close the drawer', and now you are performing subtask 'pick up the plush toy from the drawer.'\nYou start from [220, 82]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[220, 82], [227, 103], [220, 89], [200, 79], [186, 96], [194, 89], [190, 74], [169, 60], [162, 62], [167, 67]]}" + } + ], + "images": "30469_exterior_image_1_left#389", + "gt": "[[220, 82], [227, 103], [220, 89], [200, 79], [186, 96], [194, 89], [190, 74], [169, 60], [162, 62], [167, 67]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0010_user_0010_scene_0007_cfg_0005_104122063678#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'place the handset of the telephone on the corresponding phone cradle', and now you are performing subtask 'place the handset of the telephone on the corresponding phone cradle.'\nYou start from [323, 132]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[323, 132], [325, 172], [308, 176], [328, 194], [335, 215], [280, 259], [277, 289], [282, 262], [272, 230], [285, 198]]}" + } + ], + "images": "RH20T_cfg5_task_0010_user_0010_scene_0007_cfg_0005_104122063678#0", + "gt": "[[323, 132], [325, 172], [308, 176], [328, 194], [335, 215], [280, 259], [277, 289], [282, 262], [272, 230], [285, 198]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "36160_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the cloth on the table', and now you are performing subtask 'unfold the cloth on the table.'\nWith start location [118, 78], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[118, 78], [134, 63], [159, 62], [155, 64], [161, 69], [162, 91], [161, 100], [157, 96], [186, 114], [197, 152]]}" + } + ], + "images": "36160_exterior_image_1_left#0", + "gt": "[[118, 78], [134, 63], [159, 62], [155, 64], [161, 69], [162, 91], [161, 100], [157, 96], [186, 114], [197, 152]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "77845_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the tape on the plate', and now you are performing subtask 'put the tape on the plate.'\nStarting at [308, 108], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[308, 108], [308, 54], [304, 60], [258, 64], [261, 70], [249, 84], [257, 69], [240, 55], [201, 58], [189, 74]]}" + } + ], + "images": "77845_exterior_image_2_left#0", + "gt": "[[308, 108], [308, 54], [304, 60], [258, 64], [261, 70], [249, 84], [257, 69], [240, 55], [201, 58], [189, 74]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "76379_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the white mug forward to the left side of the table, place the ballpoint pen into the white mug', and now you are performing subtask 'place the ballpoint pen inside the white mug.'\nYou begin at [151.0, 44.5]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[151.0, 44.5], [153.0, 54.5], [147.0, 59.5], [152.0, 67.5], [150.0, 101.5], [147.0, 71.5], [133.0, 44.5], [126.0, 40.5], [112.0, 44.5], [104.0, 35.5]]}" + } + ], + "images": "76379_exterior_image_1_left#191", + "gt": "[[151.0, 44.5], [153.0, 54.5], [147.0, 59.5], [152.0, 67.5], [150.0, 101.5], [147.0, 71.5], [133.0, 44.5], [126.0, 40.5], [112.0, 44.5], [104.0, 35.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "47503_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the lid from the black pot', and now you are performing subtask 'remove the lid from the black pot.'\nWith start location [251, 56], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[251, 56], [199, 76], [186, 92], [183, 92], [185, 80], [177, 80], [163, 91], [156, 108], [156, 126], [162, 106]]}" + } + ], + "images": "47503_exterior_image_2_left#0", + "gt": "[[251, 56], [199, 76], [186, 92], [183, 92], [185, 80], [177, 80], [163, 91], [156, 108], [156, 126], [162, 106]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0016_user_0014_scene_0001_cfg_0001_819112070044#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'hit the pool ball', and now you are performing subtask 'pick up the pool ball from the surface.'\nYou begin at [399, 166]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[399, 166], [374, 169], [372, 161], [321, 184], [301, 184], [285, 196], [256, 234], [248, 260], [245, 261], [246, 252]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0016_user_0014_scene_0001_cfg_0001_819112070044#0.jpg", + "gt": "[[399, 166], [374, 169], [372, 161], [321, 184], [301, 184], [285, 196], [256, 234], [248, 260], [245, 261], [246, 252]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "88052_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'place the lid on the stove', and now you are performing subtask 'place the lid on the stove.'\nBegin at [245, 32] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[245, 32], [191, 87], [201, 102], [194, 105], [197, 114], [200, 98], [209, 89], [231, 94], [227, 105], [226, 75]]}" + } + ], + "images": "88052_exterior_image_1_left#0", + "gt": "[[245, 32], [191, 87], [201, 102], [194, 105], [197, 114], [200, 98], [209, 89], [231, 94], [227, 105], [226, 75]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0037_user_0020_scene_0004_cfg_0006_104122064161#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'place the block on the other block, pick up the block on the surface, transfer the block from the surface to the other block, place the block on the other block.'\nFrom start point [380, 158], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[380, 158], [373, 189], [382, 191], [382, 200], [376, 204], [369, 161], [336, 112], [327, 123], [341, 117], [363, 130]]}" + } + ], + "images": "RH20T_cfg6_task_0037_user_0020_scene_0004_cfg_0006_104122064161#496", + "gt": "[[380, 158], [373, 189], [382, 191], [382, 200], [376, 204], [369, 161], [336, 112], [327, 123], [341, 117], [363, 130]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "87825_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the red marker from the yellow mug, place the marker back in the mug, take the marker out of the mug', and now you are performing subtask 'place the marker on the right side of the yellow mug.'\nFrom start point [152, 48], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[152, 48], [155, 59], [155, 54], [152, 57], [156, 52], [159, 32], [178, 27], [181, 49], [177, 62], [181, 68]]}" + } + ], + "images": "87825_exterior_image_1_left#250", + "gt": "[[152, 48], [155, 59], [155, 54], [152, 57], [156, 52], [159, 32], [178, 27], [181, 49], [177, 62], [181, 68]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0037_user_0007_scene_0010_cfg_0005_104422070044#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'pick up the first block on the table, transfer the first block from the table to the position above the second block, place the first block on top of the second block.'\nBegin at [374, 132] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[374, 132], [382, 141], [403, 152], [406, 191], [410, 194], [407, 206], [409, 194], [430, 168], [436, 175], [438, 164]]}" + } + ], + "images": "RH20T_cfg5_task_0037_user_0007_scene_0010_cfg_0005_104422070044#0", + "gt": "[[374, 132], [382, 141], [403, 152], [406, 191], [410, 194], [407, 206], [409, 194], [430, 168], [436, 175], [438, 164]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg3_task_0057_user_0010_scene_0007_cfg_0003_104122062823#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn on the power strips', and now you are performing subtask 'press the button of the power socket in the second position.'\nBegin at [181, 125] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[181, 125], [183, 121], [187, 117], [189, 117], [190, 119], [189, 128], [190, 129], [187, 125], [185, 114], [185, 114]]}" + } + ], + "images": "RH20T_cfg3_task_0057_user_0010_scene_0007_cfg_0003_104122062823#161", + "gt": "[[181, 125], [183, 121], [187, 117], [189, 117], [190, 119], [189, 128], [190, 129], [187, 125], [185, 114], [185, 114]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "64414_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the marker inside the white bowl then remove it and put it on the table', and now you are performing subtask 'put the marker inside the white bowl then remove it and put it on the table.'\nThe trajectory starts at [33, 40]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[33, 40], [89, 37], [139, 85], [177, 98], [172, 124], [179, 103], [168, 77], [139, 61], [128, 76], [128, 62]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/64414_exterior_image_1_left#0.jpg", + "gt": "[[33, 40], [89, 37], [139, 85], [177, 98], [172, 124], [179, 103], [168, 77], [139, 61], [128, 76], [128, 62]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "83796_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the cup on the right side of the table', and now you are performing subtask 'put the cup on the right side of the table.'\nFrom start point [266, 17], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[266, 17], [239, 25], [230, 63], [214, 75], [205, 96], [209, 97], [194, 108], [194, 91], [200, 85], [210, 89]]}" + } + ], + "images": "83796_exterior_image_1_left#0", + "gt": "[[266, 17], [239, 25], [230, 63], [214, 75], [205, 96], [209, 97], [194, 108], [194, 91], [200, 85], [210, 89]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "52362_exterior_image_1_left#TrajectoryPrediction_Task#8", + "task": "TrajectoryPrediction_Task", + "p_index": 8, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'arrange the two small pillows against the right armrest of the sofa', and now you are performing subtask 'pick up the small pillow on the left side of the sofa.'\nYour starting position is [174, 110]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[174, 110], [172, 112], [173, 114], [163, 121], [160, 113], [160, 106], [163, 100], [166, 99], [168, 101], [164, 100]]}" + } + ], + "images": "52362_exterior_image_1_left#422", + "gt": "[[174, 110], [172, 112], [173, 114], [163, 121], [160, 113], [160, 106], [163, 100], [166, 99], [168, 101], [164, 100]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "72865_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the middle washing machine door', and now you are performing subtask 'open the middle washing machine door.'\nStarting at [109, 40], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[109, 40], [119, 52], [132, 60], [141, 77], [147, 83], [151, 80], [154, 85], [132, 104], [137, 59], [123, 14]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/72865_exterior_image_1_left#0.jpg", + "gt": "[[109, 40], [119, 52], [132, 60], [141, 77], [147, 83], [151, 80], [154, 85], [132, 104], [137, 59], [123, 14]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg3_task_0071_user_0010_scene_0008_cfg_0003_104122062823#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close a sliding window', and now you are performing subtask 'push the sliding window to close.'\nYour initial coordinate is [178, 144]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[178, 144], [194, 152], [172, 158], [205, 132], [184, 131], [202, 137], [185, 154], [206, 107], [221, 103], [223, 115]]}" + } + ], + "images": "RH20T_cfg3_task_0071_user_0010_scene_0008_cfg_0003_104122062823#174", + "gt": "[[178, 144], [194, 152], [172, 158], [205, 132], [184, 131], [202, 137], [185, 154], [206, 107], [221, 103], [223, 115]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg3_task_0058_user_0010_scene_0010_cfg_0003_036422060909#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn off the power strips', and now you are performing subtask 'press the button on the power strip above, press the button on the power strip above.'\nBegin at [204, 136] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[204, 136], [203, 134], [199, 135], [199, 137], [202, 140], [201, 141], [206, 120], [213, 109], [222, 100], [221, 100]]}" + } + ], + "images": "RH20T_cfg3_task_0058_user_0010_scene_0010_cfg_0003_036422060909#161", + "gt": "[[204, 136], [203, 134], [199, 135], [199, 137], [202, 140], [201, 141], [206, 120], [213, 109], [222, 100], [221, 100]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "22578_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the lid from the glass jar and place it on the table, then put it back on the jar', and now you are performing subtask 'place the lid from the table on the right side of the glass jar onto the glass jar.'\nYou begin at [34, 45]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[34, 45], [52, 53], [112, 57], [136, 78], [122, 92], [140, 88], [156, 103], [158, 133], [160, 98], [160, 98]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/22578_exterior_image_2_left#0.jpg", + "gt": "[[34, 45], [52, 53], [112, 57], [136, 78], [122, 92], [140, 88], [156, 103], [158, 133], [160, 98], [160, 98]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0028_user_0020_scene_0003_cfg_0007_104122061602#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'grasp the handle and close the drawer', and now you are performing subtask 'grasp the handle and close the drawer.'\nYou start from [448, 116]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[448, 116], [443, 117], [447, 146], [454, 138], [444, 142], [391, 116], [421, 114], [413, 97], [438, 88], [450, 103]]}" + } + ], + "images": "RH20T_cfg7_task_0028_user_0020_scene_0003_cfg_0007_104122061602#0", + "gt": "[[448, 116], [443, 117], [447, 146], [454, 138], [444, 142], [391, 116], [421, 114], [413, 97], [438, 88], [450, 103]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "13477_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the rectangular object from the middle of the table and put it in the cabinet', and now you are performing subtask 'pick up the rectangular object from the middle of the table and put it in the cabinet.'\nStarting at [212, 93], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[212, 93], [224, 127], [215, 136], [210, 126], [219, 104], [206, 12], [179, 18], [204, 20], [224, 74], [224, 74]]}" + } + ], + "images": "13477_exterior_image_2_left#0", + "gt": "[[212, 93], [224, 127], [215, 136], [210, 126], [219, 104], [206, 12], [179, 18], [204, 20], [224, 74], [224, 74]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "58422_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'place the marker on the table', and now you are performing subtask 'place the marker on the table.'\nStarting at [151, 8], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[151, 8], [154, 43], [168, 75], [164, 81], [169, 60], [181, 63], [185, 72], [183, 102], [175, 68], [155, 56]]}" + } + ], + "images": "58422_exterior_image_1_left#0", + "gt": "[[151, 8], [154, 43], [168, 75], [164, 81], [169, 60], [181, 63], [185, 72], [183, 102], [175, 68], [155, 56]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0066_user_0014_scene_0005_cfg_0007_104122061330#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with large Megabloks for the nth time with n blocks', and now you are performing subtask 'place the block on the block board, pick up the block on the flat surface, transfer the block from the flat surface to the block board, place the block on the block board.'\nBegin at [320, 178] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[320, 178], [356, 193], [375, 212], [335, 177], [329, 143], [317, 123], [314, 125], [313, 132], [324, 128], [342, 154]]}" + } + ], + "images": "RH20T_cfg7_task_0066_user_0014_scene_0005_cfg_0007_104122061330#332", + "gt": "[[320, 178], [356, 193], [375, 212], [335, 177], [329, 143], [317, 123], [314, 125], [313, 132], [324, 128], [342, 154]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "52270_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'use the yellow towel to wipe the countertop', and now you are performing subtask 'use the yellow towel to wipe the countertop.'\nThe trajectory starts at [117, 3]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[117, 3], [81, 75], [123, 61], [126, 75], [161, 78], [102, 109], [91, 104], [104, 81], [148, 76], [146, 42]]}" + } + ], + "images": "52270_exterior_image_2_left#0", + "gt": "[[117, 3], [81, 75], [123, 61], [126, 75], [161, 78], [102, 109], [91, 104], [104, 81], [148, 76], [146, 42]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "83661_exterior_image_2_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'fold the cloth on the table and put the corn cob in the pot', and now you are performing subtask 'fold the cloth on the table again.'\nBegin at [198, 93] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[198, 93], [214, 104], [227, 105], [225, 97], [218, 98], [214, 105], [216, 78], [211, 86], [218, 63], [218, 63]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/83661_exterior_image_2_left#222.jpg", + "gt": "[[198, 93], [214, 104], [227, 105], [225, 97], [218, 98], [214, 105], [216, 78], [211, 86], [218, 63], [218, 63]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "17884_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the green object to the left side of the counter', and now you are performing subtask 'move the green object to the left side of the counter.'\nThe trajectory starts at [229, 96]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[229, 96], [213, 127], [220, 130], [217, 147], [221, 147], [217, 148], [217, 132], [203, 144], [198, 156], [205, 136]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/17884_exterior_image_2_left#0.jpg", + "gt": "[[229, 96], [213, 127], [220, 130], [217, 147], [221, 147], [217, 148], [217, 132], [203, 144], [198, 156], [205, 136]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0066_user_0014_scene_0005_cfg_0007_104122061330#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with large Megabloks for the nth time with n blocks', and now you are performing subtask 'place the block on the block board, pick up the block on the flat surface, transfer the block from the flat surface to the block board, place the block on the block board.'\nStart at [312, 188]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[312, 188], [346, 211], [366, 229], [368, 235], [302, 156], [297, 153], [293, 155], [300, 160], [302, 154], [320, 178]]}" + } + ], + "images": "RH20T_cfg7_task_0066_user_0014_scene_0005_cfg_0007_104122061330#218", + "gt": "[[312, 188], [346, 211], [366, 229], [368, 235], [302, 156], [297, 153], [293, 155], [300, 160], [302, 154], [320, 178]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0037_user_0014_scene_0009_cfg_0007_104122061018#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'pick up the first block from the desktop, transfer the block from the desktop to the second block, place the block on the second block, pick up the third block from the desktop.'\nBegin at [363, 31] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[363, 31], [359, 110], [380, 142], [380, 179], [355, 202], [361, 218], [359, 204], [340, 205], [364, 189], [382, 209]]}" + } + ], + "images": "RH20T_cfg7_task_0037_user_0014_scene_0009_cfg_0007_104122061018#0", + "gt": "[[363, 31], [359, 110], [380, 142], [380, 179], [355, 202], [361, 218], [359, 204], [340, 205], [364, 189], [382, 209]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "5631_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the longer rectangular block on top of the cube', and now you are performing subtask 'put the longer rectangular block on top of the cube.'\nFrom start point [265, 0], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[265, 0], [255, 36], [235, 47], [232, 56], [223, 42], [209, 47], [217, 50], [215, 60], [219, 25], [237, 2]]}" + } + ], + "images": "5631_exterior_image_2_left#0", + "gt": "[[265, 0], [255, 36], [235, 47], [232, 56], [223, 42], [209, 47], [217, 50], [215, 60], [219, 25], [237, 2]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "28265_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the cloth on the table', and now you are performing subtask 'unfold the cloth on the table.'\nWith start location [113, 118], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[113, 118], [124, 149], [140, 153], [142, 161], [163, 173], [147, 172], [155, 168], [116, 147], [97, 155], [146, 143]]}" + } + ], + "images": "28265_exterior_image_2_left#0", + "gt": "[[113, 118], [124, 149], [140, 153], [142, 161], [163, 173], [147, 172], [155, 168], [116, 147], [97, 155], [146, 143]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0047_user_0007_scene_0009_cfg_0005_105422061350#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the cup off the cup rack', and now you are performing subtask 'take the cup off the cup rack.'\nStart at [276, 47]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[276, 47], [248, 54], [235, 75], [125, 155], [119, 123], [140, 73], [179, 46], [191, 43], [209, 51], [205, 93]]}" + } + ], + "images": "RH20T_cfg5_task_0047_user_0007_scene_0009_cfg_0005_105422061350#0", + "gt": "[[276, 47], [248, 54], [235, 75], [125, 155], [119, 123], [140, 73], [179, 46], [191, 43], [209, 51], [205, 93]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0037_user_0020_scene_0008_cfg_0006_104122061018#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'pick up the first block on the table, transfer the first block from the table to above the second block, place the first block on top of the second block, pick up the third block on the table.'\nYour initial coordinate is [367, 28]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[367, 28], [284, 35], [258, 56], [266, 84], [280, 59], [308, 54], [339, 67], [332, 46], [350, 63], [350, 63]]}" + } + ], + "images": "RH20T_cfg6_task_0037_user_0020_scene_0008_cfg_0006_104122061018#0", + "gt": "[[367, 28], [284, 35], [258, 56], [266, 84], [280, 59], [308, 54], [339, 67], [332, 46], [350, 63], [350, 63]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "45213_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the orange block on the green block', and now you are performing subtask 'put the orange block on the green block.'\nYou begin at [63, 87]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[63, 87], [79, 89], [92, 97], [94, 102], [93, 114], [97, 117], [114, 103], [120, 102], [126, 107], [126, 107]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/45213_exterior_image_2_left#0.jpg", + "gt": "[[63, 87], [79, 89], [92, 97], [94, 102], [93, 114], [97, 117], [114, 103], [120, 102], [126, 107], [126, 107]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0073_user_0020_scene_0005_cfg_0006_037522061512#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the things in the drawer', and now you are performing subtask 'pick up the wooden block on the table, transfer the wooden block from the table to the drawer, place the wooden block in the drawer, push the drawer to close the drawer.'\nFrom start point [235, 80], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[235, 80], [263, 72], [252, 62], [270, 94], [230, 48], [191, 56], [178, 99], [197, 136], [185, 84], [230, 88]]}" + } + ], + "images": "RH20T_cfg6_task_0073_user_0020_scene_0005_cfg_0006_037522061512#351", + "gt": "[[235, 80], [263, 72], [252, 62], [270, 94], [230, 48], [191, 56], [178, 99], [197, 136], [185, 84], [230, 88]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "51220_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the orange object inside the sink', and now you are performing subtask 'put the orange object inside the sink.'\nYour initial coordinate is [231, 89]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[231, 89], [185, 121], [184, 145], [182, 123], [203, 114], [219, 114], [225, 123], [225, 146], [216, 130], [226, 129]]}" + } + ], + "images": "51220_exterior_image_2_left#0", + "gt": "[[231, 89], [185, 121], [184, 145], [182, 123], [203, 114], [219, 114], [225, 123], [225, 146], [216, 130], [226, 129]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "36015_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the pen from the white and red mug', and now you are performing subtask 'remove the pen from the white and red mug.'\nYour initial coordinate is [208, 0]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[208, 0], [140, 20], [137, 23], [148, 26], [135, 32], [136, 3], [156, 0], [162, 4], [187, 60], [192, 55]]}" + } + ], + "images": "36015_exterior_image_2_left#0", + "gt": "[[208, 0], [140, 20], [137, 23], [148, 26], [135, 32], [136, 3], [156, 0], [162, 4], [187, 60], [192, 55]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0038_user_0020_scene_0001_cfg_0006_104122061330#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the cup', and now you are performing subtask 'pick up the cup.'\nWith start location [266, 97], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[266, 97], [314, 77], [322, 58], [327, 72], [354, 79], [347, 93], [357, 128], [347, 124], [345, 142], [345, 99]]}" + } + ], + "images": "RH20T_cfg6_task_0038_user_0020_scene_0001_cfg_0006_104122061330#0", + "gt": "[[266, 97], [314, 77], [322, 58], [327, 72], [354, 79], [347, 93], [357, 128], [347, 124], [345, 142], [345, 99]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0014_user_0010_scene_0005_cfg_0004_036422060909#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the object from the scale', and now you are performing subtask 'remove the object from the scale.'\nWith start location [337, 78], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[337, 78], [321, 75], [317, 93], [327, 96], [284, 104], [305, 138], [241, 117], [206, 160], [225, 110], [250, 93]]}" + } + ], + "images": "RH20T_cfg4_task_0014_user_0010_scene_0005_cfg_0004_036422060909#0", + "gt": "[[337, 78], [321, 75], [317, 93], [327, 96], [284, 104], [305, 138], [241, 117], [206, 160], [225, 110], [250, 93]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg2_task_0057_user_0016_scene_0001_cfg_0002_037522062165#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn on the power strips', and now you are performing subtask 'press the button of the second row socket, press the button of the third row socket, press the button of the fourth row socket.'\nYou start from [152, 200]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[152, 200], [145, 227], [132, 230], [143, 225], [156, 234], [143, 225], [135, 250], [130, 240], [133, 216], [159, 183]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg2_task_0057_user_0016_scene_0001_cfg_0002_037522062165#395.jpg", + "gt": "[[152, 200], [145, 227], [132, 230], [143, 225], [156, 234], [143, 225], [135, 250], [130, 240], [133, 216], [159, 183]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "52357_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up a vial and put it in the top compartment of the tray', and now you are performing subtask 'pick up a vial and put it in the top compartment of the tray.'\nYou start from [265, 0]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[265, 0], [264, 43], [245, 63], [243, 46], [218, 41], [196, 50], [206, 48], [205, 61], [186, 57], [223, 20]]}" + } + ], + "images": "52357_exterior_image_1_left#0", + "gt": "[[265, 0], [264, 43], [245, 63], [243, 46], [218, 41], [196, 50], [206, 48], [205, 61], [186, 57], [223, 20]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "2900_exterior_image_2_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the lid on the table then pour the contents from the clear jar into the black pot', and now you are performing subtask 'place the clear jar on the table.'\nYour initial coordinate is [158, 99]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[158, 99], [158, 75], [181, 77], [190, 62], [170, 49], [185, 94], [162, 91], [169, 109], [167, 91], [167, 91]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/2900_exterior_image_2_left#203.jpg", + "gt": "[[158, 99], [158, 75], [181, 77], [190, 62], [170, 49], [185, 94], [162, 91], [169, 109], [167, 91], [167, 91]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "32611_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the pen out of the mug and put it on the counter', and now you are performing subtask 'take the pen out of the mug and put it on the counter.'\nThe trajectory starts at [28.5, 0.0]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[28.5, 0.0], [60.5, 20.0], [87.5, 28.0], [96.5, 48.0], [98.5, 8.0], [101.5, 0.0], [107.5, 0.0], [114.5, 38.0], [121.5, 31.0], [121.5, 31.0]]}" + } + ], + "images": "32611_exterior_image_1_left#0", + "gt": "[[28.5, 0.0], [60.5, 20.0], [87.5, 28.0], [96.5, 48.0], [98.5, 8.0], [101.5, 0.0], [107.5, 0.0], [114.5, 38.0], [121.5, 31.0], [121.5, 31.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "62473_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the cup to the left side of the table', and now you are performing subtask 'move the cup to the left side of the table.'\nFrom start point [206, 53], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[206, 53], [191, 60], [182, 56], [182, 63], [162, 73], [163, 89], [171, 85], [175, 76], [173, 85], [173, 85]]}" + } + ], + "images": "62473_exterior_image_1_left#0", + "gt": "[[206, 53], [191, 60], [182, 56], [182, 63], [162, 73], [163, 89], [171, 85], [175, 76], [173, 85], [173, 85]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "57664_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the spoon out of the cup, place it on the table, and pour the contents of the cup into another cup', and now you are performing subtask 'pick up the cup on the table.'\nWith start location [114, 10], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[114, 10], [133, 40], [166, 37], [158, 54], [166, 55], [169, 30], [186, 23], [195, 81], [183, 42], [152, 48]]}" + } + ], + "images": "57664_exterior_image_2_left#0", + "gt": "[[114, 10], [133, 40], [166, 37], [158, 54], [166, 55], [169, 30], [186, 23], [195, 81], [183, 42], [152, 48]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0061_user_0020_scene_0001_cfg_0007_104122063633#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the lid of the gift box on the table, then take everything out of the gift box and place it all on the table', and now you are performing subtask 'place the object on the tabletop, pick up the block from the gift box, transfer the block from the gift box to the tabletop, place the block on the tabletop.'\nYour initial coordinate is [205, 160]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[205, 160], [192, 148], [185, 148], [178, 159], [192, 218], [189, 131], [196, 119], [196, 141], [199, 116], [217, 110]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg7_task_0061_user_0020_scene_0001_cfg_0007_104122063633#492.jpg", + "gt": "[[205, 160], [192, 148], [185, 148], [178, 159], [192, 218], [189, 131], [196, 119], [196, 141], [199, 116], [217, 110]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "58247_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the microwave door, place the bowl inside the microwave', and now you are performing subtask 'push the microwave door to close.'\nYour starting position is [167, 118]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[167, 118], [170, 123], [161, 134], [157, 129], [162, 106], [177, 96], [154, 99], [152, 71], [150, 63], [145, 63]]}" + } + ], + "images": "58247_exterior_image_1_left#122", + "gt": "[[167, 118], [170, 123], [161, 134], [157, 129], [162, 106], [177, 96], [154, 99], [152, 71], [150, 63], [145, 63]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "87674_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the microwave door', and now you are performing subtask 'push the microwave door to open the microwave door.'\nFrom start point [171, 101], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[171, 101], [170, 79], [174, 74], [174, 92], [186, 98], [180, 104], [177, 96], [180, 105], [162, 112], [158, 120]]}" + } + ], + "images": "87674_exterior_image_1_left#126", + "gt": "[[171, 101], [170, 79], [174, 74], [174, 92], [186, 98], [180, 104], [177, 96], [180, 105], [162, 112], [158, 120]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0038_user_0015_scene_0010_cfg_0001_038522063145#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the cup', and now you are performing subtask 'pick up the cup.'\nYour starting position is [443, 98]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[443, 98], [440, 96], [447, 87], [439, 100], [426, 96], [419, 101], [445, 45], [448, 26], [458, 17], [456, 3]]}" + } + ], + "images": "RH20T_cfg1_task_0038_user_0015_scene_0010_cfg_0001_038522063145#0", + "gt": "[[443, 98], [440, 96], [447, 87], [439, 100], [426, 96], [419, 101], [445, 45], [448, 26], [458, 17], [456, 3]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "13889_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'shift the garment to the right then use the spoon to stir the contents of the bowl', and now you are performing subtask 'pick up the spoon on the table.'\nStart at [98, 93]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[98, 93], [129, 96], [143, 115], [187, 102], [161, 93], [152, 96], [150, 102], [159, 113], [159, 126], [164, 133]]}" + } + ], + "images": "13889_exterior_image_1_left#0", + "gt": "[[98, 93], [129, 96], [143, 115], [187, 102], [161, 93], [152, 96], [150, 102], [159, 113], [159, 126], [164, 133]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg3_task_0057_user_0010_scene_0005_cfg_0003_104122062823#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn them on', and now you are performing subtask 'press the fourth button on the power board.'\nYour starting position is [225, 21]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[225, 21], [217, 29], [218, 33], [217, 14], [222, 3], [230, 0], [285, 0], [277, 0], [284, 12], [277, 7]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg3_task_0057_user_0010_scene_0005_cfg_0003_104122062823#251.jpg", + "gt": "[[225, 21], [217, 29], [218, 33], [217, 14], [222, 3], [230, 0], [285, 0], [277, 0], [284, 12], [277, 7]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "50798_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the black spoon in the cutlery stand', and now you are performing subtask 'put the black spoon in the cutlery stand.'\nYour initial coordinate is [111, 68]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[111, 68], [120, 59], [164, 97], [159, 61], [164, 64], [182, 44], [223, 31], [235, 37], [236, 50], [215, 25]]}" + } + ], + "images": "50798_exterior_image_1_left#0", + "gt": "[[111, 68], [120, 59], [164, 97], [159, 61], [164, 64], [182, 44], [223, 31], [235, 37], [236, 50], [215, 25]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "53120_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the drawer, then remove the banana plush toy out of the drawer, then close the drawer', and now you are performing subtask 'pull the drawer handle to open the drawer.'\nFrom start point [214, 65], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[214, 65], [197, 74], [201, 74], [204, 86], [190, 85], [194, 90], [190, 98], [211, 98], [197, 83], [189, 87]]}" + } + ], + "images": "53120_exterior_image_1_left#0", + "gt": "[[214, 65], [197, 74], [201, 74], [204, 86], [190, 85], [194, 90], [190, 98], [211, 98], [197, 83], [189, 87]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0058_user_0015_scene_0003_cfg_0001_750612070851#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn off the power strips', and now you are performing subtask 'press the first button on the power socket.'\nStarting at [316, 162], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[316, 162], [295, 157], [213, 168], [163, 149], [136, 149], [136, 142], [112, 157], [110, 173], [125, 186], [125, 186]]}" + } + ], + "images": "RH20T_cfg1_task_0058_user_0015_scene_0003_cfg_0001_750612070851#0", + "gt": "[[316, 162], [295, 157], [213, 168], [163, 149], [136, 149], [136, 142], [112, 157], [110, 173], [125, 186], [125, 186]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "81300_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the pen out of the bowl and put it on the table', and now you are performing subtask 'take the pen out of the bowl and put it on the table.'\nThe trajectory starts at [219, 0]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[219, 0], [196, 20], [180, 51], [177, 21], [172, 16], [166, 22], [156, 54], [159, 82], [169, 100], [165, 87]]}" + } + ], + "images": "81300_exterior_image_2_left#0", + "gt": "[[219, 0], [196, 20], [180, 51], [177, 21], [172, 16], [166, 22], [156, 54], [159, 82], [169, 100], [165, 87]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0081_user_0007_scene_0003_cfg_0005_104422070044#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the leg of the glasses (with one hand)', and now you are performing subtask 'fold the legs of the glasses to unfold them.'\nStarting at [382, 124], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[382, 124], [382, 137], [384, 142], [386, 162], [387, 163], [378, 163], [376, 161], [375, 157], [377, 133], [385, 121]]}" + } + ], + "images": "RH20T_cfg5_task_0081_user_0007_scene_0003_cfg_0005_104422070044#142", + "gt": "[[382, 124], [382, 137], [384, 142], [386, 162], [387, 163], [378, 163], [376, 161], [375, 157], [377, 133], [385, 121]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg2_task_0034_user_0003_scene_0006_cfg_0002_037522062165#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the squares into a pyramid shape', and now you are performing subtask 'pick up the second square next to the first square, transfer the second square from the countertop to the left side of the first square, place the second square to the left of the first square.'\nYou start from [190, 205]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[190, 205], [197, 195], [204, 203], [195, 204], [203, 206], [211, 180], [212, 187], [203, 192], [188, 180], [183, 198]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg2_task_0034_user_0003_scene_0006_cfg_0002_037522062165#214.jpg", + "gt": "[[190, 205], [197, 195], [204, 203], [195, 204], [203, 206], [211, 180], [212, 187], [203, 192], [188, 180], [183, 198]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "63177_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the objects on the plate and put them in the bin', and now you are performing subtask 'take the object from the plate and move it to the bowl.'\nThe trajectory starts at [199, 49]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[199, 49], [192, 62], [190, 52], [181, 35], [185, 34], [184, 36], [183, 34], [186, 29], [195, 24], [195, 24]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/63177_exterior_image_1_left#202.jpg", + "gt": "[[199, 49], [192, 62], [190, 52], [181, 35], [185, 34], [184, 36], [183, 34], [186, 29], [195, 24], [195, 24]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "38930_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the pen and place it in the bowl', and now you are performing subtask 'pick up the pen and place it in the bowl.'\nFrom start point [0.0, 24.5], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[0.0, 24.5], [26.0, 58.5], [30.0, 53.5], [28.0, 57.5], [59.0, 68.5], [99.0, 106.5], [116.0, 113.5], [116.0, 94.5], [127.0, 83.5], [163.0, 96.5]]}" + } + ], + "images": "38930_exterior_image_1_left#0", + "gt": "[[0.0, 24.5], [26.0, 58.5], [30.0, 53.5], [28.0, 57.5], [59.0, 68.5], [99.0, 106.5], [116.0, 113.5], [116.0, 94.5], [127.0, 83.5], [163.0, 96.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0061_user_0007_scene_0008_cfg_0005_037522062165#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the first block out of the box and place it on the table, then take the second block and place it on top of the first block', and now you are performing subtask 'place the first block on the table, pick up the second block in the box, transfer the second block from the box to above the first block, place the second block on the first block.'\nFrom start point [336, 260], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[336, 260], [332, 242], [281, 216], [254, 210], [242, 226], [310, 218], [329, 229], [331, 250], [326, 221], [274, 180]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0061_user_0007_scene_0008_cfg_0005_037522062165#286.jpg", + "gt": "[[336, 260], [332, 242], [281, 216], [254, 210], [242, 226], [310, 218], [329, 229], [331, 250], [326, 221], [274, 180]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "44464_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the plush toy out of the box and put it on the black tray', and now you are performing subtask 'throw the green fruit plush toy on the black tray.'\nStarting at [188, 81], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[188, 81], [145, 98], [135, 111], [143, 110], [136, 119], [170, 101], [199, 101], [212, 107], [205, 86], [208, 70]]}" + } + ], + "images": "44464_exterior_image_1_left#190", + "gt": "[[188, 81], [145, 98], [135, 111], [143, 110], [136, 119], [170, 101], [199, 101], [212, 107], [205, 86], [208, 70]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "30882_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the rod and stir in the silver cup', and now you are performing subtask 'pick up the rod and stir in the silver cup.'\nStart at [131, 41]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[131, 41], [135, 58], [108, 97], [107, 74], [112, 91], [114, 65], [115, 91], [117, 66], [116, 98], [115, 66]]}" + } + ], + "images": "30882_exterior_image_2_left#0", + "gt": "[[131, 41], [135, 58], [108, 97], [107, 74], [112, 91], [114, 65], [115, 91], [117, 66], [116, 98], [115, 66]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg3_task_0023_user_0010_scene_0004_cfg_0003_104422070011#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn on the power strip by pressing the button', and now you are performing subtask 'turn on the power strip by pressing the button.'\nYour initial coordinate is [330, 110]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[330, 110], [333, 132], [307, 130], [328, 120], [326, 98], [253, 175], [261, 194], [220, 163], [232, 152], [270, 182]]}" + } + ], + "images": "RH20T_cfg3_task_0023_user_0010_scene_0004_cfg_0003_104422070011#0", + "gt": "[[330, 110], [333, 132], [307, 130], [328, 120], [326, 98], [253, 175], [261, 194], [220, 163], [232, 152], [270, 182]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg2_task_0015_user_0006_scene_0003_cfg_0002_105422061350#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'play the drum', and now you are performing subtask 'play the drum.'\nBegin at [386, 157] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[386, 157], [428, 113], [480, 114], [479, 92], [461, 145], [446, 156], [473, 165], [459, 185], [468, 177], [473, 185]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg2_task_0015_user_0006_scene_0003_cfg_0002_105422061350#0.jpg", + "gt": "[[386, 157], [428, 113], [480, 114], [479, 92], [461, 145], [446, 156], [473, 165], [459, 185], [468, 177], [473, 185]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "31068_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the marker from the cup and put it on the book', and now you are performing subtask 'remove the marker from the cup and put it on the book.'\nFrom start point [188, 68], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[188, 68], [179, 69], [181, 81], [187, 77], [195, 50], [193, 75], [208, 92], [197, 91], [203, 75], [195, 66]]}" + } + ], + "images": "31068_exterior_image_1_left#0", + "gt": "[[188, 68], [179, 69], [181, 81], [187, 77], [195, 50], [193, 75], [208, 92], [197, 91], [203, 75], [195, 66]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg3_task_0003_user_0016_scene_0001_cfg_0003_104122063550#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press three buttons from left to right in sequence', and now you are performing subtask 'press the green button in the middle, press the red button on the left.'\nYour initial coordinate is [305, 228]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[305, 228], [283, 160], [269, 145], [263, 148], [262, 130], [270, 129], [276, 135], [269, 127], [270, 156], [273, 154]]}" + } + ], + "images": "RH20T_cfg3_task_0003_user_0016_scene_0001_cfg_0003_104122063550#214", + "gt": "[[305, 228], [283, 160], [269, 145], [263, 148], [262, 130], [270, 129], [276, 135], [269, 127], [270, 156], [273, 154]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "61768_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the marker out of the pot and put it on the table', and now you are performing subtask 'take the marker out of the pot and put it on the table.'\nThe trajectory starts at [165, 0]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[165, 0], [170, 69], [176, 66], [177, 55], [187, 50], [195, 54], [210, 73], [211, 81], [207, 85], [208, 72]]}" + } + ], + "images": "61768_exterior_image_1_left#0", + "gt": "[[165, 0], [170, 69], [176, 66], [177, 55], [187, 50], [195, 54], [210, 73], [211, 81], [207, 85], [208, 72]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg2_task_0008_user_0007_scene_0004_cfg_0002_104422070044#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'swinging the flag', and now you are performing subtask 'swinging the flag.'\nYour initial coordinate is [311, 188]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[311, 188], [308, 193], [324, 227], [317, 194], [300, 174], [257, 156], [327, 172], [272, 160], [312, 176], [324, 199]]}" + } + ], + "images": "RH20T_cfg2_task_0008_user_0007_scene_0004_cfg_0002_104422070044#0", + "gt": "[[311, 188], [308, 193], [324, 227], [317, 194], [300, 174], [257, 156], [327, 172], [272, 160], [312, 176], [324, 199]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0029_user_0014_scene_0005_cfg_0006_104122060811#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the drawer', and now you are performing subtask 'open the drawer.'\nYou begin at [385, 127]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[385, 127], [384, 121], [387, 122], [393, 133], [411, 143], [386, 150], [349, 145], [348, 148], [350, 145], [370, 148]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg6_task_0029_user_0014_scene_0005_cfg_0006_104122060811#0.jpg", + "gt": "[[385, 127], [384, 121], [387, 122], [393, 133], [411, 143], [386, 150], [349, 145], [348, 148], [350, 145], [370, 148]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0037_user_0016_scene_0002_cfg_0004_036422060909#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'pick up the third block on the surface, transfer the third block from the surface to the position above the first block, place the third block on the first block, pick up the fourth block on the surface.'\nStarting at [345, 128], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[345, 128], [341, 109], [313, 87], [302, 88], [297, 95], [327, 107], [315, 94], [299, 96], [300, 149], [290, 187]]}" + } + ], + "images": "RH20T_cfg4_task_0037_user_0016_scene_0002_cfg_0004_036422060909#153", + "gt": "[[345, 128], [341, 109], [313, 87], [302, 88], [297, 95], [327, 107], [315, 94], [299, 96], [300, 149], [290, 187]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "20823_exterior_image_2_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the banana inside the first drawer from the right then close the drawer', and now you are performing subtask 'push the first drawer on the right.'\nWith start location [197, 97], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[197, 97], [191, 86], [176, 90], [166, 101], [166, 116], [191, 131], [204, 115], [189, 97], [185, 68], [175, 52]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/20823_exterior_image_2_left#224.jpg", + "gt": "[[197, 97], [191, 86], [176, 90], [166, 101], [166, 116], [191, 131], [204, 115], [189, 97], [185, 68], [175, 52]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "33943_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the carrot plush toy into the pot', and now you are performing subtask 'put the carrot plush toy into the pot.'\nStarting at [34.5, 4.0], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[34.5, 4.0], [102.5, 61.0], [119.5, 89.0], [112.5, 89.0], [109.5, 84.0], [113.5, 77.0], [129.5, 76.0], [133.5, 83.0], [127.5, 77.0], [111.5, 75.0]]}" + } + ], + "images": "33943_exterior_image_1_left#0", + "gt": "[[34.5, 4.0], [102.5, 61.0], [119.5, 89.0], [112.5, 89.0], [109.5, 84.0], [113.5, 77.0], [129.5, 76.0], [133.5, 83.0], [127.5, 77.0], [111.5, 75.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "61794_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the mug with the marker to the left', and now you are performing subtask 'pull the bowl to the left front of the table.'\nStart at [162, 73]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[162, 73], [159, 80], [165, 103], [159, 108], [161, 121], [163, 106], [160, 88], [157, 87], [156, 96], [138, 91]]}" + } + ], + "images": "61794_exterior_image_1_left#98", + "gt": "[[162, 73], [159, 80], [165, 103], [159, 108], [161, 121], [163, 106], [160, 88], [157, 87], [156, 96], [138, 91]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0001_user_0014_scene_0010_cfg_0005_104122063678#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the button from top to bottom', and now you are performing subtask 'press the button from top to bottom.'\nFrom start point [323, 132], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[323, 132], [338, 126], [377, 118], [390, 96], [385, 158], [375, 166], [364, 181], [370, 174], [370, 183], [378, 150]]}" + } + ], + "images": "RH20T_cfg5_task_0001_user_0014_scene_0010_cfg_0005_104122063678#0", + "gt": "[[323, 132], [338, 126], [377, 118], [390, 96], [385, 158], [375, 166], [364, 181], [370, 174], [370, 183], [378, 150]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0127_user_0010_scene_0001_cfg_0004_036422060909#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'plug in the power cord of the desk lamp, turn on the socket, and light up the desk lamp', and now you are performing subtask 'pick up the power cable on the table, transfer the cable from the tabletop to the corresponding socket above, insert the power cable into the socket on the table.'\nYou start from [341, 79]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[341, 79], [311, 81], [320, 115], [282, 99], [269, 103], [280, 116], [224, 129], [234, 151], [336, 115], [328, 135]]}" + } + ], + "images": "RH20T_cfg4_task_0127_user_0010_scene_0001_cfg_0004_036422060909#0", + "gt": "[[341, 79], [311, 81], [320, 115], [282, 99], [269, 103], [280, 116], [224, 129], [234, 151], [336, 115], [328, 135]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0003_user_0010_scene_0005_cfg_0005_104122063678#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press three buttons from left to right in sequence', and now you are performing subtask 'press the green button on the right, press the red button in the middle.'\nWith start location [347, 244], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[347, 244], [359, 225], [359, 220], [340, 197], [335, 197], [335, 199], [338, 196], [335, 203], [338, 203], [338, 196]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0003_user_0010_scene_0005_cfg_0005_104122063678#277.jpg", + "gt": "[[347, 244], [359, 225], [359, 220], [340, 197], [335, 197], [335, 199], [338, 196], [335, 203], [338, 203], [338, 196]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0044_user_0010_scene_0007_cfg_0005_105422061350#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up a bag of things', and now you are performing subtask 'pick up a bag of things.'\nStarting at [272, 50], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[272, 50], [269, 70], [252, 63], [250, 68], [239, 68], [239, 75], [245, 12], [240, 0], [286, 0], [291, 9]]}" + } + ], + "images": "RH20T_cfg5_task_0044_user_0010_scene_0007_cfg_0005_105422061350#0", + "gt": "[[272, 50], [269, 70], [252, 63], [250, 68], [239, 68], [239, 75], [245, 12], [240, 0], [286, 0], [291, 9]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0094_user_0014_scene_0010_cfg_0001_039422060546#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open a box', and now you are performing subtask 'fold the first lid on the box on the table.'\nWith start location [265, 124], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[265, 124], [192, 192], [151, 188], [133, 201], [138, 207], [132, 199], [152, 247], [138, 224], [150, 202], [182, 204]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0094_user_0014_scene_0010_cfg_0001_039422060546#0.jpg", + "gt": "[[265, 124], [192, 192], [151, 188], [133, 201], [138, 207], [132, 199], [152, 247], [138, 224], [150, 202], [182, 204]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "56943_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the fork', and now you are performing subtask 'move the fork.'\nYour initial coordinate is [118, 45]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[118, 45], [140, 70], [150, 86], [147, 87], [159, 94], [166, 109], [164, 117], [165, 95], [168, 114], [172, 93]]}" + } + ], + "images": "56943_exterior_image_1_left#0", + "gt": "[[118, 45], [140, 70], [150, 86], [147, 87], [159, 94], [166, 109], [164, 117], [165, 95], [168, 114], [172, 93]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "29131_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'rotate the second rod forwards', and now you are performing subtask 'rotate the second rod forwards.'\nYou start from [132, 65]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[132, 65], [169, 47], [212, 51], [236, 63], [228, 65], [234, 64], [240, 78], [234, 81], [250, 92], [222, 84]]}" + } + ], + "images": "29131_exterior_image_1_left#0", + "gt": "[[132, 65], [169, 47], [212, 51], [236, 63], [228, 65], [234, 64], [240, 78], [234, 81], [250, 92], [222, 84]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "81300_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the pen out of the bowl and put it on the table', and now you are performing subtask 'take the pen out of the bowl and put it on the table.'\nYou start from [37, 3]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[37, 3], [144, 74], [172, 119], [177, 86], [163, 59], [143, 49], [127, 51], [115, 67], [114, 82], [121, 77]]}" + } + ], + "images": "81300_exterior_image_1_left#0", + "gt": "[[37, 3], [144, 74], [172, 119], [177, 86], [163, 59], [143, 49], [127, 51], [115, 67], [114, 82], [121, 77]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg3_task_0003_user_0016_scene_0002_cfg_0003_104122062295#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the three buttons in sequence', and now you are performing subtask 'press the green button in the middle, press the red button on the left.'\nYour initial coordinate is [244, 149]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[244, 149], [255, 141], [324, 186], [343, 234], [335, 263], [340, 233], [333, 222], [330, 235], [362, 276], [307, 239]]}" + } + ], + "images": "RH20T_cfg3_task_0003_user_0016_scene_0002_cfg_0003_104122062295#194", + "gt": "[[244, 149], [255, 141], [324, 186], [343, 234], [335, 263], [340, 233], [333, 222], [330, 235], [362, 276], [307, 239]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg2_task_0104_user_0007_scene_0007_cfg_0002_037522062165#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'drag the plate back after holding it down', and now you are performing subtask 'drag the plate back after holding it down.'\nFrom start point [278, 175], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[278, 175], [271, 189], [223, 203], [246, 212], [239, 200], [286, 229], [271, 227], [293, 254], [268, 211], [268, 211]]}" + } + ], + "images": "RH20T_cfg2_task_0104_user_0007_scene_0007_cfg_0002_037522062165#0", + "gt": "[[278, 175], [271, 189], [223, 203], [246, 212], [239, 200], [286, 229], [271, 227], [293, 254], [268, 211], [268, 211]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0094_user_0007_scene_0009_cfg_0005_104122061850#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open a box', and now you are performing subtask 'press the cardboard box on the side, press the cardboard box on the side.'\nYou begin at [350, 129]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[350, 129], [335, 128], [328, 131], [321, 122], [293, 116], [293, 120], [294, 116], [312, 119], [325, 127], [335, 138]]}" + } + ], + "images": "RH20T_cfg5_task_0094_user_0007_scene_0009_cfg_0005_104122061850#406", + "gt": "[[350, 129], [335, 128], [328, 131], [321, 122], [293, 116], [293, 120], [294, 116], [312, 119], [325, 127], [335, 138]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "62432_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stand the box upright then put the plastic items inside', and now you are performing subtask 'place the plastic item inside the box.'\nFrom start point [108.0, 111.5], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[108.0, 111.5], [101.0, 124.5], [111.0, 132.5], [115.0, 127.5], [119.0, 130.5], [110.0, 116.5], [115.0, 65.5], [133.0, 54.5], [136.0, 83.5], [119.0, 65.5]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/62432_exterior_image_1_left#266.jpg", + "gt": "[[108.0, 111.5], [101.0, 124.5], [111.0, 132.5], [115.0, 127.5], [119.0, 130.5], [110.0, 116.5], [115.0, 65.5], [133.0, 54.5], [136.0, 83.5], [119.0, 65.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "43202_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close the bottom drawer of the right cabinet', and now you are performing subtask 'close the bottom drawer of the right cabinet.'\nStarting at [111, 111], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[111, 111], [120, 107], [139, 107], [161, 117], [169, 109], [177, 107], [175, 107], [185, 119], [187, 112], [190, 112]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/43202_exterior_image_2_left#0.jpg", + "gt": "[[111, 111], [120, 107], [139, 107], [161, 117], [169, 109], [177, 107], [175, 107], [185, 119], [187, 112], [190, 112]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0065_user_0015_scene_0012_cfg_0004_104122062823#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with small Lego blocks', and now you are performing subtask 'pick up black block on the left side of the table, transfer black block from the left side of the table to the central base, place black block on the base, push black block to the right, push black block to the left, push black block to the left again, press black block down, press black block down again, press black block down, press black block down, press black block down, pick up red small block on the left side of the table.'\nThe trajectory starts at [291, 0]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[291, 0], [249, 0], [259, 11], [225, 24], [238, 49], [234, 30], [277, 51], [317, 89], [259, 60], [259, 60]]}" + } + ], + "images": "RH20T_cfg4_task_0065_user_0015_scene_0012_cfg_0004_104122062823#0", + "gt": "[[291, 0], [249, 0], [259, 11], [225, 24], [238, 49], [234, 30], [277, 51], [317, 89], [259, 60], [259, 60]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg3_task_0038_user_0010_scene_0003_cfg_0003_104422070011#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the cup to the top of the cup rack and then place it down', and now you are performing subtask 'move the cup to the top of the cup rack and then place it down.'\nBegin at [328, 107] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[328, 107], [361, 154], [353, 183], [327, 176], [310, 136], [289, 120], [300, 127], [287, 101], [297, 105], [306, 83]]}" + } + ], + "images": "RH20T_cfg3_task_0038_user_0010_scene_0003_cfg_0003_104422070011#0", + "gt": "[[328, 107], [361, 154], [353, 183], [327, 176], [310, 136], [289, 120], [300, 127], [287, 101], [297, 105], [306, 83]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "10074_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the blue block and put it on top of the green block', and now you are performing subtask 'pick up the blue block and put it on top of the green block.'\nFrom start point [171, 2], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[171, 2], [186, 52], [181, 55], [168, 46], [164, 0], [148, 7], [155, 18], [144, 1], [129, 0], [141, 2]]}" + } + ], + "images": "10074_exterior_image_1_left#0", + "gt": "[[171, 2], [186, 52], [181, 55], [168, 46], [164, 0], [148, 7], [155, 18], [144, 1], [129, 0], [141, 2]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0005_user_0008_scene_0001_cfg_0001_038522062547#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'approach and touch the side of the small block', and now you are performing subtask 'approach and touch the side of the small block.'\nYou start from [405, 135]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[405, 135], [407, 134], [404, 134], [408, 144], [403, 195], [418, 223], [418, 247], [419, 231], [408, 192], [411, 191]]}" + } + ], + "images": "RH20T_cfg1_task_0005_user_0008_scene_0001_cfg_0001_038522062547#0", + "gt": "[[405, 135], [407, 134], [404, 134], [408, 144], [403, 195], [418, 223], [418, 247], [419, 231], [408, 192], [411, 191]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0016_user_0014_scene_0001_cfg_0001_038522062547#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'hit the pool ball', and now you are performing subtask 'pick up the pool ball from the surface.'\nStarting at [407, 136], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[407, 136], [424, 104], [416, 78], [421, 26], [402, 19], [392, 29], [416, 28], [415, 39], [396, 25], [391, 51]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0016_user_0014_scene_0001_cfg_0001_038522062547#0.jpg", + "gt": "[[407, 136], [424, 104], [416, 78], [421, 26], [402, 19], [392, 29], [416, 28], [415, 39], [396, 25], [391, 51]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "54044_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up and put down the green block, then put the salt cellar into the pot and the green block into the sink', and now you are performing subtask 'pick up the salt cellar on the countertop.'\nYou begin at [229, 68]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[229, 68], [204, 79], [200, 106], [209, 102], [214, 90], [212, 104], [204, 104], [207, 98], [221, 98], [215, 94]]}" + } + ], + "images": "54044_exterior_image_1_left#0", + "gt": "[[229, 68], [204, 79], [200, 106], [209, 102], [214, 90], [212, 104], [204, 104], [207, 98], [221, 98], [215, 94]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0110_user_0015_scene_0003_cfg_0001_035622060973#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the pencil out from the pencil sharpener', and now you are performing subtask 'take the pencil out from the pencil sharpener.'\nBegin at [247, 131] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[247, 131], [254, 185], [257, 194], [265, 197], [228, 221], [263, 240], [265, 258], [271, 258], [251, 208], [251, 208]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0110_user_0015_scene_0003_cfg_0001_035622060973#0.jpg", + "gt": "[[247, 131], [254, 185], [257, 194], [265, 197], [228, 221], [263, 240], [265, 258], [271, 258], [251, 208], [251, 208]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "83937_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the rectangle block from the table and put it on top of the toy tower blocks', and now you are performing subtask 'pick up the rectangular block from the table.'\nYour starting position is [264, 24]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[264, 24], [186, 73], [156, 75], [152, 82], [145, 82], [166, 82], [184, 88], [177, 88], [168, 107], [163, 105]]}" + } + ], + "images": "83937_exterior_image_2_left#0", + "gt": "[[264, 24], [186, 73], [156, 75], [152, 82], [145, 82], [166, 82], [184, 88], [177, 88], [168, 107], [163, 105]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0071_user_0015_scene_0010_cfg_0004_104122062823#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close a sliding window', and now you are performing subtask 'push the handle of the sliding window to close the window.'\nStart at [291, 0]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[291, 0], [310, 0], [297, 0], [290, 3], [282, 22], [301, 59], [299, 75], [315, 88], [332, 137], [334, 186]]}" + } + ], + "images": "RH20T_cfg4_task_0071_user_0015_scene_0010_cfg_0004_104122062823#0", + "gt": "[[291, 0], [310, 0], [297, 0], [290, 3], [282, 22], [301, 59], [299, 75], [315, 88], [332, 137], [334, 186]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "43239_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the towel', and now you are performing subtask 'shake the towel on the table.'\nThe trajectory starts at [276, 29]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[276, 29], [270, 36], [211, 45], [205, 52], [208, 58], [182, 90], [202, 81], [226, 96], [209, 90], [191, 95]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/43239_exterior_image_1_left#0.jpg", + "gt": "[[276, 29], [270, 36], [211, 45], [205, 52], [208, 58], [182, 90], [202, 81], [226, 96], [209, 90], [191, 95]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "57652_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'hang up the cloth on the glass barrier', and now you are performing subtask 'pick up the cloth from the table.'\nWith start location [78, 46], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[78, 46], [96, 83], [134, 124], [136, 131], [128, 141], [128, 132], [121, 122], [119, 69], [119, 79], [141, 111]]}" + } + ], + "images": "57652_exterior_image_2_left#0", + "gt": "[[78, 46], [96, 83], [134, 124], [136, 131], [128, 141], [128, 132], [121, 122], [119, 69], [119, 79], [141, 111]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0044_user_0010_scene_0008_cfg_0005_104122061850#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up a bag of things', and now you are performing subtask 'pick up a bag of things.'\nYou start from [311, 50]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[311, 50], [337, 88], [347, 96], [344, 117], [352, 141], [348, 139], [349, 150], [350, 121], [316, 43], [317, 38]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0044_user_0010_scene_0008_cfg_0005_104122061850#0.jpg", + "gt": "[[311, 50], [337, 88], [347, 96], [344, 117], [352, 141], [348, 139], [349, 150], [350, 121], [316, 43], [317, 38]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "11614_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the big orange plush toy out of the box and put it on the tray', and now you are performing subtask 'take the big orange plush toy out of the box and put it on the tray.'\nBegin at [187, 20] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[187, 20], [187, 29], [160, 64], [168, 90], [163, 98], [158, 75], [168, 52], [214, 23], [226, 21], [226, 33]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/11614_exterior_image_1_left#0.jpg", + "gt": "[[187, 20], [187, 29], [160, 64], [168, 90], [163, 98], [158, 75], [168, 52], [214, 23], [226, 21], [226, 33]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0003_user_0014_scene_0010_cfg_0006_104122063633#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press three buttons from left to right in sequence', and now you are performing subtask 'press the red button at the bottom.'\nYour initial coordinate is [233, 118]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[233, 118], [226, 117], [224, 114], [209, 114], [198, 118], [194, 122], [192, 120], [196, 119], [190, 125], [183, 121]]}" + } + ], + "images": "RH20T_cfg6_task_0003_user_0014_scene_0010_cfg_0006_104122063633#0", + "gt": "[[233, 118], [226, 117], [224, 114], [209, 114], [198, 118], [194, 122], [192, 120], [196, 119], [190, 125], [183, 121]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "88052_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'place the lid on the stove', and now you are performing subtask 'place the lid on the stove.'\nStarting at [76, 24], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[76, 24], [90, 40], [83, 55], [94, 71], [86, 89], [90, 97], [81, 105], [81, 85], [92, 107], [91, 75]]}" + } + ], + "images": "88052_exterior_image_2_left#0", + "gt": "[[76, 24], [90, 40], [83, 55], [94, 71], [86, 89], [90, 97], [81, 105], [81, 85], [92, 107], [91, 75]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "70956_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the lid', and now you are performing subtask 'open the lid.'\nYou start from [97, 66]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[97, 66], [98, 75], [91, 85], [91, 91], [95, 88], [95, 97], [99, 99], [89, 97], [93, 58], [98, 71]]}" + } + ], + "images": "70956_exterior_image_2_left#0", + "gt": "[[97, 66], [98, 75], [91, 85], [91, 91], [95, 88], [95, 97], [99, 99], [89, 97], [93, 58], [98, 71]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "4810_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove one white plate from the dishwasher and place it on top of the white plate on the countertop', and now you are performing subtask 'remove one white plate from the dishwasher and place it on top of the white plate on the countertop.'\nStarting at [193, 70], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[193, 70], [129, 94], [107, 111], [97, 133], [106, 155], [101, 180], [111, 166], [116, 76], [120, 97], [161, 96]]}" + } + ], + "images": "4810_exterior_image_1_left#0", + "gt": "[[193, 70], [129, 94], [107, 111], [97, 133], [106, 155], [101, 180], [111, 166], [116, 76], [120, 97], [161, 96]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "22632_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the towel then fold it again', and now you are performing subtask 'fold the towel.'\nYour starting position is [230, 108]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[230, 108], [225, 132], [182, 124], [190, 130], [181, 133], [177, 102], [216, 69], [242, 83], [273, 50], [273, 50]]}" + } + ], + "images": "22632_exterior_image_1_left#367", + "gt": "[[230, 108], [225, 132], [182, 124], [190, 130], [181, 133], [177, 102], [216, 69], [242, 83], [273, 50], [273, 50]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "42632_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the lid', and now you are performing subtask 'press the lid.'\nStart at [173, 113]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[173, 113], [165, 120], [165, 123], [167, 123], [169, 128], [166, 119], [176, 98], [178, 97], [174, 100], [175, 98]]}" + } + ], + "images": "42632_exterior_image_1_left#156", + "gt": "[[173, 113], [165, 120], [165, 123], [167, 123], [169, 128], [166, 119], [176, 98], [178, 97], [174, 100], [175, 98]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "33104_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close the top drawer of the gray file cabinet', and now you are performing subtask 'close the top drawer of the gray file cabinet.'\nYou begin at [223, 179]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[223, 179], [213, 168], [209, 159], [206, 147], [196, 133], [170, 121], [165, 120], [146, 110], [142, 109], [139, 110]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/33104_exterior_image_1_left#0.jpg", + "gt": "[[223, 179], [213, 168], [209, 159], [206, 147], [196, 133], [170, 121], [165, 120], [146, 110], [142, 109], [139, 110]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "15364_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the marker from the glass cup and put it on the table', and now you are performing subtask 'pick up the marker from the glass cup and put it on the table.'\nStarting at [192.5, 4.0], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[192.5, 4.0], [184.5, 31.0], [192.5, 33.0], [174.5, 42.0], [174.5, 64.0], [174.5, 46.0], [185.5, 52.0], [202.5, 72.0], [203.5, 85.0], [184.5, 55.0]]}" + } + ], + "images": "15364_exterior_image_1_left#0", + "gt": "[[192.5, 4.0], [184.5, 31.0], [192.5, 33.0], [174.5, 42.0], [174.5, 64.0], [174.5, 46.0], [185.5, 52.0], [202.5, 72.0], [203.5, 85.0], [184.5, 55.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg2_task_0015_user_0006_scene_0003_cfg_0002_037522062165#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'play the drum', and now you are performing subtask 'play the drum.'\nYou begin at [283, 174]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[283, 174], [224, 131], [226, 89], [194, 86], [232, 120], [227, 142], [240, 121], [245, 142], [248, 129], [293, 115]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg2_task_0015_user_0006_scene_0003_cfg_0002_037522062165#0.jpg", + "gt": "[[283, 174], [224, 131], [226, 89], [194, 86], [232, 120], [227, 142], [240, 121], [245, 142], [248, 129], [293, 115]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "81224_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the lid on the pot', and now you are performing subtask 'put the lid on the pot.'\nYou begin at [21, 0]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[21, 0], [97, 52], [125, 87], [123, 98], [97, 73], [105, 58], [146, 52], [162, 67], [169, 96], [154, 76]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/81224_exterior_image_1_left#0.jpg", + "gt": "[[21, 0], [97, 52], [125, 87], [123, 98], [97, 73], [105, 58], [146, 52], [162, 67], [169, 96], [154, 76]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "79181_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'use the spatula to stir the contents in the bowl', and now you are performing subtask 'use the spatula to stir the contents in the bowl.'\nStarting at [264.0, 90.5], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[264.0, 90.5], [212.0, 108.5], [195.0, 132.5], [224.0, 103.5], [202.0, 114.5], [203.0, 98.5], [211.0, 106.5], [193.0, 126.5], [208.0, 116.5], [185.0, 119.5]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/79181_exterior_image_1_left#0.jpg", + "gt": "[[264.0, 90.5], [212.0, 108.5], [195.0, 132.5], [224.0, 103.5], [202.0, 114.5], [203.0, 98.5], [211.0, 106.5], [193.0, 126.5], [208.0, 116.5], [185.0, 119.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "14053_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the small brush from the mug and put it on the table. pick up the mug and slightly move it to the right. then pick up the small brush from the table and put it back in the mug', and now you are performing subtask 'place the mug on the table.'\nStarting at [160, 49], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[160, 49], [157, 48], [155, 51], [158, 57], [162, 53], [170, 52], [185, 61], [188, 77], [184, 85], [183, 73]]}" + } + ], + "images": "14053_exterior_image_1_left#192", + "gt": "[[160, 49], [157, 48], [155, 51], [158, 57], [162, 53], [170, 52], [185, 61], [188, 77], [184, 85], [183, 73]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "83691_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'throw the tissue into the trash can', and now you are performing subtask 'throw the tissue into the trash can.'\nFrom start point [204, 0], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[204, 0], [177, 20], [183, 20], [170, 31], [157, 53], [156, 62], [173, 46], [182, 42], [195, 42], [193, 40]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/83691_exterior_image_2_left#0.jpg", + "gt": "[[204, 0], [177, 20], [183, 20], [170, 31], [157, 53], [156, 62], [173, 46], [182, 42], [195, 42], [193, 40]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "57652_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'hang up the cloth on the glass barrier', and now you are performing subtask 'place the cloth on the glass barrier.'\nWith start location [203, 122], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[203, 122], [201, 128], [191, 116], [177, 134], [166, 76], [166, 40], [158, 9], [154, 18], [162, 39], [165, 26]]}" + } + ], + "images": "57652_exterior_image_1_left#186", + "gt": "[[203, 122], [201, 128], [191, 116], [177, 134], [166, 76], [166, 40], [158, 9], [154, 18], [162, 39], [165, 26]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "44936_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the water bottle forward', and now you are performing subtask 'pick up the water bottle from the middle of the table.'\nWith start location [166, 112], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[166, 112], [156, 112], [155, 131], [148, 146], [160, 140], [173, 156], [183, 157], [157, 139], [130, 142], [134, 150]]}" + } + ], + "images": "44936_exterior_image_1_left#0", + "gt": "[[166, 112], [156, 112], [155, 131], [148, 146], [160, 140], [173, 156], [183, 157], [157, 139], [130, 142], [134, 150]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "84139_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'hang the cloth on the brown object', and now you are performing subtask 'hang the cloth on the brown object.'\nBegin at [135, 43] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[135, 43], [137, 66], [120, 95], [112, 124], [115, 160], [122, 159], [114, 127], [128, 71], [139, 58], [135, 71]]}" + } + ], + "images": "84139_exterior_image_2_left#0", + "gt": "[[135, 43], [137, 66], [120, 95], [112, 124], [115, 160], [122, 159], [114, 127], [128, 71], [139, 58], [135, 71]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0004_user_0020_scene_0005_cfg_0007_104122064161#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the big block from the desktop and move it to the left', and now you are performing subtask 'pick up the big block from the desktop and move it to the left.'\nFrom start point [337, 115], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[337, 115], [346, 195], [368, 218], [371, 254], [373, 203], [361, 173], [386, 143], [373, 113], [352, 128], [373, 113]]}" + } + ], + "images": "RH20T_cfg7_task_0004_user_0020_scene_0005_cfg_0007_104122064161#0", + "gt": "[[337, 115], [346, 195], [368, 218], [371, 254], [373, 203], [361, 173], [386, 143], [373, 113], [352, 128], [373, 113]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0046_user_0020_scene_0004_cfg_0006_104122063633#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the cup on the cup rack', and now you are performing subtask 'put the cup on the cup rack.'\nYou start from [233, 118]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[233, 118], [210, 139], [183, 127], [196, 152], [197, 139], [176, 125], [142, 133], [124, 126], [138, 145], [134, 127]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg6_task_0046_user_0020_scene_0004_cfg_0006_104122063633#0.jpg", + "gt": "[[233, 118], [210, 139], [183, 127], [196, 152], [197, 139], [176, 125], [142, 133], [124, 126], [138, 145], [134, 127]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "17163_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick the marker and put it in the cup', and now you are performing subtask 'pick the marker and put it in the cup.'\nStarting at [228, 102], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[228, 102], [203, 103], [200, 114], [202, 107], [195, 95], [180, 101], [171, 98], [167, 103], [171, 106], [175, 103]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/17163_exterior_image_1_left#0.jpg", + "gt": "[[228, 102], [203, 103], [200, 114], [202, 107], [195, 95], [180, 101], [171, 98], [167, 103], [171, 106], [175, 103]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "85214_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'use the spoon to place some of the contents in the bowl into the jug, then pour the contents in the jug into the bowl', and now you are performing subtask 'pick up the jug from the table.'\nStart at [156, 24]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[156, 24], [171, 62], [160, 84], [168, 82], [163, 67], [176, 68], [177, 80], [179, 69], [167, 62], [172, 77]]}" + } + ], + "images": "85214_exterior_image_1_left#0", + "gt": "[[156, 24], [171, 62], [160, 84], [168, 82], [163, 67], [176, 68], [177, 80], [179, 69], [167, 62], [172, 77]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0104_user_0007_scene_0007_cfg_0005_104422070044#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'drag the plate back after holding it down', and now you are performing subtask 'drag the plate back after holding it down.'\nYour initial coordinate is [374, 132]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[374, 132], [401, 122], [437, 172], [442, 171], [442, 184], [431, 180], [440, 180], [438, 184], [417, 168], [431, 147]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0104_user_0007_scene_0007_cfg_0005_104422070044#0.jpg", + "gt": "[[374, 132], [401, 122], [437, 172], [442, 171], [442, 184], [431, 180], [440, 180], [438, 184], [417, 168], [431, 147]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "26685_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'push the can to the right', and now you are performing subtask 'push the can to the right.'\nFrom start point [102.5, 21.0], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[102.5, 21.0], [122.5, 20.0], [150.5, 23.0], [179.5, 35.0], [183.5, 41.0], [181.5, 59.0], [188.5, 64.0], [197.5, 62.0], [214.5, 52.0], [208.5, 42.0]]}" + } + ], + "images": "26685_exterior_image_1_left#0", + "gt": "[[102.5, 21.0], [122.5, 20.0], [150.5, 23.0], [179.5, 35.0], [183.5, 41.0], [181.5, 59.0], [188.5, 64.0], [197.5, 62.0], [214.5, 52.0], [208.5, 42.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "90987_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put a black pen on top of the table, then move another black pen and place it into the white cup, then, open the grey towel on the table', and now you are performing subtask 'transfer a pen from under the table to above the table.'\nThe trajectory starts at [85, 64]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[85, 64], [146, 77], [167, 89], [170, 93], [166, 95], [187, 97], [191, 108], [216, 87], [221, 91], [213, 89]]}" + } + ], + "images": "90987_exterior_image_1_left#0", + "gt": "[[85, 64], [146, 77], [167, 89], [170, 93], [166, 95], [187, 97], [191, 108], [216, 87], [221, 91], [213, 89]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "68412_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'throw the metal lid onto the table', and now you are performing subtask 'throw the metal lid onto the table.'\nYou start from [279, 4]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[279, 4], [280, 21], [245, 39], [219, 81], [185, 79], [197, 88], [195, 108], [211, 108], [203, 110], [209, 93]]}" + } + ], + "images": "68412_exterior_image_1_left#0", + "gt": "[[279, 4], [280, 21], [245, 39], [219, 81], [185, 79], [197, 88], [195, 108], [211, 108], [203, 110], [209, 93]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "40510_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the glue stick from the cup, place it on the box, then on the table, back into the cup, and lastly on the table', and now you are performing subtask 'place glue stick on the box.'\nYour starting position is [195, 37]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[195, 37], [202, 53], [183, 80], [190, 87], [182, 93], [195, 78], [214, 88], [218, 93], [215, 99], [216, 94]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/40510_exterior_image_2_left#0.jpg", + "gt": "[[195, 37], [202, 53], [183, 80], [190, 87], [182, 93], [195, 78], [214, 88], [218, 93], [215, 99], [216, 94]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg3_task_0057_user_0010_scene_0010_cfg_0003_104122062823#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn on the power strips', and now you are performing subtask 'press the first button on the power strip.'\nWith start location [246, 0], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[246, 0], [288, 0], [260, 3], [267, 31], [243, 22], [312, 53], [412, 134], [369, 156], [373, 176], [344, 184]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg3_task_0057_user_0010_scene_0010_cfg_0003_104122062823#0.jpg", + "gt": "[[246, 0], [288, 0], [260, 3], [267, 31], [243, 22], [312, 53], [412, 134], [369, 156], [373, 176], [344, 184]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg2_task_0008_user_0007_scene_0004_cfg_0002_036422060215#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'swinging the flag', and now you are performing subtask 'swinging the flag.'\nWith start location [293, 160], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[293, 160], [277, 196], [281, 209], [299, 140], [260, 150], [330, 122], [270, 147], [302, 142], [312, 153], [306, 165]]}" + } + ], + "images": "RH20T_cfg2_task_0008_user_0007_scene_0004_cfg_0002_036422060215#0", + "gt": "[[293, 160], [277, 196], [281, 209], [299, 140], [260, 150], [330, 122], [270, 147], [302, 142], [312, 153], [306, 165]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "65809_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'place the lid on the pot', and now you are performing subtask 'place the lid on the pot.'\nYou begin at [274, 8]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[274, 8], [206, 10], [187, 21], [171, 50], [162, 93], [151, 97], [168, 89], [181, 116], [152, 129], [155, 119]]}" + } + ], + "images": "65809_exterior_image_2_left#0", + "gt": "[[274, 8], [206, 10], [187, 21], [171, 50], [162, 93], [151, 97], [168, 89], [181, 116], [152, 129], [155, 119]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0017_user_0014_scene_0002_cfg_0007_104122061330#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the pen into the pen holder', and now you are performing subtask 'put the pen into the pen holder.'\nFrom start point [266, 103], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[266, 103], [315, 105], [339, 128], [337, 144], [333, 138], [278, 165], [245, 226], [261, 236], [275, 169], [274, 132]]}" + } + ], + "images": "RH20T_cfg7_task_0017_user_0014_scene_0002_cfg_0007_104122061330#0", + "gt": "[[266, 103], [315, 105], [339, 128], [337, 144], [333, 138], [278, 165], [245, 226], [261, 236], [275, 169], [274, 132]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "511_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the box slightly to the center of the table', and now you are performing subtask 'move the box slightly to the center of the table.'\nWith start location [230, 20], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[230, 20], [217, 47], [215, 95], [196, 107], [193, 118], [180, 114], [169, 102], [175, 98], [171, 75], [178, 64]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/511_exterior_image_1_left#0.jpg", + "gt": "[[230, 20], [217, 47], [215, 95], [196, 107], [193, 118], [180, 114], [169, 102], [175, 98], [171, 75], [178, 64]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "15001_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the glue stick inside the cup then take it out', and now you are performing subtask 'place the glue stick on the table.'\nYou start from [172, 77]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[172, 77], [180, 80], [175, 80], [180, 88], [176, 89], [177, 76], [189, 70], [202, 80], [198, 93], [196, 83]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/15001_exterior_image_1_left#174.jpg", + "gt": "[[172, 77], [180, 80], [175, 80], [180, 88], [176, 89], [177, 76], [189, 70], [202, 80], [198, 93], [196, 83]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "40658_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the green cloth', and now you are performing subtask 'unfold the green cloth.'\nYour initial coordinate is [214, 5]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[214, 5], [183, 15], [185, 56], [199, 89], [185, 119], [177, 104], [156, 92], [134, 105], [119, 126], [137, 117]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/40658_exterior_image_2_left#0.jpg", + "gt": "[[214, 5], [183, 15], [185, 56], [199, 89], [185, 119], [177, 104], [156, 92], [134, 105], [119, 126], [137, 117]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "30514_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the towel to the left, then to the right', and now you are performing subtask 'move the towel to the left, then to the right.'\nStart at [168, 0]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[168, 0], [210, 32], [197, 28], [253, 99], [239, 119], [199, 112], [168, 89], [169, 67], [170, 88], [203, 106]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/30514_exterior_image_1_left#0.jpg", + "gt": "[[168, 0], [210, 32], [197, 28], [253, 99], [239, 119], [199, 112], [168, 89], [169, 67], [170, 88], [203, 106]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0057_user_0014_scene_0008_cfg_0004_038522062288#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn on the power strips', and now you are performing subtask 'press the button on the first power strip, press the button on the second power strip.'\nStart at [265, 151]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[265, 151], [263, 150], [265, 153], [266, 158], [268, 163], [271, 165], [273, 165], [279, 158], [280, 155], [281, 154]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg4_task_0057_user_0014_scene_0008_cfg_0004_038522062288#135.jpg", + "gt": "[[265, 151], [263, 150], [265, 153], [266, 158], [268, 163], [271, 165], [273, 165], [279, 158], [280, 155], [281, 154]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0033_user_0020_scene_0001_cfg_0007_104122061330#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pushing another small block to the designated position while grasping one small block', and now you are performing subtask 'place the front square in the position aligned with the second square, push the front square to move the second square to the position on the black dot on the cardboard.'\nThe trajectory starts at [403, 106]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[403, 106], [392, 135], [331, 210], [341, 193], [343, 180], [340, 137], [338, 130], [326, 119], [318, 115], [314, 118]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg7_task_0033_user_0020_scene_0001_cfg_0007_104122061330#279.jpg", + "gt": "[[403, 106], [392, 135], [331, 210], [341, 193], [343, 180], [340, 137], [338, 130], [326, 119], [318, 115], [314, 118]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0016_user_0014_scene_0008_cfg_0001_038522062547#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'hit the pool ball', and now you are performing subtask 'hit the pool ball.'\nBegin at [407, 136] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[407, 136], [414, 134], [425, 142], [440, 167], [450, 164], [451, 172], [436, 179], [438, 173], [446, 171], [437, 152]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0016_user_0014_scene_0008_cfg_0001_038522062547#0.jpg", + "gt": "[[407, 136], [414, 134], [425, 142], [440, 167], [450, 164], [451, 172], [436, 179], [438, 173], [446, 171], [437, 152]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "89090_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the black lid from the table and put it on the small cup', and now you are performing subtask 'pick up the black lid from the table and put it on the small cup.'\nBegin at [130.5, 67.0] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[130.5, 67.0], [155.5, 77.0], [162.5, 93.0], [158.5, 90.0], [159.5, 93.0], [171.5, 103.0], [157.5, 89.0], [136.5, 80.0], [127.5, 70.0], [127.5, 70.0]]}" + } + ], + "images": "89090_exterior_image_1_left#0", + "gt": "[[130.5, 67.0], [155.5, 77.0], [162.5, 93.0], [158.5, 90.0], [159.5, 93.0], [171.5, 103.0], [157.5, 89.0], [136.5, 80.0], [127.5, 70.0], [127.5, 70.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "48888_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'after opening and then closing the flask lid, and then opening it again', and now you are performing subtask 'press the flask lid closed.'\nFrom start point [249, 34], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[249, 34], [224, 43], [214, 56], [219, 56], [215, 66], [227, 88], [213, 74], [209, 64], [217, 58], [238, 73]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/48888_exterior_image_1_left#0.jpg", + "gt": "[[249, 34], [224, 43], [214, 56], [219, 56], [215, 66], [227, 88], [213, 74], [209, 64], [217, 58], [238, 73]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0061_user_0020_scene_0001_cfg_0007_104122061602#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the lid of the gift box on the table, then take everything out of the gift box and place it all on the table', and now you are performing subtask 'place the lid on the tabletop, pick up the cube from the gift box, transfer the cube from the gift box to the tabletop, place the cube on the tabletop.'\nThe trajectory starts at [395, 109]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[395, 109], [411, 97], [436, 108], [455, 131], [458, 152], [450, 122], [479, 124], [508, 164], [507, 192], [507, 192]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg7_task_0061_user_0020_scene_0001_cfg_0007_104122061602#223.jpg", + "gt": "[[395, 109], [411, 97], [436, 108], [455, 131], [458, 152], [450, 122], [479, 124], [508, 164], [507, 192], [507, 192]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "17712_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the cup', and now you are performing subtask 'move the cup.'\nYou begin at [206.5, 13.0]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[206.5, 13.0], [171.5, 54.0], [151.5, 67.0], [159.5, 65.0], [143.5, 83.0], [142.5, 95.0], [160.5, 78.0], [172.5, 81.0], [183.5, 95.0], [181.5, 77.0]]}" + } + ], + "images": "17712_exterior_image_1_left#0", + "gt": "[[206.5, 13.0], [171.5, 54.0], [151.5, 67.0], [159.5, 65.0], [143.5, 83.0], [142.5, 95.0], [160.5, 78.0], [172.5, 81.0], [183.5, 95.0], [181.5, 77.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg3_task_0018_user_0011_scene_0002_cfg_0003_104122062823#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'play jenga', and now you are performing subtask 'play jenga.'\nYou begin at [197, 41]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[197, 41], [230, 25], [213, 20], [227, 50], [215, 59], [239, 68], [220, 143], [276, 175], [209, 121], [232, 126]]}" + } + ], + "images": "RH20T_cfg3_task_0018_user_0011_scene_0002_cfg_0003_104122062823#0", + "gt": "[[197, 41], [230, 25], [213, 20], [227, 50], [215, 59], [239, 68], [220, 143], [276, 175], [209, 121], [232, 126]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0094_user_0007_scene_0003_cfg_0004_104122062295#TrajectoryPrediction_Task#10", + "task": "TrajectoryPrediction_Task", + "p_index": 10, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the box', and now you are performing subtask 'push the lid of the box, push the lid of the box.'\nStarting at [227, 109], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[227, 109], [280, 165], [356, 149], [384, 174], [382, 205], [370, 217], [383, 188], [363, 137], [279, 90], [302, 0]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg4_task_0094_user_0007_scene_0003_cfg_0004_104122062295#314.jpg", + "gt": "[[227, 109], [280, 165], [356, 149], [384, 174], [382, 205], [370, 217], [383, 188], [363, 137], [279, 90], [302, 0]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "69053_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'transfer the white cloth from the transparent board to the table', and now you are performing subtask 'transfer the white cloth from the transparent board to the table.'\nYour starting position is [101, 39]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[101, 39], [114, 65], [123, 50], [137, 44], [128, 56], [138, 61], [117, 55], [96, 89], [119, 106], [121, 71]]}" + } + ], + "images": "69053_exterior_image_2_left#0", + "gt": "[[101, 39], [114, 65], [123, 50], [137, 44], [128, 56], [138, 61], [117, 55], [96, 89], [119, 106], [121, 71]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0016_user_0014_scene_0008_cfg_0001_038522063145#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'hit the pool ball', and now you are performing subtask 'hit the pool ball.'\nFrom start point [443, 97], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[443, 97], [441, 95], [446, 94], [453, 99], [456, 113], [452, 125], [457, 120], [445, 145], [452, 131], [435, 124]]}" + } + ], + "images": "RH20T_cfg1_task_0016_user_0014_scene_0008_cfg_0001_038522063145#0", + "gt": "[[443, 97], [441, 95], [446, 94], [453, 99], [456, 113], [452, 125], [457, 120], [445, 145], [452, 131], [435, 124]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "14309_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pour the contents of the orange cup into the bowl', and now you are performing subtask 'pour the contents of the orange cup into the bowl.'\nYour initial coordinate is [188, 98]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[188, 98], [180, 99], [171, 104], [168, 116], [157, 111], [157, 105], [163, 103], [158, 95], [158, 90], [158, 90]]}" + } + ], + "images": "14309_exterior_image_1_left#0", + "gt": "[[188, 98], [180, 99], [171, 104], [168, 116], [157, 111], [157, 105], [163, 103], [158, 95], [158, 90], [158, 90]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0057_user_0007_scene_0002_cfg_0005_105422061350#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press a row of four power strip buttons to turn on the power strips', and now you are performing subtask 'press the second button on the power socket, press the third button on the power socket.'\nThe trajectory starts at [265, 129]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[265, 129], [275, 131], [278, 130], [282, 125], [284, 125], [275, 124], [273, 126], [277, 127], [279, 125], [287, 108]]}" + } + ], + "images": "RH20T_cfg5_task_0057_user_0007_scene_0002_cfg_0005_105422061350#577", + "gt": "[[265, 129], [275, 131], [278, 130], [282, 125], [284, 125], [275, 124], [273, 126], [277, 127], [279, 125], [287, 108]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "14064_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pull the curtain to close', and now you are performing subtask 'pull the curtain to close.'\nYour starting position is [181, 166]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[181, 166], [122, 145], [122, 118], [143, 81], [145, 56], [223, 105], [235, 123], [198, 109], [202, 128], [202, 128]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/14064_exterior_image_1_left#0.jpg", + "gt": "[[181, 166], [122, 145], [122, 118], [143, 81], [145, 56], [223, 105], [235, 123], [198, 109], [202, 128], [202, 128]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0022_user_0014_scene_0006_cfg_0006_104122061018#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'wave the flag', and now you are performing subtask 'wave the flag.'\nYou begin at [367, 28]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[367, 28], [297, 64], [268, 113], [279, 83], [289, 90], [297, 140], [310, 99], [307, 1], [283, 0], [350, 0]]}" + } + ], + "images": "RH20T_cfg6_task_0022_user_0014_scene_0006_cfg_0006_104122061018#0", + "gt": "[[367, 28], [297, 64], [268, 113], [279, 83], [289, 90], [297, 140], [310, 99], [307, 1], [283, 0], [350, 0]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "4936_exterior_image_2_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the drawer, place the black clip in the open drawer', and now you are performing subtask 'place the black clip in the open drawer.'\nFrom start point [176, 95], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[176, 95], [172, 85], [151, 65], [140, 65], [124, 73], [146, 72], [137, 73], [165, 85], [169, 95], [171, 67]]}" + } + ], + "images": "4936_exterior_image_2_left#192", + "gt": "[[176, 95], [172, 85], [151, 65], [140, 65], [124, 73], [146, 72], [137, 73], [165, 85], [169, 95], [171, 67]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "42244_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the two sachets from the box and place them on the upper countertop', and now you are performing subtask 'place the object on the tabletop.'\nWith start location [157, 102], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[157, 102], [160, 130], [158, 138], [149, 140], [157, 145], [150, 146], [148, 105], [153, 97], [161, 109], [188, 119]]}" + } + ], + "images": "42244_exterior_image_1_left#269", + "gt": "[[157, 102], [160, 130], [158, 138], [149, 140], [157, 145], [150, 146], [148, 105], [153, 97], [161, 109], [188, 119]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0034_user_0020_scene_0001_cfg_0006_104122063633#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the squares into a pyramid shape', and now you are performing subtask 'pick up the first square on the right, transfer the first square from the right to the center, place the first square in the center.'\nYour initial coordinate is [233, 118]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[233, 118], [223, 148], [214, 140], [222, 128], [210, 127], [217, 145], [229, 135], [213, 153], [216, 171], [221, 135]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg6_task_0034_user_0020_scene_0001_cfg_0006_104122063633#0.jpg", + "gt": "[[233, 118], [223, 148], [214, 140], [222, 128], [210, 127], [217, 145], [229, 135], [213, 153], [216, 171], [221, 135]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0001_user_0014_scene_0006_cfg_0001_038522062547#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the button from top to bottom', and now you are performing subtask 'press the button from top to bottom.'\nYour initial coordinate is [406, 133]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[406, 133], [431, 100], [422, 69], [423, 58], [429, 58], [412, 60], [401, 73], [395, 63], [392, 68], [400, 38]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0001_user_0014_scene_0006_cfg_0001_038522062547#0.jpg", + "gt": "[[406, 133], [431, 100], [422, 69], [423, 58], [429, 58], [412, 60], [401, 73], [395, 63], [392, 68], [400, 38]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "49658_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the cup from the dishwasher and place it on the countertop', and now you are performing subtask 'remove the cup from the dishwasher and place it on the countertop.'\nYour starting position is [116, 70]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[116, 70], [162, 60], [152, 65], [162, 66], [151, 90], [159, 130], [179, 89], [201, 90], [210, 103], [196, 80]]}" + } + ], + "images": "49658_exterior_image_2_left#0", + "gt": "[[116, 70], [162, 60], [152, 65], [162, 66], [151, 90], [159, 130], [179, 89], [201, 90], [210, 103], [196, 80]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0130_user_0020_scene_0002_cfg_0006_104122064161#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'plug in the bulb holder with a bulb to the socket and turn on the switch of the bulb', and now you are performing subtask 'pick up the bulb from the table, transfer the bulb from the table to the socket, insert the bulb into the socket.'\nBegin at [338, 111] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[338, 111], [377, 83], [382, 122], [375, 78], [387, 95], [376, 159], [403, 165], [403, 177], [403, 148], [403, 148]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg6_task_0130_user_0020_scene_0002_cfg_0006_104122064161#0.jpg", + "gt": "[[338, 111], [377, 83], [382, 122], [375, 78], [387, 95], [376, 159], [403, 165], [403, 177], [403, 148], [403, 148]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "40526_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the right door of the cabinet', and now you are performing subtask 'push the cabinet door to fully open.'\nFrom start point [156, 38], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[156, 38], [157, 33], [144, 18], [141, 8], [143, 19], [158, 33], [186, 28], [192, 23], [171, 0], [134, 0]]}" + } + ], + "images": "40526_exterior_image_1_left#218", + "gt": "[[156, 38], [157, 33], [144, 18], [141, 8], [143, 19], [158, 33], [186, 28], [192, 23], [171, 0], [134, 0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "37843_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'use the blackboard eraser to wipe the whiteboard and place it on the table', and now you are performing subtask 'use the blackboard eraser to wipe the whiteboard and place it on the table.'\nYou start from [227, 11]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[227, 11], [195, 44], [200, 33], [181, 19], [144, 12], [118, 19], [151, 18], [161, 31], [178, 135], [190, 68]]}" + } + ], + "images": "37843_exterior_image_2_left#0", + "gt": "[[227, 11], [195, 44], [200, 33], [181, 19], [144, 12], [118, 19], [151, 18], [161, 31], [178, 135], [190, 68]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0057_user_0007_scene_0003_cfg_0005_036422060215#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn on the power strips', and now you are performing subtask 'press the fourth button on the power socket.'\nBegin at [292, 190] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[292, 190], [297, 194], [303, 192], [298, 190], [297, 195], [298, 187], [304, 179], [311, 160], [311, 154], [323, 145]]}" + } + ], + "images": "RH20T_cfg5_task_0057_user_0007_scene_0003_cfg_0005_036422060215#620", + "gt": "[[292, 190], [297, 194], [303, 192], [298, 190], [297, 195], [298, 187], [304, 179], [311, 160], [311, 154], [323, 145]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0003_user_0014_scene_0010_cfg_0006_104122061330#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press three buttons from left to right in sequence', and now you are performing subtask 'press the green button in the middle.'\nBegin at [316, 187] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[316, 187], [316, 185], [315, 187], [313, 185], [308, 189], [301, 200], [305, 205], [303, 202], [315, 179], [315, 179]]}" + } + ], + "images": "RH20T_cfg6_task_0003_user_0014_scene_0010_cfg_0006_104122061330#111", + "gt": "[[316, 187], [316, 185], [315, 187], [313, 185], [308, 189], [301, 200], [305, 205], [303, 202], [315, 179], [315, 179]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "60752_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the green towel to the left', and now you are performing subtask 'move the green towel to the left.'\nYou begin at [44, 7]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[44, 7], [89, 20], [129, 43], [151, 70], [163, 104], [162, 114], [171, 54], [165, 55], [150, 82], [154, 57]]}" + } + ], + "images": "60752_exterior_image_1_left#0", + "gt": "[[44, 7], [89, 20], [129, 43], [151, 70], [163, 104], [162, 114], [171, 54], [165, 55], [150, 82], [154, 57]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "71515_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'place the yellow block on its side', and now you are performing subtask 'place the yellow block on its side.'\nBegin at [266, 0] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[266, 0], [216, 41], [182, 49], [160, 62], [169, 64], [158, 55], [156, 65], [179, 77], [183, 65], [181, 47]]}" + } + ], + "images": "71515_exterior_image_2_left#0", + "gt": "[[266, 0], [216, 41], [182, 49], [160, 62], [169, 64], [158, 55], [156, 65], [179, 77], [183, 65], [181, 47]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "6963_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the stopper in the drain of the sink', and now you are performing subtask 'put the stopper in the drain of the sink.'\nYou begin at [144, 57]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[144, 57], [179, 64], [236, 96], [242, 86], [249, 86], [245, 91], [249, 90], [240, 80], [225, 85], [216, 80]]}" + } + ], + "images": "6963_exterior_image_1_left#0", + "gt": "[[144, 57], [179, 64], [236, 96], [242, 86], [249, 86], [245, 91], [249, 90], [240, 80], [225, 85], [216, 80]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "25200_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stir the contents in the orange bowl with a spoon, then put the spoon into the cup', and now you are performing subtask 'stir the contents in the orange bowl with a spoon, then put the spoon into the cup.'\nStarting at [94, 56], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[94, 56], [134, 60], [153, 47], [150, 67], [164, 78], [170, 49], [173, 82], [166, 52], [156, 49], [160, 60]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/25200_exterior_image_1_left#0.jpg", + "gt": "[[94, 56], [134, 60], [153, 47], [150, 67], [164, 78], [170, 49], [173, 82], [166, 52], [156, 49], [160, 60]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "64205_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the white can out of the grey bin, pour the contents in the can into the grey mug, place the can back in the bin', and now you are performing subtask 'take the white can out of the grey bin, pour the contents in the can into the grey mug, place the can back in the bin.'\nYou begin at [141, 91]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[141, 91], [168, 106], [199, 105], [192, 72], [149, 176], [168, 180], [204, 82], [192, 96], [191, 79], [172, 72]]}" + } + ], + "images": "64205_exterior_image_1_left#0", + "gt": "[[141, 91], [168, 106], [199, 105], [192, 72], [149, 176], [168, 180], [204, 82], [192, 96], [191, 79], [172, 72]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "7907_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pour the candy out of the light blue cup and into the green bowl', and now you are performing subtask 'pour the candy out of the light blue cup and into the green bowl.'\nStarting at [136, 128], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[136, 128], [167, 97], [208, 97], [216, 101], [188, 95], [193, 102], [186, 100], [196, 99], [205, 110], [192, 104]]}" + } + ], + "images": "7907_exterior_image_1_left#0", + "gt": "[[136, 128], [167, 97], [208, 97], [216, 101], [188, 95], [193, 102], [186, 100], [196, 99], [205, 110], [192, 104]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "75634_exterior_image_1_left#TrajectoryPrediction_Task#10", + "task": "TrajectoryPrediction_Task", + "p_index": 10, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the drawer, take out the fruit toy, place it in the basket, and then close the drawer', and now you are performing subtask 'push the handle of the drawer to close the drawer.'\nFrom start point [160.5, 84.5], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[160.5, 84.5], [149.5, 84.5], [155.5, 81.5], [155.5, 71.5], [156.5, 70.5], [156.5, 68.5], [159.5, 66.5], [162.5, 66.5], [157.5, 66.5], [160.5, 67.5]]}" + } + ], + "images": "75634_exterior_image_1_left#420", + "gt": "[[160.5, 84.5], [149.5, 84.5], [155.5, 81.5], [155.5, 71.5], [156.5, 70.5], [156.5, 68.5], [159.5, 66.5], [162.5, 66.5], [157.5, 66.5], [160.5, 67.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "25286_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the boxes inside the case', and now you are performing subtask 'place the white box inside the box.'\nWith start location [174, 110], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[174, 110], [180, 122], [178, 137], [182, 134], [173, 132], [181, 133], [177, 143], [174, 106], [161, 99], [159, 108]]}" + } + ], + "images": "25286_exterior_image_1_left#516", + "gt": "[[174, 110], [180, 122], [178, 137], [182, 134], [173, 132], [181, 133], [177, 143], [174, 106], [161, 99], [159, 108]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "56862_exterior_image_1_left#TrajectoryPrediction_Task#8", + "task": "TrajectoryPrediction_Task", + "p_index": 8, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the bottle of water, the black bag, the dark blue bag, the top plastic and the remaining snack pack in the box respectively', and now you are performing subtask 'place the packaging bag in the box.'\nYour starting position is [155, 103]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[155, 103], [133, 110], [134, 142], [122, 123], [122, 104], [148, 92], [174, 105], [178, 130], [161, 107], [145, 101]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/56862_exterior_image_1_left#777.jpg", + "gt": "[[155, 103], [133, 110], [134, 142], [122, 123], [122, 104], [148, 92], [174, 105], [178, 130], [161, 107], [145, 101]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg2_task_0051_user_0016_scene_0003_cfg_0002_104122061850#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the dish off the dish rack', and now you are performing subtask 'take the dish off the dish rack.'\nYour initial coordinate is [338, 109]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[338, 109], [362, 91], [361, 80], [377, 66], [400, 15], [409, 11], [427, 35], [408, 12], [388, 53], [394, 57]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg2_task_0051_user_0016_scene_0003_cfg_0002_104122061850#0.jpg", + "gt": "[[338, 109], [362, 91], [361, 80], [377, 66], [400, 15], [409, 11], [427, 35], [408, 12], [388, 53], [394, 57]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0130_user_0020_scene_0002_cfg_0006_104122060811#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'plug in the bulb holder with a bulb to the socket and turn on the switch of the bulb', and now you are performing subtask 'insert the bulb into the socket, press the switch on the socket to turn on the bulb.'\nYour starting position is [356, 119]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[356, 119], [355, 113], [349, 114], [349, 116], [348, 117], [349, 120], [347, 121], [347, 125], [348, 125], [347, 118]]}" + } + ], + "images": "RH20T_cfg6_task_0130_user_0020_scene_0002_cfg_0006_104122060811#510", + "gt": "[[356, 119], [355, 113], [349, 114], [349, 116], [348, 117], [349, 120], [347, 121], [347, 125], [348, 125], [347, 118]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "84313_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press down on the lever switch of the toaster', and now you are performing subtask 'press down on the lever switch of the toaster.'\nFrom start point [88, 16], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[88, 16], [127, 9], [167, 30], [178, 51], [176, 80], [154, 66], [139, 48], [137, 33], [139, 22], [141, 27]]}" + } + ], + "images": "84313_exterior_image_1_left#0", + "gt": "[[88, 16], [127, 9], [167, 30], [178, 51], [176, 80], [154, 66], [139, 48], [137, 33], [139, 22], [141, 27]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg2_task_0104_user_0007_scene_0007_cfg_0002_036422060215#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'drag the plate back after holding it down', and now you are performing subtask 'drag the plate back after holding it down.'\nYou begin at [293, 160]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[293, 160], [304, 188], [313, 193], [315, 184], [301, 197], [313, 195], [253, 209], [265, 205], [249, 201], [283, 180]]}" + } + ], + "images": "RH20T_cfg2_task_0104_user_0007_scene_0007_cfg_0002_036422060215#0", + "gt": "[[293, 160], [304, 188], [313, 193], [315, 184], [301, 197], [313, 195], [253, 209], [265, 205], [249, 201], [283, 180]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "50306_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the tissue box on top then place it back on the other box', and now you are performing subtask 'pick up the tissue box on top then place it back on the other box.'\nStarting at [122, 100], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[122, 100], [148, 95], [135, 105], [149, 109], [143, 106], [141, 113], [156, 100], [144, 100], [141, 115], [145, 92]]}" + } + ], + "images": "50306_exterior_image_2_left#0", + "gt": "[[122, 100], [148, 95], [135, 105], [149, 109], [143, 106], [141, 113], [156, 100], [144, 100], [141, 115], [145, 92]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "66082_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the cup forward and to the right', and now you are performing subtask 'move the cup forward and to the right.'\nStarting at [235, 6], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[235, 6], [203, 15], [180, 29], [177, 49], [164, 65], [176, 46], [172, 38], [163, 45], [164, 34], [164, 34]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/66082_exterior_image_1_left#0.jpg", + "gt": "[[235, 6], [203, 15], [180, 29], [177, 49], [164, 65], [176, 46], [172, 38], [163, 45], [164, 34], [164, 34]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0061_user_0020_scene_0003_cfg_0007_104122061018#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take everything out of the gift box', and now you are performing subtask 'place the item on the table, take out the contents of the gift box, transfer the object from the container to the surface, place the object on the surface.'\nStarting at [298, 111], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[298, 111], [293, 88], [299, 112], [351, 175], [303, 58], [309, 52], [283, 47], [278, 84], [299, 22], [341, 0]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg7_task_0061_user_0020_scene_0003_cfg_0007_104122061018#440.jpg", + "gt": "[[298, 111], [293, 88], [299, 112], [351, 175], [303, 58], [309, 52], [283, 47], [278, 84], [299, 22], [341, 0]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0044_user_0014_scene_0005_cfg_0007_037522061512#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up a bag of things', and now you are performing subtask 'pick up a bag of things.'\nYour initial coordinate is [261, 86]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[261, 86], [259, 93], [260, 83], [264, 81], [280, 85], [281, 92], [275, 89], [265, 72], [269, 58], [265, 45]]}" + } + ], + "images": "RH20T_cfg7_task_0044_user_0014_scene_0005_cfg_0007_037522061512#0", + "gt": "[[261, 86], [259, 93], [260, 83], [264, 81], [280, 85], [281, 92], [275, 89], [265, 72], [269, 58], [265, 45]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0051_user_0014_scene_0002_cfg_0006_104122061602#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the dish off the dish rack', and now you are performing subtask 'take the dish off the dish rack.'\nBegin at [446, 106] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[446, 106], [483, 113], [568, 181], [585, 141], [573, 98], [496, 77], [469, 109], [462, 86], [488, 100], [467, 82]]}" + } + ], + "images": "RH20T_cfg6_task_0051_user_0014_scene_0002_cfg_0006_104122061602#0", + "gt": "[[446, 106], [483, 113], [568, 181], [585, 141], [573, 98], [496, 77], [469, 109], [462, 86], [488, 100], [467, 82]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "73116_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the button on the toaster', and now you are performing subtask 'press the button on the toaster.'\nThe trajectory starts at [135, 44]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[135, 44], [155, 72], [191, 101], [203, 129], [207, 127], [200, 131], [186, 122], [175, 89], [156, 69], [165, 74]]}" + } + ], + "images": "73116_exterior_image_1_left#0", + "gt": "[[135, 44], [155, 72], [191, 101], [203, 129], [207, 127], [200, 131], [186, 122], [175, 89], [156, 69], [165, 74]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg2_task_0071_user_0014_scene_0003_cfg_0002_036422060215#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close a sliding window', and now you are performing subtask 'push the handle of the sliding window to close the window.'\nYou begin at [295, 162]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[295, 162], [298, 173], [294, 182], [292, 159], [304, 147], [317, 147], [309, 152], [301, 166], [297, 164], [300, 165]]}" + } + ], + "images": "RH20T_cfg2_task_0071_user_0014_scene_0003_cfg_0002_036422060215#0", + "gt": "[[295, 162], [298, 173], [294, 182], [292, 159], [304, 147], [317, 147], [309, 152], [301, 166], [297, 164], [300, 165]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "1291_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the cube in the bowl', and now you are performing subtask 'put the cube in the bowl.'\nYou start from [3.0, 52.0]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[3.0, 52.0], [61.0, 11.0], [102.0, 11.0], [143.0, 34.0], [160.0, 63.0], [163.0, 124.0], [145.0, 140.0], [184.0, 80.0], [172.0, 118.0], [153.0, 93.0]]}" + } + ], + "images": "1291_exterior_image_1_left#0", + "gt": "[[3.0, 52.0], [61.0, 11.0], [102.0, 11.0], [143.0, 34.0], [160.0, 63.0], [163.0, 124.0], [145.0, 140.0], [184.0, 80.0], [172.0, 118.0], [153.0, 93.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0096_user_0007_scene_0008_cfg_0005_104122061850#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take something out of a drawer', and now you are performing subtask 'pull the drawer handle to the outside of the table.'\nStart at [305, 50]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[305, 50], [315, 40], [330, 58], [307, 150], [329, 105], [310, 148], [321, 178], [313, 188], [356, 131], [346, 115]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0096_user_0007_scene_0008_cfg_0005_104122061850#0.jpg", + "gt": "[[305, 50], [315, 40], [330, 58], [307, 150], [329, 105], [310, 148], [321, 178], [313, 188], [356, 131], [346, 115]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0051_user_0015_scene_0002_cfg_0001_035622060973#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the dish off the dish rack', and now you are performing subtask 'take the dish off the dish rack.'\nStart at [246, 130]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[246, 130], [201, 111], [218, 123], [232, 97], [275, 198], [267, 222], [280, 227], [284, 245], [275, 222], [235, 209]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0051_user_0015_scene_0002_cfg_0001_035622060973#0.jpg", + "gt": "[[246, 130], [201, 111], [218, 123], [232, 97], [275, 198], [267, 222], [280, 227], [284, 245], [275, 222], [235, 209]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "49774_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the pen from the mug and put it on the table', and now you are performing subtask 'pick up the pen from the mug and put it on the table.'\nStarting at [72, 5], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[72, 5], [132, 28], [118, 57], [126, 64], [126, 77], [131, 60], [127, 49], [109, 54], [99, 78], [110, 76]]}" + } + ], + "images": "49774_exterior_image_2_left#0", + "gt": "[[72, 5], [132, 28], [118, 57], [126, 64], [126, 77], [131, 60], [127, 49], [109, 54], [99, 78], [110, 76]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0014_user_0016_scene_0003_cfg_0004_104122062823#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'place the block on the table next to the scale', and now you are performing subtask 'place the block on the table next to the scale.'\nThe trajectory starts at [243, 0]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[243, 0], [170, 0], [249, 0], [251, 28], [265, 38], [247, 69], [260, 71], [240, 43], [218, 38], [244, 34]]}" + } + ], + "images": "RH20T_cfg4_task_0014_user_0016_scene_0003_cfg_0004_104122062823#0", + "gt": "[[243, 0], [170, 0], [249, 0], [251, 28], [265, 38], [247, 69], [260, 71], [240, 43], [218, 38], [244, 34]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "56909_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the yellow spherical toy down from the cabinet', and now you are performing subtask 'move the yellow spherical toy down from the cabinet.'\nYour starting position is [255, 30]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[255, 30], [221, 7], [203, 7], [189, 15], [189, 27], [187, 16], [175, 19], [156, 41], [167, 42], [186, 5]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/56909_exterior_image_1_left#0.jpg", + "gt": "[[255, 30], [221, 7], [203, 7], [189, 15], [189, 27], [187, 16], [175, 19], [156, 41], [167, 42], [186, 5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0034_user_0014_scene_0001_cfg_0007_104122064161#TrajectoryPrediction_Task#8", + "task": "TrajectoryPrediction_Task", + "p_index": 8, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the squares into a pyramid shape', and now you are performing subtask 'pick up the square, place the square on another square, pick up the square.'\nYou start from [369, 175]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[369, 175], [380, 186], [393, 226], [388, 264], [391, 241], [385, 209], [373, 200], [359, 202], [368, 200], [385, 217]]}" + } + ], + "images": "RH20T_cfg7_task_0034_user_0014_scene_0001_cfg_0007_104122064161#448", + "gt": "[[369, 175], [380, 186], [393, 226], [388, 264], [391, 241], [385, 209], [373, 200], [359, 202], [368, 200], [385, 217]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "39572_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the green object from the pot on the table and put it in the white bowl', and now you are performing subtask 'remove the green object from the pot on the table and put it in the white bowl.'\nStarting at [122.0, 101.5], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[122.0, 101.5], [159.0, 139.5], [136.0, 152.5], [121.0, 143.5], [145.0, 136.5], [159.0, 152.5], [151.0, 133.5], [128.0, 134.5], [125.0, 166.5], [115.0, 146.5]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/39572_exterior_image_1_left#0.jpg", + "gt": "[[122.0, 101.5], [159.0, 139.5], [136.0, 152.5], [121.0, 143.5], [145.0, 136.5], [159.0, 152.5], [151.0, 133.5], [128.0, 134.5], [125.0, 166.5], [115.0, 146.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg2_task_0029_user_0003_scene_0005_cfg_0002_104122061850#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'grasp the handle and open the drawer', and now you are performing subtask 'grasp the handle and open the drawer.'\nStart at [340, 105]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[340, 105], [340, 196], [331, 206], [339, 214], [332, 209], [331, 227], [320, 222], [325, 234], [363, 147], [361, 108]]}" + } + ], + "images": "RH20T_cfg2_task_0029_user_0003_scene_0005_cfg_0002_104122061850#0", + "gt": "[[340, 105], [340, 196], [331, 206], [339, 214], [332, 209], [331, 227], [320, 222], [325, 234], [363, 147], [361, 108]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "1654_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the whisk to the right, remove the spoon from the cup and put it beside the whisk', and now you are performing subtask 'place the kitchen utensils at the designated position on the table.'\nStarting at [276, 1], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[276, 1], [234, 31], [208, 71], [231, 104], [216, 99], [223, 118], [244, 115], [199, 83], [191, 98], [191, 57]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/1654_exterior_image_1_left#0.jpg", + "gt": "[[276, 1], [234, 31], [208, 71], [231, 104], [216, 99], [223, 118], [244, 115], [199, 83], [191, 98], [191, 57]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg3_task_0023_user_0010_scene_0003_cfg_0003_104122062823#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn on the power strip by pressing the button', and now you are performing subtask 'turn on the power strip by pressing the button.'\nYour initial coordinate is [246, 0]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[246, 0], [239, 10], [250, 7], [253, 24], [292, 52], [310, 78], [292, 86], [289, 97], [291, 46], [272, 28]]}" + } + ], + "images": "RH20T_cfg3_task_0023_user_0010_scene_0003_cfg_0003_104122062823#0", + "gt": "[[246, 0], [239, 10], [250, 7], [253, 24], [292, 52], [310, 78], [292, 86], [289, 97], [291, 46], [272, 28]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0201_user_0015_scene_0007_cfg_0001_750612070853#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'the medium pipette tip is inserted into the holder for medium pipette tips', and now you are performing subtask 'pick up the medium pipette from the table, transfer the medium pipette from the table to the holder for medium pipette tips, place the tip of the medium pipette into the holder for medium pipette tips.'\nYour initial coordinate is [355, 82]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[355, 82], [300, 100], [308, 79], [275, 123], [309, 197], [312, 162], [336, 136], [405, 98], [399, 110], [406, 131]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0201_user_0015_scene_0007_cfg_0001_750612070853#0.jpg", + "gt": "[[355, 82], [300, 100], [308, 79], [275, 123], [309, 197], [312, 162], [336, 136], [405, 98], [399, 110], [406, 131]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0105_user_0020_scene_0001_cfg_0006_104122061330#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the object on the shelf', and now you are performing subtask 'pick up the cup on the table, transfer the cup from the table to the shelf, place the cup on the shelf.'\nWith start location [304, 111], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[304, 111], [328, 145], [385, 133], [385, 148], [378, 132], [353, 132], [331, 83], [279, 160], [289, 128], [289, 128]]}" + } + ], + "images": "RH20T_cfg6_task_0105_user_0020_scene_0001_cfg_0006_104122061330#375", + "gt": "[[304, 111], [328, 145], [385, 133], [385, 148], [378, 132], [353, 132], [331, 83], [279, 160], [289, 128], [289, 128]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0085_user_0007_scene_0007_cfg_0005_036422060215#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the bubble ring from the assembled bubble ring and ball', and now you are performing subtask 'remove the bubble ring from the assembled bubble ring and ball.'\nStarting at [286, 108], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[286, 108], [269, 92], [256, 121], [266, 148], [263, 163], [265, 167], [268, 160], [266, 156], [244, 170], [270, 136]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0085_user_0007_scene_0007_cfg_0005_036422060215#0.jpg", + "gt": "[[286, 108], [269, 92], [256, 121], [266, 148], [263, 163], [265, 167], [268, 160], [266, 156], [244, 170], [270, 136]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "15364_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the marker from the glass cup and put it on the table', and now you are performing subtask 'pick up the marker from the glass cup and put it on the table.'\nStarting at [293, 57], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[293, 57], [194, 61], [154, 87], [125, 120], [129, 129], [126, 113], [157, 105], [163, 108], [157, 117], [149, 108]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/15364_exterior_image_2_left#0.jpg", + "gt": "[[293, 57], [194, 61], [154, 87], [125, 120], [129, 129], [126, 113], [157, 105], [163, 108], [157, 117], [149, 108]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0005_user_0008_scene_0001_cfg_0001_819112071037#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'approach and touch the side of the small block', and now you are performing subtask 'approach and touch the side of the small block.'\nYou start from [326, 0]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[326, 0], [320, 1], [302, 78], [283, 101], [137, 150], [118, 142], [104, 148], [131, 128], [197, 97], [224, 67]]}" + } + ], + "images": "RH20T_cfg1_task_0005_user_0008_scene_0001_cfg_0001_819112071037#0", + "gt": "[[326, 0], [320, 1], [302, 78], [283, 101], [137, 150], [118, 142], [104, 148], [131, 128], [197, 97], [224, 67]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0004_user_0005_scene_0003_cfg_0001_750612070851#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the small block on the left and move it to the right', and now you are performing subtask 'pick up the small block on the left and move it to the right.'\nFrom start point [333, 156], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[333, 156], [233, 135], [232, 162], [243, 169], [220, 185], [227, 177], [238, 198], [269, 173], [309, 214], [309, 214]]}" + } + ], + "images": "RH20T_cfg1_task_0004_user_0005_scene_0003_cfg_0001_750612070851#0", + "gt": "[[333, 156], [233, 135], [232, 162], [243, 169], [220, 185], [227, 177], [238, 198], [269, 173], [309, 214], [309, 214]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0017_user_0014_scene_0002_cfg_0006_104122060811#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the pen into the pen holder', and now you are performing subtask 'pick up the pen from the table.'\nStarting at [385, 127], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[385, 127], [377, 140], [378, 146], [375, 157], [377, 168], [378, 162], [373, 150], [370, 150], [334, 185], [350, 174]]}" + } + ], + "images": "RH20T_cfg6_task_0017_user_0014_scene_0002_cfg_0006_104122060811#0", + "gt": "[[385, 127], [377, 140], [378, 146], [375, 157], [377, 168], [378, 162], [373, 150], [370, 150], [334, 185], [350, 174]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg3_task_0057_user_0010_scene_0006_cfg_0003_104122062823#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn on the power strips', and now you are performing subtask 'press the button on the middle right power strip, press the button on the middle left power strip, press the button on the left power strip.'\nBegin at [136, 52] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[136, 52], [145, 55], [140, 60], [141, 63], [137, 54], [130, 49], [120, 46], [117, 47], [117, 50], [120, 52]]}" + } + ], + "images": "RH20T_cfg3_task_0057_user_0010_scene_0006_cfg_0003_104122062823#106", + "gt": "[[136, 52], [145, 55], [140, 60], [141, 63], [137, 54], [130, 49], [120, 46], [117, 47], [117, 50], [120, 52]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "14687_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the pen from the bowl and place it on the table', and now you are performing subtask 'take the pen from the bowl and place it on the table.'\nThe trajectory starts at [130.5, 32.5]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[130.5, 32.5], [140.5, 36.5], [159.5, 51.5], [165.5, 62.5], [173.5, 91.5], [177.5, 94.5], [171.5, 66.5], [181.5, 81.5], [185.5, 61.5], [181.5, 51.5]]}" + } + ], + "images": "14687_exterior_image_1_left#0", + "gt": "[[130.5, 32.5], [140.5, 36.5], [159.5, 51.5], [165.5, 62.5], [173.5, 91.5], [177.5, 94.5], [171.5, 66.5], [181.5, 81.5], [185.5, 61.5], [181.5, 51.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "63647_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the drawer and then put the three plush toys inside', and now you are performing subtask 'transfer a plush toy from the top of the table to the inside of the drawer.'\nYour initial coordinate is [251.5, 89.5]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[251.5, 89.5], [259.5, 111.5], [251.5, 130.5], [230.5, 146.5], [224.5, 159.5], [227.5, 163.5], [239.5, 161.5], [242.5, 158.5], [250.5, 158.5], [241.5, 155.5]]}" + } + ], + "images": "63647_exterior_image_1_left#0", + "gt": "[[251.5, 89.5], [259.5, 111.5], [251.5, 130.5], [230.5, 146.5], [224.5, 159.5], [227.5, 163.5], [239.5, 161.5], [242.5, 158.5], [250.5, 158.5], [241.5, 155.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "13502_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn on the faucet, turn it off, and then turn it on again', and now you are performing subtask 'press the faucet handle to turn off.'\nFrom start point [102, 76], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[102, 76], [104, 70], [96, 65], [93, 67], [89, 65], [88, 69], [93, 70], [95, 74], [95, 72], [99, 73]]}" + } + ], + "images": "13502_exterior_image_1_left#130", + "gt": "[[102, 76], [104, 70], [96, 65], [93, 67], [89, 65], [88, 69], [93, 70], [95, 74], [95, 72], [99, 73]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "83239_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the cloth on the transparent object', and now you are performing subtask 'pick up the cloth on the mat.'\nBegin at [269, 68] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[269, 68], [222, 85], [199, 126], [189, 59], [171, 37], [178, 50], [177, 27], [182, 21], [189, 26], [186, 72]]}" + } + ], + "images": "83239_exterior_image_1_left#0", + "gt": "[[269, 68], [222, 85], [199, 126], [189, 59], [171, 37], [178, 50], [177, 27], [182, 21], [189, 26], [186, 72]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "72950_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the yellow pepper from the container', and now you are performing subtask 'remove the yellow pepper from the container.'\nYour starting position is [173, 1]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[173, 1], [159, 28], [173, 54], [167, 77], [175, 52], [202, 41], [204, 55], [197, 74], [193, 62], [167, 48]]}" + } + ], + "images": "72950_exterior_image_2_left#0", + "gt": "[[173, 1], [159, 28], [173, 54], [167, 77], [175, 52], [202, 41], [204, 55], [197, 74], [193, 62], [167, 48]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg2_task_0037_user_0007_scene_0007_cfg_0002_105422061350#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'pick up the first block from the surface, place the first block on the surface, pick up the second block from the surface.'\nStart at [385, 157]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[385, 157], [373, 151], [377, 153], [368, 155], [350, 176], [310, 170], [304, 188], [313, 189], [315, 193], [319, 170]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg2_task_0037_user_0007_scene_0007_cfg_0002_105422061350#0.jpg", + "gt": "[[385, 157], [373, 151], [377, 153], [368, 155], [350, 176], [310, 170], [304, 188], [313, 189], [315, 193], [319, 170]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0033_user_0015_scene_0008_cfg_0001_035622060973#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the block', and now you are performing subtask 'transfer the square from the cardboard to the right side of the middle square on the cardboard, place the square to the left side of the cardboard.'\nFrom start point [244, 161], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[244, 161], [250, 165], [249, 175], [234, 173], [239, 182], [247, 180], [229, 158], [229, 163], [223, 141], [189, 115]]}" + } + ], + "images": "RH20T_cfg1_task_0033_user_0015_scene_0008_cfg_0001_035622060973#238", + "gt": "[[244, 161], [250, 165], [249, 175], [234, 173], [239, 182], [247, 180], [229, 158], [229, 163], [223, 141], [189, 115]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "79503_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the cup and move it to the right twice', and now you are performing subtask 'transfer the cup from the right side of the table to further right of the table.'\nStarting at [217, 66], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[217, 66], [230, 82], [223, 90], [225, 96], [221, 82], [208, 86], [187, 101], [190, 112], [196, 107], [184, 71]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/79503_exterior_image_1_left#223.jpg", + "gt": "[[217, 66], [230, 82], [223, 90], [225, 96], [221, 82], [208, 86], [187, 101], [190, 112], [196, 107], [184, 71]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0103_user_0010_scene_0005_cfg_0001_038522062547#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the plate to the goal post', and now you are performing subtask 'move the plate to the goal post.'\nWith start location [404, 127], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[404, 127], [395, 181], [379, 207], [392, 203], [401, 177], [415, 67], [391, 44], [420, 66], [435, 116], [455, 117]]}" + } + ], + "images": "RH20T_cfg1_task_0103_user_0010_scene_0005_cfg_0001_038522062547#0", + "gt": "[[404, 127], [395, 181], [379, 207], [392, 203], [401, 177], [415, 67], [391, 44], [420, 66], [435, 116], [455, 117]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "4558_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the small block from the stack', and now you are performing subtask 'remove the small block from the stack.'\nWith start location [113.0, 3.0], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[113.0, 3.0], [124.0, 24.0], [130.0, 52.0], [120.0, 32.0], [116.0, 40.0], [115.0, 68.0], [119.0, 86.0], [106.0, 62.0], [104.0, 37.0], [104.0, 37.0]]}" + } + ], + "images": "4558_exterior_image_1_left#0", + "gt": "[[113.0, 3.0], [124.0, 24.0], [130.0, 52.0], [120.0, 32.0], [116.0, 40.0], [115.0, 68.0], [119.0, 86.0], [106.0, 62.0], [104.0, 37.0], [104.0, 37.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0094_user_0007_scene_0003_cfg_0004_104122063550#TrajectoryPrediction_Task#8", + "task": "TrajectoryPrediction_Task", + "p_index": 8, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the box', and now you are performing subtask 'push the lid of the box, push the lid of the box.'\nYou start from [261, 186]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[261, 186], [278, 181], [286, 181], [317, 218], [322, 227], [319, 225], [316, 236], [317, 274], [319, 254], [313, 217]]}" + } + ], + "images": "RH20T_cfg4_task_0094_user_0007_scene_0003_cfg_0004_104122063550#133", + "gt": "[[261, 186], [278, 181], [286, 181], [317, 218], [322, 227], [319, 225], [316, 236], [317, 274], [319, 254], [313, 217]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0031_user_0020_scene_0007_cfg_0007_104122063633#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'cover the box', and now you are performing subtask 'cover the box.'\nStarting at [234, 121], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[234, 121], [212, 149], [210, 141], [199, 141], [200, 155], [192, 127], [192, 147], [170, 211], [192, 148], [202, 138]]}" + } + ], + "images": "RH20T_cfg7_task_0031_user_0020_scene_0007_cfg_0007_104122063633#0", + "gt": "[[234, 121], [212, 149], [210, 141], [199, 141], [200, 155], [192, 127], [192, 147], [170, 211], [192, 148], [202, 138]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0038_user_0015_scene_0010_cfg_0001_038522062547#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the cup', and now you are performing subtask 'pick up the cup.'\nWith start location [406, 134], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[406, 134], [437, 125], [413, 132], [410, 119], [416, 118], [411, 100], [392, 86], [399, 67], [407, 65], [415, 48]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0038_user_0015_scene_0010_cfg_0001_038522062547#0.jpg", + "gt": "[[406, 134], [437, 125], [413, 132], [410, 119], [416, 118], [411, 100], [392, 86], [399, 67], [407, 65], [415, 48]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0044_user_0014_scene_0005_cfg_0007_104122064161#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up a bag of things', and now you are performing subtask 'pick up a bag of things.'\nFrom start point [337, 115], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[337, 115], [346, 126], [355, 152], [373, 184], [364, 226], [365, 207], [360, 192], [352, 144], [338, 112], [340, 95]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg7_task_0044_user_0014_scene_0005_cfg_0007_104122064161#0.jpg", + "gt": "[[337, 115], [346, 126], [355, 152], [373, 184], [364, 226], [365, 207], [360, 192], [352, 144], [338, 112], [340, 95]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0065_user_0010_scene_0005_cfg_0001_819112070044#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with small Lego blocks for the nth time with n blocks', and now you are performing subtask 'pick up the black small Lego block from the table, transfer the black small Lego block from the table to the gray base plate, place the black small Lego block on the gray base plate, press the black small Lego block.'\nThe trajectory starts at [400, 168]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[400, 168], [367, 189], [382, 174], [373, 159], [382, 170], [400, 166], [391, 150], [400, 203], [387, 202], [403, 206]]}" + } + ], + "images": "RH20T_cfg1_task_0065_user_0010_scene_0005_cfg_0001_819112070044#0", + "gt": "[[400, 168], [367, 189], [382, 174], [373, 159], [382, 170], [400, 166], [391, 150], [400, 203], [387, 202], [403, 206]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "79222_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the carrot plushie in the pan', and now you are performing subtask 'put the carrot plushie in the pan.'\nYou begin at [193, 1]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[193, 1], [176, 39], [157, 56], [153, 66], [149, 60], [136, 56], [131, 61], [131, 68], [135, 55], [132, 57]]}" + } + ], + "images": "79222_exterior_image_2_left#0", + "gt": "[[193, 1], [176, 39], [157, 56], [153, 66], [149, 60], [136, 56], [131, 61], [131, 68], [135, 55], [132, 57]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0085_user_0007_scene_0002_cfg_0005_104122061850#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the bubble ring from the assembled bubble ring and ball', and now you are performing subtask 'remove the bubble ring from the assembled bubble ring and ball.'\nBegin at [305, 50] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[305, 50], [334, 62], [377, 98], [384, 126], [380, 122], [380, 132], [375, 125], [377, 114], [344, 105], [341, 93]]}" + } + ], + "images": "RH20T_cfg5_task_0085_user_0007_scene_0002_cfg_0005_104122061850#0", + "gt": "[[305, 50], [334, 62], [377, 98], [384, 126], [380, 122], [380, 132], [375, 125], [377, 114], [344, 105], [341, 93]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "48713_exterior_image_2_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack up the cups', and now you are performing subtask 'place the cup on top of another cup.'\nYou begin at [159, 94]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[159, 94], [162, 89], [169, 97], [168, 115], [170, 83], [161, 57], [157, 60], [166, 72], [159, 111], [156, 79]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/48713_exterior_image_2_left#179.jpg", + "gt": "[[159, 94], [162, 89], [169, 97], [168, 115], [170, 83], [161, 57], [157, 60], [166, 72], [159, 111], [156, 79]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "27732_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the marker inside the green cup', and now you are performing subtask 'put the marker inside the green cup.'\nWith start location [191, 22], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[191, 22], [188, 87], [176, 99], [181, 111], [183, 83], [192, 71], [230, 61], [220, 94], [216, 97], [215, 68]]}" + } + ], + "images": "27732_exterior_image_2_left#0", + "gt": "[[191, 22], [188, 87], [176, 99], [181, 111], [183, 83], [192, 71], [230, 61], [220, 94], [216, 97], [215, 68]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0063_user_0020_scene_0008_cfg_0007_037522061512#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'use a shovel to scoop up an object', and now you are performing subtask 'use a shovel to scoop up an object.'\nWith start location [261, 86], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[261, 86], [233, 146], [233, 167], [206, 209], [215, 161], [254, 143], [232, 164], [235, 180], [243, 123], [262, 104]]}" + } + ], + "images": "RH20T_cfg7_task_0063_user_0020_scene_0008_cfg_0007_037522061512#0", + "gt": "[[261, 86], [233, 146], [233, 167], [206, 209], [215, 161], [254, 143], [232, 164], [235, 180], [243, 123], [262, 104]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0103_user_0010_scene_0005_cfg_0001_038522063145#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the plate to the goal post', and now you are performing subtask 'move the plate to the goal post.'\nWith start location [440, 99], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[440, 99], [445, 182], [453, 173], [448, 164], [368, 88], [340, 85], [384, 80], [430, 98], [444, 90], [444, 90]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0103_user_0010_scene_0005_cfg_0001_038522063145#0.jpg", + "gt": "[[440, 99], [445, 182], [453, 173], [448, 164], [368, 88], [340, 85], [384, 80], [430, 98], [444, 90], [444, 90]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0096_user_0020_scene_0003_cfg_0006_104122064161#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take something out of a drawer', and now you are performing subtask 'pull the handle of the drawer, pick up the object from inside the drawer, transfer the object from inside the drawer to above the desk, place the object on the desk.'\nStart at [343, 184]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[343, 184], [323, 217], [333, 232], [344, 146], [324, 138], [321, 144], [333, 163], [337, 155], [329, 155], [331, 115]]}" + } + ], + "images": "RH20T_cfg6_task_0096_user_0020_scene_0003_cfg_0006_104122064161#564", + "gt": "[[343, 184], [323, 217], [333, 232], [344, 146], [324, 138], [321, 144], [333, 163], [337, 155], [329, 155], [331, 115]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0003_user_0014_scene_0006_cfg_0005_105422061350#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press three buttons from left to right in sequence', and now you are performing subtask 'press the green button on the gray and white base, press the red button on the black and orange base.'\nThe trajectory starts at [242, 55]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[242, 55], [242, 42], [237, 46], [213, 93], [202, 101], [192, 92], [191, 107], [199, 103], [213, 66], [225, 53]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0003_user_0014_scene_0006_cfg_0005_105422061350#400.jpg", + "gt": "[[242, 55], [242, 42], [237, 46], [213, 93], [202, 101], [192, 92], [191, 107], [199, 103], [213, 66], [225, 53]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "38044_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the light red object on the right side of the table', and now you are performing subtask 'put the light red object on the right side of the table.'\nBegin at [133, 0] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[133, 0], [122, 4], [146, 79], [135, 93], [121, 89], [144, 95], [149, 114], [141, 107], [111, 132], [129, 128]]}" + } + ], + "images": "38044_exterior_image_2_left#0", + "gt": "[[133, 0], [122, 4], [146, 79], [135, 93], [121, 89], [144, 95], [149, 114], [141, 107], [111, 132], [129, 128]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg3_task_0038_user_0010_scene_0010_cfg_0003_038522062288#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the cup', and now you are performing subtask 'pick up the cup.'\nYour starting position is [238, 128]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[238, 128], [263, 120], [220, 154], [196, 193], [169, 201], [146, 241], [136, 228], [121, 237], [156, 202], [184, 149]]}" + } + ], + "images": "RH20T_cfg3_task_0038_user_0010_scene_0010_cfg_0003_038522062288#0", + "gt": "[[238, 128], [263, 120], [220, 154], [196, 193], [169, 201], [146, 241], [136, 228], [121, 237], [156, 202], [184, 149]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0043_user_0014_scene_0008_cfg_0006_104122064161#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unscrew the lid from the jar', and now you are performing subtask 'twist the lid of the jar counterclockwise.'\nFrom start point [320, 177], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[320, 177], [320, 180], [319, 182], [322, 182], [322, 185], [322, 183], [322, 184], [321, 184], [322, 184], [324, 187]]}" + } + ], + "images": "RH20T_cfg6_task_0043_user_0014_scene_0008_cfg_0006_104122064161#430", + "gt": "[[320, 177], [320, 180], [319, 182], [322, 182], [322, 185], [322, 183], [322, 184], [321, 184], [322, 184], [324, 187]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "32431_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the detergent tray on the second washing machine', and now you are performing subtask 'open the detergent tray on the second washing machine.'\nStart at [230, 73]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[230, 73], [237, 78], [235, 100], [222, 108], [233, 116], [250, 117], [248, 113], [253, 96], [247, 77], [249, 61]]}" + } + ], + "images": "32431_exterior_image_2_left#0", + "gt": "[[230, 73], [237, 78], [235, 100], [222, 108], [233, 116], [250, 117], [248, 113], [253, 96], [247, 77], [249, 61]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0127_user_0020_scene_0006_cfg_0006_104122064161#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'plug in the power cord of the desk lamp, turn on the socket, and light up the desk lamp', and now you are performing subtask 'pick up the power cable on the table, transfer the power cable from the table to the socket on the desktop.'\nYour starting position is [338, 111]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[338, 111], [343, 101], [354, 99], [429, 106], [422, 151], [427, 132], [412, 127], [392, 134], [385, 147], [385, 147]]}" + } + ], + "images": "RH20T_cfg6_task_0127_user_0020_scene_0006_cfg_0006_104122064161#0", + "gt": "[[338, 111], [343, 101], [354, 99], [429, 106], [422, 151], [427, 132], [412, 127], [392, 134], [385, 147], [385, 147]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0037_user_0020_scene_0008_cfg_0006_104122063633#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'pick up the first block on the table, transfer the first block from the table to above the second block, place the first block on top of the second block, pick up the third block on the table.'\nStart at [233, 118]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[233, 118], [197, 111], [191, 124], [201, 146], [208, 130], [223, 131], [246, 149], [237, 129], [233, 130], [237, 144]]}" + } + ], + "images": "RH20T_cfg6_task_0037_user_0020_scene_0008_cfg_0006_104122063633#0", + "gt": "[[233, 118], [197, 111], [191, 124], [201, 146], [208, 130], [223, 131], [246, 149], [237, 129], [233, 130], [237, 144]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "29433_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pour the contents in the jug into the red bowl', and now you are performing subtask 'pour the contents in the jug into the red bowl.'\nYour starting position is [301, 23]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[301, 23], [258, 64], [242, 102], [247, 124], [225, 134], [223, 110], [235, 110], [248, 83], [219, 121], [222, 130]]}" + } + ], + "images": "29433_exterior_image_2_left#0", + "gt": "[[301, 23], [258, 64], [242, 102], [247, 124], [225, 134], [223, 110], [235, 110], [248, 83], [219, 121], [222, 130]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "36682_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the brown object in the drawer, then put in the white bowl, then put the knife in the drawer', and now you are performing subtask 'place the brown object in the white bowl.'\nWith start location [212.5, 35.5], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[212.5, 35.5], [213.5, 20.5], [209.5, 36.5], [217.5, 33.5], [224.5, 38.5], [216.5, 50.5], [185.5, 40.5], [176.5, 43.5], [175.5, 49.5], [181.5, 48.5]]}" + } + ], + "images": "36682_exterior_image_1_left#638", + "gt": "[[212.5, 35.5], [213.5, 20.5], [209.5, 36.5], [217.5, 33.5], [224.5, 38.5], [216.5, 50.5], [185.5, 40.5], [176.5, 43.5], [175.5, 49.5], [181.5, 48.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "26173_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the slice of bread in the toaster, push the lever on the toaster down', and now you are performing subtask 'press the lever of the toaster.'\nThe trajectory starts at [233.0, 108.0]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[233.0, 108.0], [203.0, 121.0], [207.0, 139.0], [226.0, 139.0], [216.0, 162.0], [226.0, 137.0], [226.0, 162.0], [214.0, 143.0], [199.0, 137.0], [199.0, 137.0]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/26173_exterior_image_1_left#271.jpg", + "gt": "[[233.0, 108.0], [203.0, 121.0], [207.0, 139.0], [226.0, 139.0], [216.0, 162.0], [226.0, 137.0], [226.0, 162.0], [214.0, 143.0], [199.0, 137.0], [199.0, 137.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "31401_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the purple packet out of the sink and place it on the countertop', and now you are performing subtask 'take the purple packet out of the sink and place it on the countertop.'\nWith start location [95, 61], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[95, 61], [125, 103], [154, 162], [167, 162], [168, 171], [167, 157], [163, 150], [150, 148], [106, 154], [112, 139]]}" + } + ], + "images": "31401_exterior_image_1_left#0", + "gt": "[[95, 61], [125, 103], [154, 162], [167, 162], [168, 171], [167, 157], [163, 150], [150, 148], [106, 154], [112, 139]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "83989_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the towel from the object and throw it on the table', and now you are performing subtask 'remove the towel from the object and throw it on the table.'\nYou start from [100, 40]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[100, 40], [122, 42], [134, 49], [128, 65], [118, 67], [119, 69], [106, 80], [113, 91], [118, 86], [118, 86]]}" + } + ], + "images": "83989_exterior_image_2_left#0", + "gt": "[[100, 40], [122, 42], [134, 49], [128, 65], [118, 67], [119, 69], [106, 80], [113, 91], [118, 86], [118, 86]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0058_user_0015_scene_0003_cfg_0001_819112070044#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn off the power strips', and now you are performing subtask 'press the fourth button on the power socket.'\nYou begin at [447, 189]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[447, 189], [447, 192], [450, 194], [449, 194], [454, 185], [457, 184], [452, 186], [426, 185], [414, 188], [406, 186]]}" + } + ], + "images": "RH20T_cfg1_task_0058_user_0015_scene_0003_cfg_0001_819112070044#262", + "gt": "[[447, 189], [447, 192], [450, 194], [449, 194], [454, 185], [457, 184], [452, 186], [426, 185], [414, 188], [406, 186]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "20007_exterior_image_1_left#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the drawer on the right, take out three mugs and place them on the countertop', and now you are performing subtask 'place the third cup on the kitchen countertop.'\nYour initial coordinate is [209, 121]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[209, 121], [214, 135], [205, 133], [222, 124], [217, 93], [206, 85], [182, 109], [193, 90], [219, 117], [219, 117]]}" + } + ], + "images": "20007_exterior_image_1_left#1100", + "gt": "[[209, 121], [214, 135], [205, 133], [222, 124], [217, 93], [206, 85], [182, 109], [193, 90], [219, 117], [219, 117]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0061_user_0020_scene_0003_cfg_0007_104122063633#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take everything out of the gift box', and now you are performing subtask 'pick up the lid on the container, transfer the lid from the container to the table.'\nStarting at [234, 121], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[234, 121], [208, 147], [208, 171], [195, 177], [200, 185], [182, 192], [180, 200], [180, 182], [192, 211], [185, 230]]}" + } + ], + "images": "RH20T_cfg7_task_0061_user_0020_scene_0003_cfg_0007_104122063633#0", + "gt": "[[234, 121], [208, 147], [208, 171], [195, 177], [200, 185], [182, 192], [180, 200], [180, 182], [192, 211], [185, 230]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0096_user_0007_scene_0003_cfg_0005_104122063678#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the drawer and place the cube on the table', and now you are performing subtask 'pull the handle of the drawer to pull open the drawer, pick up the block from the drawer, transfer the block from the drawer to the table, place the block on the table.'\nYour starting position is [372, 170]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[372, 170], [369, 143], [330, 143], [308, 188], [319, 161], [350, 143], [401, 155], [394, 180], [377, 194], [391, 152]]}" + } + ], + "images": "RH20T_cfg5_task_0096_user_0007_scene_0003_cfg_0005_104122063678#372", + "gt": "[[372, 170], [369, 143], [330, 143], [308, 188], [319, 161], [350, 143], [401, 155], [394, 180], [377, 194], [391, 152]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "45941_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the snickers bar in the sink', and now you are performing subtask 'put the snickers bar in the sink.'\nStart at [78, 60]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[78, 60], [68, 76], [81, 131], [94, 134], [98, 123], [112, 120], [163, 127], [172, 171], [167, 150], [129, 142]]}" + } + ], + "images": "45941_exterior_image_1_left#0", + "gt": "[[78, 60], [68, 76], [81, 131], [94, 134], [98, 123], [112, 120], [163, 127], [172, 171], [167, 150], [129, 142]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "70471_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the white and black mugs from the drawer, push the drawer closed, close the open bottom cabinet', and now you are performing subtask 'place the white cup on the countertop.'\nWith start location [102, 110], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[102, 110], [109, 106], [126, 108], [133, 116], [130, 126], [134, 128], [130, 124], [130, 104], [144, 87], [147, 95]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/70471_exterior_image_2_left#0.jpg", + "gt": "[[102, 110], [109, 106], [126, 108], [133, 116], [130, 126], [134, 128], [130, 124], [130, 104], [144, 87], [147, 95]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "35069_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the towel and put it on the couch', and now you are performing subtask 'fold the towel together.'\nYour starting position is [112, 59]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[112, 59], [173, 96], [184, 143], [174, 0], [91, 79], [107, 102], [138, 106], [186, 54], [248, 43], [197, 109]]}" + } + ], + "images": "35069_exterior_image_1_left#0", + "gt": "[[112, 59], [173, 96], [184, 143], [174, 0], [91, 79], [107, 102], [138, 106], [186, 54], [248, 43], [197, 109]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "27562_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'fold the towel then remove the object from the drawer', and now you are performing subtask 'place the object on the table.'\nThe trajectory starts at [147, 44]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[147, 44], [131, 47], [125, 54], [132, 65], [135, 56], [147, 52], [159, 58], [160, 65], [152, 82], [151, 62]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/27562_exterior_image_1_left#110.jpg", + "gt": "[[147, 44], [131, 47], [125, 54], [132, 65], [135, 56], [147, 52], [159, 58], [160, 65], [152, 82], [151, 62]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0094_user_0007_scene_0006_cfg_0005_037522062165#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open a box', and now you are performing subtask 'press the part of the box, press the part of the box.'\nFrom start point [217, 222], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[217, 222], [221, 225], [225, 224], [236, 215], [250, 209], [261, 198], [263, 198], [266, 202], [263, 202], [253, 215]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0094_user_0007_scene_0006_cfg_0005_037522062165#214.jpg", + "gt": "[[217, 222], [221, 225], [225, 224], [236, 215], [250, 209], [261, 198], [263, 198], [266, 202], [263, 202], [253, 215]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0038_user_0020_scene_0006_cfg_0007_104122061018#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the cup', and now you are performing subtask 'pick up the cup.'\nBegin at [363, 31] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[363, 31], [343, 56], [330, 116], [308, 127], [302, 146], [288, 136], [294, 125], [289, 96], [307, 69], [306, 58]]}" + } + ], + "images": "RH20T_cfg7_task_0038_user_0020_scene_0006_cfg_0007_104122061018#0", + "gt": "[[363, 31], [343, 56], [330, 116], [308, 127], [302, 146], [288, 136], [294, 125], [289, 96], [307, 69], [306, 58]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0033_user_0010_scene_0010_cfg_0005_104122063678#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'grasp a small block to sweep the other small block into the designated position', and now you are performing subtask 'push another block towards the mark, place the block on the mark.'\nStarting at [373, 274], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[373, 274], [348, 262], [366, 264], [397, 281], [406, 301], [405, 266], [384, 224], [329, 177], [323, 166], [333, 165]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0033_user_0010_scene_0010_cfg_0005_104122063678#681.jpg", + "gt": "[[373, 274], [348, 262], [366, 264], [397, 281], [406, 301], [405, 266], [384, 224], [329, 177], [323, 166], [333, 165]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0066_user_0016_scene_0001_cfg_0004_104122062823#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with large megabloks for the nth time with n blocks', and now you are performing subtask 'pick up a large Megablok from the bottom right corner, transfer the large Megablok from the bottom right corner to the designated building area on the table, place the large Megablok in the building area, press the large Megablok.'\nWith start location [501, 96], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[501, 96], [479, 73], [452, 67], [436, 89], [429, 125], [434, 98], [424, 107], [442, 89], [422, 60], [402, 52]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg4_task_0066_user_0016_scene_0001_cfg_0004_104122062823#151.jpg", + "gt": "[[501, 96], [479, 73], [452, 67], [436, 89], [429, 125], [434, 98], [424, 107], [442, 89], [422, 60], [402, 52]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0037_user_0014_scene_0001_cfg_0007_104122061330#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line', and now you are performing subtask 'pick up the second block from the table, transfer the second block from the table to the stacking position, place the second block on top of the first block, pick up the third block from the table.'\nYou begin at [309, 220]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[309, 220], [298, 208], [285, 204], [278, 203], [272, 208], [267, 205], [266, 207], [278, 201], [311, 217], [314, 221]]}" + } + ], + "images": "RH20T_cfg7_task_0037_user_0014_scene_0001_cfg_0007_104122061330#213", + "gt": "[[309, 220], [298, 208], [285, 204], [278, 203], [272, 208], [267, 205], [266, 207], [278, 201], [311, 217], [314, 221]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg2_task_0003_user_0006_scene_0007_cfg_0002_104422070044#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the three buttons in sequence', and now you are performing subtask 'press the gray base red button, press the yellow base green button.'\nWith start location [315, 201], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[315, 201], [304, 181], [292, 177], [293, 174], [293, 187], [287, 177], [284, 175], [282, 179], [285, 197], [292, 198]]}" + } + ], + "images": "RH20T_cfg2_task_0003_user_0006_scene_0007_cfg_0002_104422070044#175", + "gt": "[[315, 201], [304, 181], [292, 177], [293, 174], [293, 187], [287, 177], [284, 175], [282, 179], [285, 197], [292, 198]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "43469_exterior_image_1_left#TrajectoryPrediction_Task#8", + "task": "TrajectoryPrediction_Task", + "p_index": 8, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'fold the sweatshirt twice', and now you are performing subtask 'fold the sweatshirt in half again.'\nThe trajectory starts at [195, 57]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[195, 57], [194, 58], [191, 55], [187, 60], [182, 60], [176, 56], [169, 44], [172, 42], [176, 42], [192, 47]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/43469_exterior_image_1_left#329.jpg", + "gt": "[[195, 57], [194, 58], [191, 55], [187, 60], [182, 60], [176, 56], [169, 44], [172, 42], [176, 42], [192, 47]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "38414_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the plush toy and put it on the plate, then move the tap to the right', and now you are performing subtask 'twist the faucet counterclockwise.'\nStart at [55.5, 2.0]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[55.5, 2.0], [92.5, 51.0], [103.5, 75.0], [115.5, 90.0], [124.5, 86.0], [133.5, 90.0], [133.5, 94.0], [122.5, 92.0], [125.5, 87.0], [160.5, 62.0]]}" + } + ], + "images": "38414_exterior_image_1_left#0", + "gt": "[[55.5, 2.0], [92.5, 51.0], [103.5, 75.0], [115.5, 90.0], [124.5, 86.0], [133.5, 90.0], [133.5, 94.0], [122.5, 92.0], [125.5, 87.0], [160.5, 62.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "16307_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'line up the empty water bottles', and now you are performing subtask 'pick up the fifth empty water bottle on the table.'\nYou begin at [97, 153]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[97, 153], [106, 142], [117, 149], [111, 151], [115, 158], [152, 165], [131, 149], [128, 138], [154, 122], [168, 144]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/16307_exterior_image_1_left#557.jpg", + "gt": "[[97, 153], [106, 142], [117, 149], [111, 151], [115, 158], [152, 165], [131, 149], [128, 138], [154, 122], [168, 144]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0018_user_0014_scene_0007_cfg_0006_104122061018#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'sliding the Lego blocks on the desktop', and now you are performing subtask 'sliding the Lego blocks on the desktop.'\nYou begin at [367, 28]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[367, 28], [342, 75], [332, 104], [333, 117], [342, 129], [330, 112], [339, 57], [346, 42], [362, 42], [362, 67]]}" + } + ], + "images": "RH20T_cfg6_task_0018_user_0014_scene_0007_cfg_0006_104122061018#0", + "gt": "[[367, 28], [342, 75], [332, 104], [333, 117], [342, 129], [330, 112], [339, 57], [346, 42], [362, 42], [362, 67]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "41068_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the drawer and then put the brown object from the bowl on the green cloth', and now you are performing subtask 'open the drawer and then put the brown object from the bowl on the green cloth.'\nStart at [139.0, 3.5]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[139.0, 3.5], [182.0, 78.5], [213.0, 85.5], [182.0, 88.5], [189.0, 69.5], [175.0, 46.5], [141.0, 69.5], [163.0, 63.5], [169.0, 76.5], [167.0, 56.5]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/41068_exterior_image_1_left#0.jpg", + "gt": "[[139.0, 3.5], [182.0, 78.5], [213.0, 85.5], [182.0, 88.5], [189.0, 69.5], [175.0, 46.5], [141.0, 69.5], [163.0, 63.5], [169.0, 76.5], [167.0, 56.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "42632_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the lid', and now you are performing subtask 'press the lid.'\nYou start from [173, 114]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[173, 114], [176, 114], [176, 115], [177, 115], [179, 121], [179, 122], [177, 119], [176, 114], [173, 113], [173, 113]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/42632_exterior_image_1_left#115.jpg", + "gt": "[[173, 114], [176, 114], [176, 115], [177, 115], [179, 121], [179, 122], [177, 119], [176, 114], [173, 113], [173, 113]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0065_user_0010_scene_0005_cfg_0001_038522063145#TrajectoryPrediction_Task#14", + "task": "TrajectoryPrediction_Task", + "p_index": 14, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with small Lego blocks for the nth time with n blocks', and now you are performing subtask 'pick up the red small Lego block from the desktop, transfer the red small Lego block from the desktop to the blue small Lego block, place the red small Lego block on the blue small Lego block.'\nStarting at [442, 134], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[442, 134], [431, 116], [434, 125], [440, 120], [445, 122], [454, 152], [448, 153], [452, 156], [447, 167], [452, 150]]}" + } + ], + "images": "RH20T_cfg1_task_0065_user_0010_scene_0005_cfg_0001_038522063145#1478", + "gt": "[[442, 134], [431, 116], [434, 125], [440, 120], [445, 122], [454, 152], [448, 153], [452, 156], [447, 167], [452, 150]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0057_user_0007_scene_0003_cfg_0005_105422061350#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn on the power strips', and now you are performing subtask 'press the third button on the power socket, press the fourth button on the power socket.'\nStarting at [291, 137], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[291, 137], [290, 139], [283, 138], [286, 140], [284, 139], [288, 136], [292, 136], [295, 130], [293, 125], [298, 126]]}" + } + ], + "images": "RH20T_cfg5_task_0057_user_0007_scene_0003_cfg_0005_105422061350#527", + "gt": "[[291, 137], [290, 139], [283, 138], [286, 140], [284, 139], [288, 136], [292, 136], [295, 130], [293, 125], [298, 126]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "73393_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the spoon to above the table', and now you are performing subtask 'move the spoon to above the table.'\nYou start from [181, 21]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[181, 21], [184, 55], [174, 63], [172, 83], [165, 90], [178, 108], [183, 109], [189, 86], [181, 38], [194, 33]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/73393_exterior_image_2_left#0.jpg", + "gt": "[[181, 21], [184, 55], [174, 63], [172, 83], [165, 90], [178, 108], [183, 109], [189, 86], [181, 38], [194, 33]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0002_user_0010_scene_0001_cfg_0005_104122063678#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pull out a napkin', and now you are performing subtask 'pull out a napkin.'\nBegin at [340, 150] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[340, 150], [318, 166], [315, 185], [322, 188], [323, 170], [343, 149], [363, 152], [376, 178], [359, 185], [355, 202]]}" + } + ], + "images": "RH20T_cfg5_task_0002_user_0010_scene_0001_cfg_0005_104122063678#0", + "gt": "[[340, 150], [318, 166], [315, 185], [322, 188], [323, 170], [343, 149], [363, 152], [376, 178], [359, 185], [355, 202]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "81170_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn the faucet clockwise', and now you are performing subtask 'turn the faucet clockwise.'\nYou begin at [202, 77]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[202, 77], [189, 51], [179, 57], [197, 46], [174, 71], [183, 68], [188, 76], [174, 85], [141, 89], [140, 76]]}" + } + ], + "images": "81170_exterior_image_1_left#0", + "gt": "[[202, 77], [189, 51], [179, 57], [197, 46], [174, 71], [183, 68], [188, 76], [174, 85], [141, 89], [140, 76]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "17981_exterior_image_2_left#TrajectoryPrediction_Task#16", + "task": "TrajectoryPrediction_Task", + "p_index": 16, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the orange cloth', and now you are performing subtask 'fold the cloth on the table for the last time.'\nYour starting position is [206, 135]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[206, 135], [205, 133], [202, 133], [202, 132], [201, 132], [200, 130], [196, 128], [195, 128], [196, 131], [196, 131]]}" + } + ], + "images": "17981_exterior_image_2_left#431", + "gt": "[[206, 135], [205, 133], [202, 133], [202, 132], [201, 132], [200, 130], [196, 128], [195, 128], [196, 131], [196, 131]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0034_user_0015_scene_0008_cfg_0001_038522062547#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the squares into a pyramid shape', and now you are performing subtask 'place the third block beside the second block, pick up the fourth block from the table, transfer the fourth block from the table to above the first and second blocks, place the fourth block on top of the first and second blocks.'\nFrom start point [392, 126], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[392, 126], [387, 85], [453, 131], [466, 198], [447, 207], [456, 195], [442, 172], [426, 163], [413, 172], [387, 155]]}" + } + ], + "images": "RH20T_cfg1_task_0034_user_0015_scene_0008_cfg_0001_038522062547#564", + "gt": "[[392, 126], [387, 85], [453, 131], [466, 198], [447, 207], [456, 195], [442, 172], [426, 163], [413, 172], [387, 155]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "61723_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the pen out of the cup, put it on the table, then move the cup to the left side of the table, and finally put the pen back in the cup', and now you are performing subtask 'pick up the cup from the table.'\nBegin at [155, 49] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[155, 49], [174, 47], [212, 72], [225, 96], [250, 111], [259, 131], [251, 119], [255, 97], [237, 99], [246, 115]]}" + } + ], + "images": "61723_exterior_image_1_left#0", + "gt": "[[155, 49], [174, 47], [212, 72], [225, 96], [250, 111], [259, 131], [251, 119], [255, 97], [237, 99], [246, 115]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0031_user_0020_scene_0007_cfg_0007_104122061018#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'cover the box', and now you are performing subtask 'cover the box.'\nStarting at [363, 30], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[363, 30], [321, 79], [296, 70], [273, 95], [277, 63], [297, 67], [332, 117], [332, 172], [337, 80], [352, 64]]}" + } + ], + "images": "RH20T_cfg7_task_0031_user_0020_scene_0007_cfg_0007_104122061018#0", + "gt": "[[363, 30], [321, 79], [296, 70], [273, 95], [277, 63], [297, 67], [332, 117], [332, 172], [337, 80], [352, 64]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "57236_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the clear lid on the white plate', and now you are performing subtask 'put the clear lid on the white plate.'\nYour starting position is [134, 7]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[134, 7], [135, 22], [143, 40], [135, 79], [142, 83], [135, 72], [127, 73], [130, 74], [128, 62], [131, 62]]}" + } + ], + "images": "57236_exterior_image_1_left#0", + "gt": "[[134, 7], [135, 22], [143, 40], [135, 79], [142, 83], [135, 72], [127, 73], [130, 74], [128, 62], [131, 62]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0036_user_0014_scene_0005_cfg_0007_104122061330#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'shake the test tube', and now you are performing subtask 'pick up the second test tube on the left, shake the test tube, place the test tube back in the rack.'\nFrom start point [303, 89], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[303, 89], [303, 71], [272, 85], [293, 60], [284, 73], [289, 72], [301, 87], [316, 150], [313, 110], [307, 103]]}" + } + ], + "images": "RH20T_cfg7_task_0036_user_0014_scene_0005_cfg_0007_104122061330#154", + "gt": "[[303, 89], [303, 71], [272, 85], [293, 60], [284, 73], [289, 72], [301, 87], [316, 150], [313, 110], [307, 103]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0014_user_0010_scene_0005_cfg_0004_038522062288#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the object from the scale', and now you are performing subtask 'remove the object from the scale.'\nYou start from [232, 120]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[232, 120], [227, 137], [241, 156], [222, 211], [242, 200], [248, 265], [294, 310], [204, 254], [201, 262], [201, 262]]}" + } + ], + "images": "RH20T_cfg4_task_0014_user_0010_scene_0005_cfg_0004_038522062288#0", + "gt": "[[232, 120], [227, 137], [241, 156], [222, 211], [242, 200], [248, 265], [294, 310], [204, 254], [201, 262], [201, 262]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg3_task_0003_user_0016_scene_0001_cfg_0003_104122062295#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press three buttons from left to right in sequence', and now you are performing subtask 'press the green button on the right, press the green button in the middle.'\nYou begin at [265, 86]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[265, 86], [315, 112], [250, 89], [265, 99], [225, 68], [178, 50], [162, 63], [147, 101], [168, 74], [206, 107]]}" + } + ], + "images": "RH20T_cfg3_task_0003_user_0016_scene_0001_cfg_0003_104122062295#0", + "gt": "[[265, 86], [315, 112], [250, 89], [265, 99], [225, 68], [178, 50], [162, 63], [147, 101], [168, 74], [206, 107]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0018_user_0010_scene_0009_cfg_0005_104122063678#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'throw a block pulled out from the middle of the Jenga tower onto the table', and now you are performing subtask 'throw a block pulled out from the middle of the Jenga tower onto the table.'\nStart at [323, 132]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[323, 132], [320, 153], [366, 183], [345, 205], [352, 202], [353, 193], [336, 174], [334, 156], [348, 145], [336, 144]]}" + } + ], + "images": "RH20T_cfg5_task_0018_user_0010_scene_0009_cfg_0005_104122063678#0", + "gt": "[[323, 132], [320, 153], [366, 183], [345, 205], [352, 202], [353, 193], [336, 174], [334, 156], [348, 145], [336, 144]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "64004_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the left cabinet door', and now you are performing subtask 'open the left cabinet door.'\nStarting at [181, 56], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[181, 56], [189, 58], [183, 56], [187, 61], [205, 60], [253, 75], [277, 87], [231, 79], [208, 65], [208, 65]]}" + } + ], + "images": "64004_exterior_image_2_left#0", + "gt": "[[181, 56], [189, 58], [183, 56], [187, 61], [205, 60], [253, 75], [277, 87], [231, 79], [208, 65], [208, 65]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "80402_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the two bottles and put them on the counter', and now you are performing subtask 'pick up the second bottle on the table.'\nYou start from [92, 85]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[92, 85], [90, 79], [98, 67], [105, 67], [117, 74], [127, 89], [129, 98], [130, 114], [122, 117], [126, 117]]}" + } + ], + "images": "80402_exterior_image_1_left#163", + "gt": "[[92, 85], [90, 79], [98, 67], [105, 67], [117, 74], [127, 89], [129, 98], [130, 114], [122, 117], [126, 117]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "72943_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the tap to the right', and now you are performing subtask 'move the tap to the right.'\nYour starting position is [78, 88]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[78, 88], [135, 89], [191, 57], [218, 70], [200, 47], [228, 65], [217, 76], [234, 99], [320, 142], [210, 76]]}" + } + ], + "images": "72943_exterior_image_1_left#0", + "gt": "[[78, 88], [135, 89], [191, 57], [218, 70], [200, 47], [228, 65], [217, 76], [234, 99], [320, 142], [210, 76]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg2_task_0101_user_0007_scene_0002_cfg_0002_037522062165#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'cleaning the table with a cloth', and now you are performing subtask 'cleaning the table with a cloth.'\nStarting at [280, 175], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[280, 175], [251, 183], [229, 202], [201, 212], [175, 247], [232, 275], [275, 282], [277, 265], [252, 225], [254, 214]]}" + } + ], + "images": "RH20T_cfg2_task_0101_user_0007_scene_0002_cfg_0002_037522062165#0", + "gt": "[[280, 175], [251, 183], [229, 202], [201, 212], [175, 247], [232, 275], [275, 282], [277, 265], [252, 225], [254, 214]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "40869_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the yellow cube to the right', and now you are performing subtask 'move the yellow cube to the right.'\nThe trajectory starts at [87.0, 2.5]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[87.0, 2.5], [119.0, 68.5], [121.0, 83.5], [115.0, 87.5], [117.0, 79.5], [122.0, 83.5], [129.0, 116.5], [135.0, 108.5], [110.0, 60.5], [122.0, 70.5]]}" + } + ], + "images": "40869_exterior_image_1_left#0", + "gt": "[[87.0, 2.5], [119.0, 68.5], [121.0, 83.5], [115.0, 87.5], [117.0, 79.5], [122.0, 83.5], [129.0, 116.5], [135.0, 108.5], [110.0, 60.5], [122.0, 70.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "75616_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'use the pen to stir the contents in the mug then empty the mug', and now you are performing subtask 'pick up the cup from the table.'\nYou begin at [219, 81]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[219, 81], [212, 72], [207, 121], [177, 84], [159, 93], [155, 118], [157, 101], [142, 102], [137, 147], [162, 107]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/75616_exterior_image_2_left#0.jpg", + "gt": "[[219, 81], [212, 72], [207, 121], [177, 84], [159, 93], [155, 118], [157, 101], [142, 102], [137, 147], [162, 107]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "14166_exterior_image_2_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the towel from the bar and put it on the seat', and now you are performing subtask 'place the towel onto the chair.'\nFrom start point [109, 81], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[109, 81], [103, 73], [113, 75], [116, 58], [141, 25], [146, 0], [142, 43], [147, 74], [158, 75], [130, 68]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/14166_exterior_image_2_left#238.jpg", + "gt": "[[109, 81], [103, 73], [113, 75], [116, 58], [141, 25], [146, 0], [142, 43], [147, 74], [158, 75], [130, 68]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "17817_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the blue block on the tower', and now you are performing subtask 'insert the blue block into the block tower.'\nThe trajectory starts at [76, 67]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[76, 67], [89, 109], [82, 119], [89, 118], [72, 86], [111, 91], [95, 86], [106, 89], [93, 80], [104, 71]]}" + } + ], + "images": "17817_exterior_image_2_left#0", + "gt": "[[76, 67], [89, 109], [82, 119], [89, 118], [72, 86], [111, 91], [95, 86], [106, 89], [93, 80], [104, 71]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "16270_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'fold the towel', and now you are performing subtask 'fold the towel.'\nStarting at [320, 1], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[320, 1], [221, 54], [187, 98], [192, 112], [180, 112], [182, 129], [175, 119], [191, 92], [250, 50], [224, 40]]}" + } + ], + "images": "16270_exterior_image_1_left#0", + "gt": "[[320, 1], [221, 54], [187, 98], [192, 112], [180, 112], [182, 129], [175, 119], [191, 92], [250, 50], [224, 40]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "8075_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the lid from the silver object and place it on the table', and now you are performing subtask 'remove the lid from the silver object and place it on the table.'\nStarting at [180, 2], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[180, 2], [172, 36], [202, 57], [185, 68], [188, 76], [186, 45], [214, 53], [200, 52], [206, 60], [185, 29]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/8075_exterior_image_1_left#0.jpg", + "gt": "[[180, 2], [172, 36], [202, 57], [185, 68], [188, 76], [186, 45], [214, 53], [200, 52], [206, 60], [185, 29]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "36648_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close the microwave door, close the rice cooker, push the lever on the toaster downwards', and now you are performing subtask 'push the rice cooker lid to the closed position.'\nBegin at [177, 40] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[177, 40], [173, 46], [151, 48], [118, 64], [103, 66], [121, 66], [133, 73], [126, 81], [124, 101], [120, 96]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/36648_exterior_image_1_left#123.jpg", + "gt": "[[177, 40], [173, 46], [151, 48], [118, 64], [103, 66], [121, 66], [133, 73], [126, 81], [124, 101], [120, 96]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "91226_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the green marker inside the yellow mug', and now you are performing subtask 'put the green marker inside the yellow mug.'\nYou start from [149, 67]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[149, 67], [139, 75], [159, 84], [138, 85], [138, 119], [142, 123], [145, 115], [140, 97], [120, 114], [116, 111]]}" + } + ], + "images": "91226_exterior_image_2_left#0", + "gt": "[[149, 67], [139, 75], [159, 84], [138, 85], [138, 119], [142, 123], [145, 115], [140, 97], [120, 114], [116, 111]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "27813_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn off the toaster', and now you are performing subtask 'turn off the toaster.'\nYour starting position is [187.5, 6.0]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[187.5, 6.0], [213.5, 109.0], [212.5, 106.0], [210.5, 109.0], [211.5, 105.0], [212.5, 111.0], [212.5, 107.0], [202.5, 113.0], [172.5, 102.0], [159.5, 86.0]]}" + } + ], + "images": "27813_exterior_image_1_left#0", + "gt": "[[187.5, 6.0], [213.5, 109.0], [212.5, 106.0], [210.5, 109.0], [211.5, 105.0], [212.5, 111.0], [212.5, 107.0], [202.5, 113.0], [172.5, 102.0], [159.5, 86.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "89302_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the rectangular object and place it on the other shapes', and now you are performing subtask 'pick up the rectangular object and place it on the other shapes.'\nFrom start point [141.0, 2.0], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[141.0, 2.0], [188.0, 38.0], [192.0, 54.0], [186.0, 74.0], [175.0, 63.0], [159.0, 63.0], [150.0, 59.0], [136.0, 61.0], [134.0, 69.0], [135.0, 55.0]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/89302_exterior_image_1_left#0.jpg", + "gt": "[[141.0, 2.0], [188.0, 38.0], [192.0, 54.0], [186.0, 74.0], [175.0, 63.0], [159.0, 63.0], [150.0, 59.0], [136.0, 61.0], [134.0, 69.0], [135.0, 55.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "5842_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the lid from the pot and put it on the table', and now you are performing subtask 'remove the lid from the pot and put it on the table.'\nYour starting position is [238, 0]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[238, 0], [150, 47], [155, 64], [170, 64], [159, 67], [156, 30], [173, 21], [234, 41], [238, 61], [207, 79]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/5842_exterior_image_2_left#0.jpg", + "gt": "[[238, 0], [150, 47], [155, 64], [170, 64], [159, 67], [156, 30], [173, 21], [234, 41], [238, 61], [207, 79]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "60918_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pour the candy out of the clear cup and onto the table', and now you are performing subtask 'pour the candy out of the clear cup and onto the table.'\nYou begin at [154, 142]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[154, 142], [173, 142], [178, 157], [187, 146], [194, 157], [216, 135], [242, 160], [224, 143], [203, 157], [195, 151]]}" + } + ], + "images": "60918_exterior_image_1_left#0", + "gt": "[[154, 142], [173, 142], [178, 157], [187, 146], [194, 157], [216, 135], [242, 160], [224, 143], [203, 157], [195, 151]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0037_user_0007_scene_0004_cfg_0005_036422060215#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'place the third block on top of the second block, pick up the fourth block from the surface, place the fourth block on top of the third block.'\nBegin at [274, 109] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[274, 109], [277, 92], [265, 86], [207, 102], [173, 162], [177, 172], [222, 86], [267, 61], [284, 80], [289, 53]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0037_user_0007_scene_0004_cfg_0005_036422060215#915.jpg", + "gt": "[[274, 109], [277, 92], [265, 86], [207, 102], [173, 162], [177, 172], [222, 86], [267, 61], [284, 80], [289, 53]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "1571_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move all the plush toys from the basket to the table one by one', and now you are performing subtask 'pick up the second toy from the basket.'\nYour initial coordinate is [234, 58]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[234, 58], [169, 0], [162, 16], [179, 9], [165, 23], [168, 69], [148, 86], [137, 72], [121, 103], [140, 86]]}" + } + ], + "images": "1571_exterior_image_1_left#0", + "gt": "[[234, 58], [169, 0], [162, 16], [179, 9], [165, 23], [168, 69], [148, 86], [137, 72], [121, 103], [140, 86]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "63177_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the objects on the plate and put them in the bin', and now you are performing subtask 'take the object from the plate and move it to the bowl.'\nStart at [245, 9]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[245, 9], [214, 14], [220, 14], [203, 30], [204, 36], [180, 60], [192, 43], [181, 37], [181, 30], [199, 49]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/63177_exterior_image_1_left#0.jpg", + "gt": "[[245, 9], [214, 14], [220, 14], [203, 30], [204, 36], [180, 60], [192, 43], [181, 37], [181, 30], [199, 49]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0044_user_0020_scene_0001_cfg_0007_104122061330#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up a bag of things', and now you are performing subtask 'pick up a bag of things.'\nBegin at [266, 103] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[266, 103], [268, 134], [276, 166], [282, 173], [286, 200], [295, 210], [291, 211], [285, 181], [285, 139], [274, 128]]}" + } + ], + "images": "RH20T_cfg7_task_0044_user_0020_scene_0001_cfg_0007_104122061330#0", + "gt": "[[266, 103], [268, 134], [276, 166], [282, 173], [286, 200], [295, 210], [291, 211], [285, 181], [285, 139], [274, 128]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "70745_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the measuring tape', and now you are performing subtask 'move the measuring tape.'\nYour initial coordinate is [177, 2]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[177, 2], [165, 22], [149, 38], [151, 60], [153, 56], [161, 53], [154, 56], [152, 64], [151, 54], [148, 51]]}" + } + ], + "images": "70745_exterior_image_2_left#0", + "gt": "[[177, 2], [165, 22], [149, 38], [151, 60], [153, 56], [161, 53], [154, 56], [152, 64], [151, 54], [148, 51]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0010_user_0010_scene_0002_cfg_0005_104422070044#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'place the handset of the telephone on the corresponding phone cradle', and now you are performing subtask 'place the handset of the telephone on the corresponding phone cradle.'\nStarting at [374, 132], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[374, 132], [396, 146], [419, 188], [420, 229], [415, 215], [393, 208], [391, 191], [349, 199], [368, 175], [368, 175]]}" + } + ], + "images": "RH20T_cfg5_task_0010_user_0010_scene_0002_cfg_0005_104422070044#0", + "gt": "[[374, 132], [396, 146], [419, 188], [420, 229], [415, 215], [393, 208], [391, 191], [349, 199], [368, 175], [368, 175]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "51601_exterior_image_2_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the pen into the bowl, then take it out and put it back on the table', and now you are performing subtask 'put the pen back on the table.'\nWith start location [177, 33], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[177, 33], [182, 43], [187, 44], [185, 51], [187, 40], [184, 31], [179, 36], [179, 62], [186, 74], [195, 81]]}" + } + ], + "images": "51601_exterior_image_2_left#107", + "gt": "[[177, 33], [182, 43], [187, 44], [185, 51], [187, 40], [184, 31], [179, 36], [179, 62], [186, 74], [195, 81]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "23167_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'wipe the table with the cloth', and now you are performing subtask 'slide the cloth on the table to wipe the surface.'\nYou start from [168, 86]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[168, 86], [167, 94], [221, 108], [194, 92], [221, 96], [193, 123], [159, 103], [154, 91], [166, 74], [154, 77]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/23167_exterior_image_1_left#70.jpg", + "gt": "[[168, 86], [167, 94], [221, 108], [194, 92], [221, 96], [193, 123], [159, 103], [154, 91], [166, 74], [154, 77]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "488_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the marker from the cup and place it on the table', and now you are performing subtask 'pick up the marker from the cup and place it on the table.'\nWith start location [128, 62], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[128, 62], [156, 85], [158, 95], [175, 99], [167, 112], [174, 122], [179, 113], [167, 90], [152, 101], [150, 120]]}" + } + ], + "images": "488_exterior_image_2_left#0", + "gt": "[[128, 62], [156, 85], [158, 95], [175, 99], [167, 112], [174, 122], [179, 113], [167, 90], [152, 101], [150, 120]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0058_user_0007_scene_0002_cfg_0005_105422061350#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press a row of two power strip buttons to turn off the power strips', and now you are performing subtask 'press the first button on the power socket.'\nStart at [276, 47]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[276, 47], [262, 42], [243, 48], [231, 78], [235, 94], [232, 103], [236, 106], [237, 98], [243, 102], [243, 102]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0058_user_0007_scene_0002_cfg_0005_105422061350#0.jpg", + "gt": "[[276, 47], [262, 42], [243, 48], [231, 78], [235, 94], [232, 103], [236, 106], [237, 98], [243, 102], [243, 102]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg3_task_0035_user_0010_scene_0001_cfg_0003_104122063550#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up a small block', and now you are performing subtask 'pick up a small block.'\nStarting at [277, 192], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[277, 192], [266, 200], [275, 217], [259, 210], [293, 221], [333, 287], [346, 279], [366, 289], [314, 318], [332, 318]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg3_task_0035_user_0010_scene_0001_cfg_0003_104122063550#0.jpg", + "gt": "[[277, 192], [266, 200], [275, 217], [259, 210], [293, 221], [333, 287], [346, 279], [366, 289], [314, 318], [332, 318]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "23502_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the orange cuboid on the stack', and now you are performing subtask 'put the orange cuboid on the stack.'\nYour starting position is [249, 2]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[249, 2], [232, 33], [231, 59], [214, 67], [198, 39], [164, 19], [123, 43], [125, 56], [148, 4], [134, 8]]}" + } + ], + "images": "23502_exterior_image_2_left#0", + "gt": "[[249, 2], [232, 33], [231, 59], [214, 67], [198, 39], [164, 19], [123, 43], [125, 56], [148, 4], [134, 8]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0066_user_0016_scene_0003_cfg_0004_038522062288#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'building blocks', and now you are performing subtask 'pick up the red block from the table, transfer the red block from the table to the block board, place the red block on the block board.'\nYou start from [103, 201]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[103, 201], [85, 227], [95, 238], [107, 188], [154, 174], [172, 179], [172, 190], [153, 174], [173, 175], [172, 217]]}" + } + ], + "images": "RH20T_cfg4_task_0066_user_0016_scene_0003_cfg_0004_038522062288#166", + "gt": "[[103, 201], [85, 227], [95, 238], [107, 188], [154, 174], [172, 179], [172, 190], [153, 174], [173, 175], [172, 217]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg3_task_0008_user_0016_scene_0005_cfg_0003_104122062823#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'grab the block and place it at the designated location', and now you are performing subtask 'pick up the block from the right side of the cardboard, transfer the block from the right side of the cardboard to the left side of the cardboard, place the block at the left side of the cardboard.'\nYou start from [391, 61]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[391, 61], [383, 87], [359, 78], [347, 81], [354, 86], [303, 101], [291, 93], [291, 72], [304, 64], [331, 65]]}" + } + ], + "images": "RH20T_cfg3_task_0008_user_0016_scene_0005_cfg_0003_104122062823#119", + "gt": "[[391, 61], [383, 87], [359, 78], [347, 81], [354, 86], [303, 101], [291, 93], [291, 72], [304, 64], [331, 65]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0096_user_0007_scene_0008_cfg_0005_105422061350#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take something out of a drawer', and now you are performing subtask 'pull the drawer handle to the outside of the table.'\nYour initial coordinate is [276, 47]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[276, 47], [247, 3], [238, 0], [259, 0], [240, 0], [259, 0], [261, 7], [240, 28], [234, 25], [222, 45]]}" + } + ], + "images": "RH20T_cfg5_task_0096_user_0007_scene_0008_cfg_0005_105422061350#0", + "gt": "[[276, 47], [247, 3], [238, 0], [259, 0], [240, 0], [259, 0], [261, 7], [240, 28], [234, 25], [222, 45]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0057_user_0007_scene_0002_cfg_0005_105422061350#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press a row of four power strip buttons to turn on the power strips', and now you are performing subtask 'press the third button on the power socket, press the fourth button on the power socket.'\nYour starting position is [287, 108]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[287, 108], [289, 110], [287, 113], [292, 109], [293, 102], [288, 99], [287, 100], [298, 92], [305, 75], [312, 68]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0057_user_0007_scene_0002_cfg_0005_105422061350#678.jpg", + "gt": "[[287, 108], [289, 110], [287, 113], [292, 109], [293, 102], [288, 99], [287, 100], [298, 92], [305, 75], [312, 68]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "49706_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the plush toy from the box into the drawer after opening the drawer, then close the drawer', and now you are performing subtask 'push the drawer to the open position.'\nBegin at [203, 92] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[203, 92], [211, 88], [216, 94], [210, 89], [209, 91], [210, 88], [202, 77], [191, 82], [189, 96], [215, 95]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/49706_exterior_image_1_left#201.jpg", + "gt": "[[203, 92], [211, 88], [216, 94], [210, 89], [209, 91], [210, 88], [202, 77], [191, 82], [189, 96], [215, 95]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg2_task_0018_user_0003_scene_0010_cfg_0002_037522062165#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'play jenga', and now you are performing subtask 'play jenga.'\nThe trajectory starts at [284, 174]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[284, 174], [207, 182], [180, 176], [169, 183], [174, 197], [182, 191], [204, 231], [231, 247], [207, 197], [207, 197]]}" + } + ], + "images": "RH20T_cfg2_task_0018_user_0003_scene_0010_cfg_0002_037522062165#0", + "gt": "[[284, 174], [207, 182], [180, 176], [169, 183], [174, 197], [182, 191], [204, 231], [231, 247], [207, 197], [207, 197]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "19783_exterior_image_2_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the button on the adaptor and push the switch on the electric kettle', and now you are performing subtask 'press the switch on the electric kettle.'\nYou start from [159, 112]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[159, 112], [158, 112], [160, 113], [160, 115], [162, 115], [162, 117], [159, 115], [156, 106], [151, 99], [152, 99]]}" + } + ], + "images": "19783_exterior_image_2_left#208", + "gt": "[[159, 112], [158, 112], [160, 113], [160, 115], [162, 115], [162, 117], [159, 115], [156, 106], [151, 99], [152, 99]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "69884_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the watermelon plush toy in the box', and now you are performing subtask 'put the watermelon plush toy in the box.'\nYou start from [235.0, 16.0]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[235.0, 16.0], [234.0, 32.0], [247.0, 78.0], [243.0, 89.0], [230.0, 85.0], [221.0, 71.0], [207.0, 58.0], [198.0, 56.0], [193.0, 60.0], [186.0, 46.0]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/69884_exterior_image_1_left#0.jpg", + "gt": "[[235.0, 16.0], [234.0, 32.0], [247.0, 78.0], [243.0, 89.0], [230.0, 85.0], [221.0, 71.0], [207.0, 58.0], [198.0, 56.0], [193.0, 60.0], [186.0, 46.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0013_user_0020_scene_0004_cfg_0007_037522061512#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'place the block on the scale', and now you are performing subtask 'place the block on the scale.'\nYou start from [261, 86]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[261, 86], [217, 153], [211, 180], [239, 130], [275, 108], [272, 102], [277, 112], [263, 87], [273, 97], [273, 97]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg7_task_0013_user_0020_scene_0004_cfg_0007_037522061512#0.jpg", + "gt": "[[261, 86], [217, 153], [211, 180], [239, 130], [275, 108], [272, 102], [277, 112], [263, 87], [273, 97], [273, 97]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg3_task_0057_user_0010_scene_0010_cfg_0003_104122062823#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn on the power strips', and now you are performing subtask 'press the first button on the power strip, press the first button on the power strip.'\nStarting at [344, 184], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[344, 184], [354, 189], [356, 195], [354, 193], [354, 196], [351, 199], [354, 201], [358, 201], [367, 188], [365, 169]]}" + } + ], + "images": "RH20T_cfg3_task_0057_user_0010_scene_0010_cfg_0003_104122062823#241", + "gt": "[[344, 184], [354, 189], [356, 195], [354, 193], [354, 196], [351, 199], [354, 201], [358, 201], [367, 188], [365, 169]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0037_user_0015_scene_0004_cfg_0001_819112070044#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'place the fourth block on top of the third block, pick up the fifth block on the table, transfer the fifth block from the table to above the fourth block, place the fifth block on top of the fourth block.'\nStart at [413, 162]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[413, 162], [368, 138], [321, 143], [299, 174], [271, 183], [264, 221], [406, 126], [422, 144], [382, 116], [348, 124]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0037_user_0015_scene_0004_cfg_0001_819112070044#710.jpg", + "gt": "[[413, 162], [368, 138], [321, 143], [299, 174], [271, 183], [264, 221], [406, 126], [422, 144], [382, 116], [348, 124]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "26228_exterior_image_2_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the drawer, place the orange cup inside the drawer, close the drawer', and now you are performing subtask 'place the orange cup in the drawer.'\nWith start location [161, 131], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[161, 131], [210, 91], [214, 103], [157, 119], [148, 142], [178, 129], [137, 132], [183, 150], [177, 130], [131, 139]]}" + } + ], + "images": "26228_exterior_image_2_left#260", + "gt": "[[161, 131], [210, 91], [214, 103], [157, 119], [148, 142], [178, 129], [137, 132], [183, 150], [177, 130], [131, 139]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "39570_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the bottle to the left', and now you are performing subtask 'move the bottle to the left.'\nYou begin at [247, 40]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[247, 40], [222, 31], [216, 38], [222, 61], [214, 64], [208, 28], [186, 22], [185, 39], [210, 89], [237, 47]]}" + } + ], + "images": "39570_exterior_image_1_left#0", + "gt": "[[247, 40], [222, 31], [216, 38], [222, 61], [214, 64], [208, 28], [186, 22], [185, 39], [210, 89], [237, 47]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "62801_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the lid on the black pot', and now you are performing subtask 'put the lid on the black pot.'\nStarting at [169.0, 81.5], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[169.0, 81.5], [164.0, 61.5], [151.0, 56.5], [154.0, 62.5], [127.0, 87.5], [116.0, 88.5], [119.0, 96.5], [115.0, 78.5], [126.0, 98.5], [126.0, 89.5]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/62801_exterior_image_1_left#0.jpg", + "gt": "[[169.0, 81.5], [164.0, 61.5], [151.0, 56.5], [154.0, 62.5], [127.0, 87.5], [116.0, 88.5], [119.0, 96.5], [115.0, 78.5], [126.0, 98.5], [126.0, 89.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "37843_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'use the blackboard eraser to wipe the whiteboard and place it on the table', and now you are performing subtask 'use the blackboard eraser to wipe the whiteboard and place it on the table.'\nStarting at [184.5, 38.5], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[184.5, 38.5], [216.5, 31.5], [243.5, 50.5], [273.5, 54.5], [197.5, 22.5], [188.5, 29.5], [204.5, 25.5], [153.5, 72.5], [164.5, 101.5], [156.5, 89.5]]}" + } + ], + "images": "37843_exterior_image_1_left#0", + "gt": "[[184.5, 38.5], [216.5, 31.5], [243.5, 50.5], [273.5, 54.5], [197.5, 22.5], [188.5, 29.5], [204.5, 25.5], [153.5, 72.5], [164.5, 101.5], [156.5, 89.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0037_user_0014_scene_0002_cfg_0007_037522061512#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'place the third block on the first block, pick up the fourth block from the tabletop, transfer the fourth block from the tabletop to the third block, place the fourth block on the third block.'\nBegin at [253, 127] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[253, 127], [239, 112], [219, 111], [204, 131], [203, 147], [209, 152], [214, 119], [223, 91], [233, 87], [245, 103]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg7_task_0037_user_0014_scene_0002_cfg_0007_037522061512#248.jpg", + "gt": "[[253, 127], [239, 112], [219, 111], [204, 131], [203, 147], [209, 152], [214, 119], [223, 91], [233, 87], [245, 103]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "30342_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the garlic on the counter into the glass bowl one by one', and now you are performing subtask 'place the third garlic into the glass bowl.'\nYour starting position is [209, 129]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[209, 129], [215, 123], [225, 123], [228, 137], [223, 140], [223, 131], [214, 128], [205, 144], [218, 124], [213, 125]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/30342_exterior_image_1_left#233.jpg", + "gt": "[[209, 129], [215, 123], [225, 123], [228, 137], [223, 140], [223, 131], [214, 128], [205, 144], [218, 124], [213, 125]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0070_user_0020_scene_0003_cfg_0006_104122061018#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open a sliding window', and now you are performing subtask 'slide the left window.'\nStart at [367, 28]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[367, 28], [323, 102], [305, 120], [308, 123], [300, 116], [303, 122], [297, 118], [294, 131], [276, 127], [296, 123]]}" + } + ], + "images": "RH20T_cfg6_task_0070_user_0020_scene_0003_cfg_0006_104122061018#0", + "gt": "[[367, 28], [323, 102], [305, 120], [308, 123], [300, 116], [303, 122], [297, 118], [294, 131], [276, 127], [296, 123]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "6070_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the white cup', and now you are performing subtask 'move the white cup.'\nYou begin at [207, 45]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[207, 45], [173, 42], [141, 64], [136, 76], [139, 101], [169, 96], [162, 96], [164, 88], [170, 92], [165, 67]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/6070_exterior_image_2_left#0.jpg", + "gt": "[[207, 45], [173, 42], [141, 64], [136, 76], [139, 101], [169, 96], [162, 96], [164, 88], [170, 92], [165, 67]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "27640_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'flip the second switch on the left side of the adaptor', and now you are performing subtask 'flip the second switch on the left side of the adaptor.'\nStart at [87, 80]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[87, 80], [137, 91], [149, 107], [148, 120], [154, 127], [157, 123], [155, 145], [146, 129], [157, 129], [156, 136]]}" + } + ], + "images": "27640_exterior_image_2_left#0", + "gt": "[[87, 80], [137, 91], [149, 107], [148, 120], [154, 127], [157, 123], [155, 145], [146, 129], [157, 129], [156, 136]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "76380_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unhang the blue object from the hanger', and now you are performing subtask 'unhang the blue object from the hanger.'\nFrom start point [145, 81], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[145, 81], [169, 60], [163, 66], [180, 95], [213, 99], [221, 107], [181, 127], [197, 118], [187, 107], [188, 85]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/76380_exterior_image_2_left#0.jpg", + "gt": "[[145, 81], [169, 60], [163, 66], [180, 95], [213, 99], [221, 107], [181, 127], [197, 118], [187, 107], [188, 85]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0085_user_0015_scene_0002_cfg_0001_035622060973#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the bubble ring from the assembled bubble ring and ball', and now you are performing subtask 'remove the bubble ring from the assembled bubble ring and ball.'\nStart at [246, 130]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[246, 130], [241, 159], [220, 176], [227, 210], [217, 164], [210, 148], [205, 154], [220, 153], [202, 147], [195, 130]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0085_user_0015_scene_0002_cfg_0001_035622060973#0.jpg", + "gt": "[[246, 130], [241, 159], [220, 176], [227, 210], [217, 164], [210, 148], [205, 154], [220, 153], [202, 147], [195, 130]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "49058_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the yellow towel to the left', and now you are performing subtask 'move the yellow towel to the left.'\nStart at [217, 0]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[217, 0], [220, 17], [220, 65], [213, 79], [153, 94], [139, 72], [132, 45], [134, 39], [129, 46], [133, 42]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/49058_exterior_image_2_left#0.jpg", + "gt": "[[217, 0], [220, 17], [220, 65], [213, 79], [153, 94], [139, 72], [132, 45], [134, 39], [129, 46], [133, 42]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0028_user_0020_scene_0003_cfg_0007_104122061018#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'grasp the handle and close the drawer', and now you are performing subtask 'grasp the handle and close the drawer.'\nYou begin at [363, 31]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[363, 31], [364, 45], [293, 171], [290, 195], [374, 246], [358, 228], [344, 191], [352, 176], [367, 175], [350, 66]]}" + } + ], + "images": "RH20T_cfg7_task_0028_user_0020_scene_0003_cfg_0007_104122061018#0", + "gt": "[[363, 31], [364, 45], [293, 171], [290, 195], [374, 246], [358, 228], [344, 191], [352, 176], [367, 175], [350, 66]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg3_task_0003_user_0016_scene_0003_cfg_0003_036422060909#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the three buttons in sequence', and now you are performing subtask 'press the gray base red button.'\nStarting at [336, 88], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[336, 88], [259, 84], [295, 69], [344, 78], [359, 97], [405, 71], [424, 96], [412, 84], [417, 92], [396, 104]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg3_task_0003_user_0016_scene_0003_cfg_0003_036422060909#0.jpg", + "gt": "[[336, 88], [259, 84], [295, 69], [344, 78], [359, 97], [405, 71], [424, 96], [412, 84], [417, 92], [396, 104]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "47434_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the purple object in the bowl', and now you are performing subtask 'put the purple object in the bowl.'\nYour starting position is [128, 0]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[128, 0], [212, 77], [169, 69], [200, 78], [196, 94], [184, 91], [194, 111], [180, 116], [149, 64], [149, 64]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/47434_exterior_image_1_left#0.jpg", + "gt": "[[128, 0], [212, 77], [169, 69], [200, 78], [196, 94], [184, 91], [194, 111], [180, 116], [149, 64], [149, 64]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0016_user_0014_scene_0001_cfg_0001_750612070851#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'hit the pool ball', and now you are performing subtask 'hit the pool ball.'\nWith start location [317, 154], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[317, 154], [347, 174], [360, 174], [365, 160], [401, 158], [518, 187], [549, 218], [549, 264], [552, 237], [490, 234]]}" + } + ], + "images": "RH20T_cfg1_task_0016_user_0014_scene_0001_cfg_0001_750612070851#0", + "gt": "[[317, 154], [347, 174], [360, 174], [365, 160], [401, 158], [518, 187], [549, 218], [549, 264], [552, 237], [490, 234]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0070_user_0015_scene_0002_cfg_0001_038522062547#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open a sliding window', and now you are performing subtask 'pull the sliding window to the left to open the window.'\nThe trajectory starts at [405, 132]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[405, 132], [415, 163], [445, 189], [446, 203], [437, 156], [428, 151], [434, 137], [430, 130], [437, 118], [427, 143]]}" + } + ], + "images": "RH20T_cfg1_task_0070_user_0015_scene_0002_cfg_0001_038522062547#0", + "gt": "[[405, 132], [415, 163], [445, 189], [446, 203], [437, 156], [428, 151], [434, 137], [430, 130], [437, 118], [427, 143]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0001_user_0007_scene_0008_cfg_0005_037522062165#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the button from top to bottom', and now you are performing subtask 'press the button from top to bottom.'\nStart at [298, 155]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[298, 155], [294, 177], [268, 200], [186, 179], [199, 176], [209, 163], [209, 191], [202, 204], [215, 173], [239, 169]]}" + } + ], + "images": "RH20T_cfg5_task_0001_user_0007_scene_0008_cfg_0005_037522062165#0", + "gt": "[[298, 155], [294, 177], [268, 200], [186, 179], [199, 176], [209, 163], [209, 191], [202, 204], [215, 173], [239, 169]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0029_user_0020_scene_0002_cfg_0007_104122063633#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'grasp the handle and open the drawer', and now you are performing subtask 'grasp the handle and open the drawer.'\nYou start from [234, 121]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[234, 121], [219, 127], [219, 135], [193, 139], [181, 152], [169, 194], [160, 156], [167, 97], [178, 87], [191, 94]]}" + } + ], + "images": "RH20T_cfg7_task_0029_user_0020_scene_0002_cfg_0007_104122063633#0", + "gt": "[[234, 121], [219, 127], [219, 135], [193, 139], [181, 152], [169, 194], [160, 156], [167, 97], [178, 87], [191, 94]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0096_user_0007_scene_0008_cfg_0005_104122063678#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take something out of a drawer', and now you are performing subtask 'pull the drawer handle to the outside of the table.'\nWith start location [323, 132], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[323, 132], [336, 120], [379, 129], [398, 196], [394, 170], [412, 210], [384, 254], [377, 193], [386, 176], [399, 197]]}" + } + ], + "images": "RH20T_cfg5_task_0096_user_0007_scene_0008_cfg_0005_104122063678#0", + "gt": "[[323, 132], [336, 120], [379, 129], [398, 196], [394, 170], [412, 210], [384, 254], [377, 193], [386, 176], [399, 197]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "26514_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'fold the towel in half then fold it in half again', and now you are performing subtask 'adjust the towel and place it on the tabletop.'\nYou begin at [153, 103]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[153, 103], [149, 109], [156, 108], [174, 99], [172, 94], [154, 95], [148, 98], [149, 88], [153, 87], [158, 91]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/26514_exterior_image_1_left#313.jpg", + "gt": "[[153, 103], [149, 109], [156, 108], [174, 99], [172, 94], [154, 95], [148, 98], [149, 88], [153, 87], [158, 91]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "10958_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the green doll in the pot', and now you are performing subtask 'put the green doll in the pot.'\nFrom start point [238, 0], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[238, 0], [215, 14], [170, 80], [152, 85], [152, 96], [164, 77], [223, 88], [196, 93], [206, 105], [198, 92]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/10958_exterior_image_2_left#0.jpg", + "gt": "[[238, 0], [215, 14], [170, 80], [152, 85], [152, 96], [164, 77], [223, 88], [196, 93], [206, 105], [198, 92]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "87825_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the red marker from the yellow mug, place the marker back in the mug, take the marker out of the mug', and now you are performing subtask 'place the marker in the yellow mug.'\nYou begin at [175, 77]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[175, 77], [159, 94], [153, 73], [153, 42], [159, 37], [154, 53], [146, 55], [140, 46], [145, 40], [152, 48]]}" + } + ], + "images": "87825_exterior_image_1_left#137", + "gt": "[[175, 77], [159, 94], [153, 73], [153, 42], [159, 37], [154, 53], [146, 55], [140, 46], [145, 40], [152, 48]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "58247_exterior_image_1_left#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the microwave door, place the bowl inside the microwave', and now you are performing subtask 'pull the microwave door.'\nWith start location [170, 108], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[170, 108], [159, 104], [170, 119], [156, 112], [167, 113], [161, 125], [148, 107], [140, 59], [144, 38], [150, 39]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/58247_exterior_image_1_left#298.jpg", + "gt": "[[170, 108], [159, 104], [170, 119], [156, 112], [167, 113], [161, 125], [148, 107], [140, 59], [144, 38], [150, 39]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "81663_exterior_image_2_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the cup and put it on top of the table, then pick up the cloth and put it in the bowl and close the drawer', and now you are performing subtask 'push the handle of the drawer to close the drawer.'\nStart at [167, 117]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[167, 117], [160, 118], [164, 115], [164, 118], [166, 114], [165, 118], [142, 140], [142, 148], [142, 131], [139, 125]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/81663_exterior_image_2_left#277.jpg", + "gt": "[[167, 117], [160, 118], [164, 115], [164, 118], [166, 114], [165, 118], [142, 140], [142, 148], [142, 131], [139, 125]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0075_user_0007_scene_0001_cfg_0005_104122063678#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'place the black chess pieces on the chessboard', and now you are performing subtask 'pick up the white piece on the table, transfer the white piece from the table to the chessboard.'\nYou start from [376, 152]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[376, 152], [387, 154], [418, 186], [418, 191], [396, 239], [394, 265], [389, 270], [380, 223], [375, 217], [364, 229]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0075_user_0007_scene_0001_cfg_0005_104122063678#753.jpg", + "gt": "[[376, 152], [387, 154], [418, 186], [418, 191], [396, 239], [394, 265], [389, 270], [380, 223], [375, 217], [364, 229]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0081_user_0015_scene_0002_cfg_0004_104422070011#TrajectoryPrediction_Task#10", + "task": "TrajectoryPrediction_Task", + "p_index": 10, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the leg of the glasses (with one hand)', and now you are performing subtask 'pick up the glasses on the table.'\nYour starting position is [287, 159]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[287, 159], [291, 154], [292, 166], [284, 166], [296, 167], [304, 185], [279, 186], [263, 175], [295, 173], [275, 170]]}" + } + ], + "images": "RH20T_cfg4_task_0081_user_0015_scene_0002_cfg_0004_104422070011#325", + "gt": "[[287, 159], [291, 154], [292, 166], [284, 166], [296, 167], [304, 185], [279, 186], [263, 175], [295, 173], [275, 170]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "83759_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the marker from the mug cup and place it on the table', and now you are performing subtask 'remove the marker from the mug cup and place it on the table.'\nYour initial coordinate is [117.0, 18.5]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[117.0, 18.5], [137.0, 33.5], [158.0, 68.5], [170.0, 76.5], [164.0, 84.5], [163.0, 55.5], [168.0, 46.5], [179.0, 45.5], [211.0, 103.5], [204.0, 61.5]]}" + } + ], + "images": "83759_exterior_image_1_left#0", + "gt": "[[117.0, 18.5], [137.0, 33.5], [158.0, 68.5], [170.0, 76.5], [164.0, 84.5], [163.0, 55.5], [168.0, 46.5], [179.0, 45.5], [211.0, 103.5], [204.0, 61.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "45999_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick the purple ball and put it in the bowl', and now you are performing subtask 'pick the purple ball and put it in the bowl.'\nStart at [201, 107]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[201, 107], [195, 105], [185, 115], [191, 166], [202, 180], [214, 159], [212, 130], [201, 102], [192, 113], [208, 107]]}" + } + ], + "images": "45999_exterior_image_1_left#0", + "gt": "[[201, 107], [195, 105], [185, 115], [191, 166], [202, 180], [214, 159], [212, 130], [201, 102], [192, 113], [208, 107]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0010_user_0010_scene_0002_cfg_0005_104122063678#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'place the handset of the telephone on the corresponding phone cradle', and now you are performing subtask 'place the handset of the telephone on the corresponding phone cradle.'\nYou begin at [323, 132]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[323, 132], [338, 173], [324, 186], [317, 234], [287, 263], [293, 286], [273, 236], [295, 213], [256, 186], [284, 173]]}" + } + ], + "images": "RH20T_cfg5_task_0010_user_0010_scene_0002_cfg_0005_104122063678#0", + "gt": "[[323, 132], [338, 173], [324, 186], [317, 234], [287, 263], [293, 286], [273, 236], [295, 213], [256, 186], [284, 173]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "81550_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the mug from the coffee maker and put it on the counter, and pour the content from the transparent cup into the mug', and now you are performing subtask 'pick up the transparent cup from the countertop.'\nYou begin at [235, 96]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[235, 96], [206, 104], [210, 133], [194, 145], [173, 148], [170, 156], [188, 135], [171, 114], [177, 101], [170, 108]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/81550_exterior_image_1_left#0.jpg", + "gt": "[[235, 96], [206, 104], [210, 133], [194, 145], [173, 148], [170, 156], [188, 135], [171, 114], [177, 101], [170, 108]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "15964_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the purple object from the black plate and put it in the black pot', and now you are performing subtask 'take the purple object from the black plate and put it in the black pot.'\nYou begin at [209, 100]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[209, 100], [220, 151], [216, 162], [223, 166], [196, 143], [163, 127], [168, 123], [165, 129], [167, 123], [198, 134]]}" + } + ], + "images": "15964_exterior_image_1_left#0", + "gt": "[[209, 100], [220, 151], [216, 162], [223, 166], [196, 143], [163, 127], [168, 123], [165, 129], [167, 123], [198, 134]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0036_user_0014_scene_0005_cfg_0007_104122061330#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'shake the test tube', and now you are performing subtask 'pick up the second test tube on the left.'\nStart at [266, 103]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[266, 103], [267, 113], [308, 106], [322, 138], [316, 134], [310, 139], [323, 127], [327, 132], [320, 151], [303, 89]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg7_task_0036_user_0014_scene_0005_cfg_0007_104122061330#0.jpg", + "gt": "[[266, 103], [267, 113], [308, 106], [322, 138], [316, 134], [310, 139], [323, 127], [327, 132], [320, 151], [303, 89]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0089_user_0014_scene_0001_cfg_0004_104122062823#TrajectoryPrediction_Task#8", + "task": "TrajectoryPrediction_Task", + "p_index": 8, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'push an object with obstacles', and now you are performing subtask 'push the block upward, push the block to the left.'\nFrom start point [451, 93], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[451, 93], [460, 92], [476, 85], [465, 94], [458, 94], [435, 79], [380, 70], [379, 67], [382, 64], [405, 52]]}" + } + ], + "images": "RH20T_cfg4_task_0089_user_0014_scene_0001_cfg_0004_104122062823#287", + "gt": "[[451, 93], [460, 92], [476, 85], [465, 94], [458, 94], [435, 79], [380, 70], [379, 67], [382, 64], [405, 52]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "61367_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'push the faucet to the right', and now you are performing subtask 'push the faucet to the right.'\nYou begin at [246, 96]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[246, 96], [198, 102], [162, 101], [143, 96], [151, 101], [156, 97], [164, 99], [182, 88], [192, 73], [189, 68]]}" + } + ], + "images": "61367_exterior_image_1_left#0", + "gt": "[[246, 96], [198, 102], [162, 101], [143, 96], [151, 101], [156, 97], [164, 99], [182, 88], [192, 73], [189, 68]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "45952_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the bottle with a green lid out of the sink and place it on the counter', and now you are performing subtask 'take the bottle with a green lid out of the sink and place it on the counter.'\nYou begin at [88.5, 51.5]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[88.5, 51.5], [126.5, 56.5], [158.5, 83.5], [156.5, 49.5], [166.5, 39.5], [187.5, 69.5], [213.5, 60.5], [227.5, 75.5], [202.5, 23.5], [149.5, 38.5]]}" + } + ], + "images": "45952_exterior_image_1_left#0", + "gt": "[[88.5, 51.5], [126.5, 56.5], [158.5, 83.5], [156.5, 49.5], [166.5, 39.5], [187.5, 69.5], [213.5, 60.5], [227.5, 75.5], [202.5, 23.5], [149.5, 38.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "77845_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the tape on the plate', and now you are performing subtask 'put the tape on the plate.'\nBegin at [1.5, 56.0] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[1.5, 56.0], [123.5, 84.0], [156.5, 103.0], [159.5, 128.0], [163.5, 116.0], [152.5, 87.0], [142.5, 79.0], [142.5, 89.0], [133.5, 89.0], [133.5, 89.0]]}" + } + ], + "images": "77845_exterior_image_1_left#0", + "gt": "[[1.5, 56.0], [123.5, 84.0], [156.5, 103.0], [159.5, 128.0], [163.5, 116.0], [152.5, 87.0], [142.5, 79.0], [142.5, 89.0], [133.5, 89.0], [133.5, 89.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "31362_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'fold the towel twice', and now you are performing subtask 'fold the towel again.'\nThe trajectory starts at [141, 104]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[141, 104], [146, 114], [137, 130], [136, 96], [142, 78], [156, 72], [173, 78], [141, 67], [138, 63], [145, 65]]}" + } + ], + "images": "31362_exterior_image_1_left#139", + "gt": "[[141, 104], [146, 114], [137, 130], [136, 96], [142, 78], [156, 72], [173, 78], [141, 67], [138, 63], [145, 65]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "34215_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the small white bottle, keep it upright and move it to the right', and now you are performing subtask 'place the small white bottle upright on the table.'\nYour starting position is [232.5, 61.5]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[232.5, 61.5], [210.5, 100.5], [185.5, 103.5], [160.5, 115.5], [162.5, 123.5], [166.5, 108.5], [158.5, 107.5], [164.5, 101.5], [168.5, 134.5], [179.5, 128.5]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/34215_exterior_image_1_left#0.jpg", + "gt": "[[232.5, 61.5], [210.5, 100.5], [185.5, 103.5], [160.5, 115.5], [162.5, 123.5], [166.5, 108.5], [158.5, 107.5], [164.5, 101.5], [168.5, 134.5], [179.5, 128.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0047_user_0014_scene_0002_cfg_0006_104122064161#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the cup off the cup rack', and now you are performing subtask 'take the cup off the cup rack.'\nYour initial coordinate is [338, 110]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[338, 110], [351, 83], [374, 76], [403, 105], [411, 171], [374, 280], [399, 202], [384, 175], [366, 207], [362, 181]]}" + } + ], + "images": "RH20T_cfg6_task_0047_user_0014_scene_0002_cfg_0006_104122064161#0", + "gt": "[[338, 110], [351, 83], [374, 76], [403, 105], [411, 171], [374, 280], [399, 202], [384, 175], [366, 207], [362, 181]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "6997_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the peach plush toy in the box and remove the green plush from the box and put it on the tray', and now you are performing subtask 'push box to side of table.'\nStarting at [188, 114], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[188, 114], [198, 117], [200, 107], [200, 116], [223, 127], [226, 139], [209, 124], [236, 130], [235, 119], [223, 112]]}" + } + ], + "images": "6997_exterior_image_1_left#144", + "gt": "[[188, 114], [198, 117], [200, 107], [200, 116], [223, 127], [226, 139], [209, 124], [236, 130], [235, 119], [223, 112]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0094_user_0007_scene_0009_cfg_0004_104122062823#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open a box', and now you are performing subtask 'push the box to open the box, push the box to open the box.'\nYou start from [267, 41]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[267, 41], [287, 0], [298, 0], [286, 0], [290, 25], [298, 0], [331, 9], [335, 0], [321, 0], [342, 0]]}" + } + ], + "images": "RH20T_cfg4_task_0094_user_0007_scene_0009_cfg_0004_104122062823#253", + "gt": "[[267, 41], [287, 0], [298, 0], [286, 0], [290, 25], [298, 0], [331, 9], [335, 0], [321, 0], [342, 0]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0034_user_0020_scene_0001_cfg_0006_104122063633#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the squares into a pyramid shape', and now you are performing subtask 'place the second square below the first square, pick up the third square on the bottom, transfer the third square from the bottom to above the square, place the third square above the square.'\nYou begin at [228, 125]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[228, 125], [237, 118], [229, 83], [237, 100], [214, 119], [216, 144], [216, 124], [207, 133], [205, 166], [220, 182]]}" + } + ], + "images": "RH20T_cfg6_task_0034_user_0020_scene_0001_cfg_0006_104122063633#1014", + "gt": "[[228, 125], [237, 118], [229, 83], [237, 100], [214, 119], [216, 144], [216, 124], [207, 133], [205, 166], [220, 182]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0038_user_0020_scene_0001_cfg_0006_104122064161#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the cup', and now you are performing subtask 'pick up the cup.'\nStart at [338, 110]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[338, 110], [359, 100], [360, 80], [363, 92], [384, 93], [390, 136], [378, 136], [385, 142], [379, 151], [382, 111]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg6_task_0038_user_0020_scene_0001_cfg_0006_104122064161#0.jpg", + "gt": "[[338, 110], [359, 100], [360, 80], [363, 92], [384, 93], [390, 136], [378, 136], [385, 142], [379, 151], [382, 111]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "27294_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the yellow pen in the glass bowl', and now you are performing subtask 'put the yellow pen in the glass bowl.'\nYour initial coordinate is [196, 4]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[196, 4], [208, 36], [215, 71], [209, 122], [198, 112], [172, 99], [164, 102], [167, 109], [167, 91], [167, 91]]}" + } + ], + "images": "27294_exterior_image_2_left#0", + "gt": "[[196, 4], [208, 36], [215, 71], [209, 122], [198, 112], [172, 99], [164, 102], [167, 109], [167, 91], [167, 91]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "15487_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the pen out of the mug and put it on the table', and now you are performing subtask 'take the pen out of the mug and put it on the table.'\nYour starting position is [160, 8]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[160, 8], [159, 63], [181, 97], [192, 72], [172, 83], [175, 93], [194, 75], [174, 117], [164, 105], [175, 78]]}" + } + ], + "images": "15487_exterior_image_2_left#0", + "gt": "[[160, 8], [159, 63], [181, 97], [192, 72], [172, 83], [175, 93], [194, 75], [174, 117], [164, 105], [175, 78]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "11614_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the big orange plush toy out of the box and put it on the tray', and now you are performing subtask 'take the big orange plush toy out of the box and put it on the tray.'\nYou begin at [155, 37]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[155, 37], [171, 67], [188, 80], [188, 92], [172, 99], [179, 99], [173, 60], [146, 49], [136, 56], [136, 56]]}" + } + ], + "images": "11614_exterior_image_2_left#0", + "gt": "[[155, 37], [171, 67], [188, 80], [188, 92], [172, 99], [179, 99], [173, 60], [146, 49], [136, 56], [136, 56]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "88538_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'folding the towel', and now you are performing subtask 'fold the towel on the desk.'\nStart at [121, 36]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[121, 36], [174, 33], [199, 90], [191, 121], [196, 132], [188, 131], [194, 136], [187, 94], [166, 87], [132, 94]]}" + } + ], + "images": "88538_exterior_image_1_left#0", + "gt": "[[121, 36], [174, 33], [199, 90], [191, 121], [196, 132], [188, 131], [194, 136], [187, 94], [166, 87], [132, 94]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0034_user_0014_scene_0004_cfg_0001_038522062547#TrajectoryPrediction_Task#8", + "task": "TrajectoryPrediction_Task", + "p_index": 8, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the squares into a pyramid shape', and now you are performing subtask 'pick up the fifth square from the right side of the table, transfer the fifth square from the right side of the table to the top of the second square, place the fifth square on top of the second square, pick up the sixth square on the table.'\nFrom start point [428, 159], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[428, 159], [453, 157], [459, 166], [457, 158], [419, 159], [394, 168], [395, 175], [383, 169], [399, 157], [451, 148]]}" + } + ], + "images": "RH20T_cfg1_task_0034_user_0014_scene_0004_cfg_0001_038522062547#736", + "gt": "[[428, 159], [453, 157], [459, 166], [457, 158], [419, 159], [394, 168], [395, 175], [383, 169], [399, 157], [451, 148]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0023_user_0010_scene_0007_cfg_0005_036422060215#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn on the power strip by pressing the button', and now you are performing subtask 'turn on the power strip by pressing the button.'\nYou start from [286, 108]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[286, 108], [297, 155], [274, 161], [245, 186], [243, 198], [240, 191], [256, 222], [257, 142], [275, 118], [299, 113]]}" + } + ], + "images": "RH20T_cfg5_task_0023_user_0010_scene_0007_cfg_0005_036422060215#0", + "gt": "[[286, 108], [297, 155], [274, 161], [245, 186], [243, 198], [240, 191], [256, 222], [257, 142], [275, 118], [299, 113]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "265_exterior_image_2_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the bowl to the right and put the rubik's cube inside it', and now you are performing subtask 'place the rubik's cube in the bowl.'\nFrom start point [162, 88], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[162, 88], [136, 79], [138, 89], [131, 104], [137, 89], [147, 83], [157, 89], [164, 87], [167, 99], [176, 65]]}" + } + ], + "images": "265_exterior_image_2_left#372", + "gt": "[[162, 88], [136, 79], [138, 89], [131, 104], [137, 89], [147, 83], [157, 89], [164, 87], [167, 99], [176, 65]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0101_user_0007_scene_0007_cfg_0005_037522062165#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'clean the table with a cloth', and now you are performing subtask 'clean the table with a cloth.'\nStarting at [289, 152], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[289, 152], [315, 182], [348, 290], [341, 320], [331, 304], [229, 258], [298, 282], [292, 312], [267, 276], [274, 226]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0101_user_0007_scene_0007_cfg_0005_037522062165#0.jpg", + "gt": "[[289, 152], [315, 182], [348, 290], [341, 320], [331, 304], [229, 258], [298, 282], [292, 312], [267, 276], [274, 226]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0042_user_0014_scene_0004_cfg_0006_104122064161#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'screw the lid onto the jar (needs to be twisted)', and now you are performing subtask 'screw the lid onto the jar (needs to be twisted).'\nBegin at [338, 110] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[338, 110], [354, 159], [348, 171], [355, 168], [344, 173], [343, 196], [326, 197], [341, 188], [325, 199], [348, 124]]}" + } + ], + "images": "RH20T_cfg6_task_0042_user_0014_scene_0004_cfg_0006_104122064161#0", + "gt": "[[338, 110], [354, 159], [348, 171], [355, 168], [344, 173], [343, 196], [326, 197], [341, 188], [325, 199], [348, 124]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0025_user_0020_scene_0008_cfg_0007_037522061512#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold a piece of paper that has been folded once (one end is pressed down by a weight)', and now you are performing subtask 'pull the paper on the table.'\nYou start from [261, 86]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[261, 86], [254, 111], [258, 129], [242, 142], [245, 153], [228, 147], [205, 175], [208, 185], [224, 176], [223, 189]]}" + } + ], + "images": "RH20T_cfg7_task_0025_user_0020_scene_0008_cfg_0007_037522061512#0", + "gt": "[[261, 86], [254, 111], [258, 129], [242, 142], [245, 153], [228, 147], [205, 175], [208, 185], [224, 176], [223, 189]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "19783_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the button on the adaptor and push the switch on the electric kettle', and now you are performing subtask 'press the switch on the electric kettle.'\nYou start from [173, 109]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[173, 109], [173, 110], [176, 111], [176, 113], [175, 110], [176, 96], [178, 93], [181, 93], [180, 93], [180, 94]]}" + } + ], + "images": "19783_exterior_image_1_left#220", + "gt": "[[173, 109], [173, 110], [176, 111], [176, 113], [175, 110], [176, 96], [178, 93], [181, 93], [180, 93], [180, 94]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0083_user_0015_scene_0004_cfg_0004_104122063550#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'swat with a flyswatter', and now you are performing subtask 'pick up the flyswatter from the surface.'\nFrom start point [279, 186], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[279, 186], [326, 179], [336, 171], [325, 172], [329, 183], [299, 194], [301, 200], [324, 174], [356, 201], [367, 203]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg4_task_0083_user_0015_scene_0004_cfg_0004_104122063550#0.jpg", + "gt": "[[279, 186], [326, 179], [336, 171], [325, 172], [329, 183], [299, 194], [301, 200], [324, 174], [356, 201], [367, 203]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "81736_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close the middle drawer doors', and now you are performing subtask 'push the handle of the right-side middle cabinet door to fully close the cabinet door.'\nYour initial coordinate is [144, 67]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[144, 67], [140, 68], [123, 57], [130, 62], [157, 72], [163, 72], [154, 70], [163, 64], [154, 63], [145, 56]]}" + } + ], + "images": "81736_exterior_image_1_left#137", + "gt": "[[144, 67], [140, 68], [123, 57], [130, 62], [157, 72], [163, 72], [154, 70], [163, 64], [154, 63], [145, 56]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "18559_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the lid on the table', and now you are performing subtask 'pick up the lid from the bowl.'\nStart at [104.0, 132.0]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[104.0, 132.0], [106.0, 133.0], [105.0, 134.0], [94.0, 138.0], [96.0, 138.0], [98.0, 135.0], [106.0, 130.0], [108.0, 130.0], [108.0, 129.0], [108.0, 130.0]]}" + } + ], + "images": "18559_exterior_image_1_left#109", + "gt": "[[104.0, 132.0], [106.0, 133.0], [105.0, 134.0], [94.0, 138.0], [96.0, 138.0], [98.0, 135.0], [106.0, 130.0], [108.0, 130.0], [108.0, 129.0], [108.0, 130.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "34753_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the box from the table and move it to the right', and now you are performing subtask 'pick up the box from the table and move it to the right.'\nYour starting position is [192, 62]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[192, 62], [128, 68], [72, 133], [115, 95], [153, 93], [149, 76], [136, 93], [147, 103], [154, 60], [154, 60]]}" + } + ], + "images": "34753_exterior_image_1_left#0", + "gt": "[[192, 62], [128, 68], [72, 133], [115, 95], [153, 93], [149, 76], [136, 93], [147, 103], [154, 60], [154, 60]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "28265_exterior_image_2_left#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the cloth on the table', and now you are performing subtask 'push the cloth to the middle of the table.'\nStarting at [119, 143], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[119, 143], [154, 160], [168, 160], [165, 161], [166, 158], [155, 153], [145, 157], [132, 154], [119, 130], [127, 126]]}" + } + ], + "images": "28265_exterior_image_2_left#381", + "gt": "[[119, 143], [154, 160], [168, 160], [165, 161], [166, 158], [155, 153], [145, 157], [132, 154], [119, 130], [127, 126]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "74482_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the lid on the transparent container and press the top', and now you are performing subtask 'put the lid on the transparent container and press the top.'\nStart at [130, 54]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[130, 54], [161, 50], [145, 61], [138, 98], [130, 91], [156, 75], [161, 104], [168, 85], [154, 68], [154, 68]]}" + } + ], + "images": "74482_exterior_image_2_left#0", + "gt": "[[130, 54], [161, 50], [145, 61], [138, 98], [130, 91], [156, 75], [161, 104], [168, 85], [154, 68], [154, 68]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0037_user_0014_scene_0001_cfg_0001_039422060546#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'place the first block on top of the second block, pick up the third block from the table, transfer the third block from the table to the position above the fourth block, place the third block on top of the second block.'\nThe trajectory starts at [304, 95]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[304, 95], [287, 169], [276, 171], [290, 192], [284, 174], [297, 93], [290, 52], [295, 39], [307, 38], [304, 78]]}" + } + ], + "images": "RH20T_cfg1_task_0037_user_0014_scene_0001_cfg_0001_039422060546#206", + "gt": "[[304, 95], [287, 169], [276, 171], [290, 192], [284, 174], [297, 93], [290, 52], [295, 39], [307, 38], [304, 78]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0015_user_0001_scene_0007_cfg_0001_819112070044#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'play the drum', and now you are performing subtask 'play the drum.'\nStart at [388, 108]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[388, 108], [325, 101], [315, 114], [322, 121], [323, 111], [362, 98], [393, 115], [392, 132], [363, 99], [355, 111]]}" + } + ], + "images": "RH20T_cfg1_task_0015_user_0001_scene_0007_cfg_0001_819112070044#0", + "gt": "[[388, 108], [325, 101], [315, 114], [322, 121], [323, 111], [362, 98], [393, 115], [392, 132], [363, 99], [355, 111]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "87645_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the pineapple plush toy out of the blue pot and put it on the counter', and now you are performing subtask 'take the pineapple plush toy out of the blue pot and put it on the counter.'\nWith start location [186, 74], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[186, 74], [210, 72], [225, 82], [233, 82], [233, 63], [225, 61], [214, 65], [203, 62], [207, 70], [214, 68]]}" + } + ], + "images": "87645_exterior_image_2_left#0", + "gt": "[[186, 74], [210, 72], [225, 82], [233, 82], [233, 63], [225, 61], [214, 65], [203, 62], [207, 70], [214, 68]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "31298_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'straighten out the towel', and now you are performing subtask 'straighten out the towel.'\nBegin at [101, 34] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[101, 34], [168, 129], [167, 118], [150, 111], [155, 61], [146, 42], [132, 60], [119, 61], [137, 59], [127, 68]]}" + } + ], + "images": "31298_exterior_image_1_left#0", + "gt": "[[101, 34], [168, 129], [167, 118], [150, 111], [155, 61], [146, 42], [132, 60], [119, 61], [137, 59], [127, 68]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "59697_exterior_image_2_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the objects from the orange bowl to the black pot, then cover the black pot with the glass lid', and now you are performing subtask 'pick up the glass lid from the table.'\nYou begin at [227, 84]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[227, 84], [226, 57], [201, 73], [194, 81], [199, 99], [221, 68], [259, 56], [264, 59], [270, 79], [266, 88]]}" + } + ], + "images": "59697_exterior_image_2_left#265", + "gt": "[[227, 84], [226, 57], [201, 73], [194, 81], [199, 99], [221, 68], [259, 56], [264, 59], [270, 79], [266, 88]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0016_user_0020_scene_0004_cfg_0007_104122064161#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'hit the pool ball', and now you are performing subtask 'hit the pool ball.'\nBegin at [337, 115] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[337, 115], [348, 139], [368, 136], [372, 150], [372, 133], [399, 114], [414, 126], [406, 149], [396, 101], [383, 100]]}" + } + ], + "images": "RH20T_cfg7_task_0016_user_0020_scene_0004_cfg_0007_104122064161#0", + "gt": "[[337, 115], [348, 139], [368, 136], [372, 150], [372, 133], [399, 114], [414, 126], [406, 149], [396, 101], [383, 100]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "54262_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the cloth and use it to wipe the frying pan', and now you are performing subtask 'pick up the cloth and use it to wipe the frying pan.'\nThe trajectory starts at [111.0, 6.5]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[111.0, 6.5], [118.0, 64.5], [105.0, 69.5], [131.0, 41.5], [140.0, 57.5], [126.0, 87.5], [160.0, 93.5], [147.0, 57.5], [110.0, 65.5], [82.0, 26.5]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/54262_exterior_image_1_left#0.jpg", + "gt": "[[111.0, 6.5], [118.0, 64.5], [105.0, 69.5], [131.0, 41.5], [140.0, 57.5], [126.0, 87.5], [160.0, 93.5], [147.0, 57.5], [110.0, 65.5], [82.0, 26.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "55408_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the glass lid on the black pot', and now you are performing subtask 'put the glass lid on the black pot.'\nBegin at [0, 6] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[0, 6], [37, 30], [84, 71], [108, 87], [114, 97], [102, 91], [94, 84], [103, 84], [120, 96], [134, 100]]}" + } + ], + "images": "55408_exterior_image_1_left#0", + "gt": "[[0, 6], [37, 30], [84, 71], [108, 87], [114, 97], [102, 91], [94, 84], [103, 84], [120, 96], [134, 100]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0004_user_0001_scene_0005_cfg_0001_819112070044#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the small block on the right side of the desk and move it to the left side of the desk', and now you are performing subtask 'pick up the small block on the right side of the desk and move it to the left side of the desk.'\nStarting at [389, 108], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[389, 108], [385, 129], [396, 137], [454, 140], [435, 157], [404, 143], [297, 162], [285, 166], [287, 181], [287, 161]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0004_user_0001_scene_0005_cfg_0001_819112070044#0.jpg", + "gt": "[[389, 108], [385, 129], [396, 137], [454, 140], [435, 157], [404, 143], [297, 162], [285, 166], [287, 181], [287, 161]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0014_user_0014_scene_0001_cfg_0001_039422060546#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the block from the scale', and now you are performing subtask 'remove the block from the scale.'\nBegin at [263, 124] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[263, 124], [286, 116], [280, 114], [285, 116], [287, 100], [313, 79], [316, 111], [313, 104], [288, 127], [264, 162]]}" + } + ], + "images": "RH20T_cfg1_task_0014_user_0014_scene_0001_cfg_0001_039422060546#0", + "gt": "[[263, 124], [286, 116], [280, 114], [285, 116], [287, 100], [313, 79], [316, 111], [313, 104], [288, 127], [264, 162]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "59697_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the objects from the orange bowl to the black pot, then cover the black pot with the glass lid', and now you are performing subtask 'pick up the item from the orange bowl.'\nStart at [249, 1]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[249, 1], [231, 58], [211, 74], [230, 85], [222, 54], [195, 83], [206, 89], [234, 54], [222, 64], [227, 84]]}" + } + ], + "images": "59697_exterior_image_2_left#0", + "gt": "[[249, 1], [231, 58], [211, 74], [230, 85], [222, 54], [195, 83], [206, 89], [234, 54], [222, 64], [227, 84]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0094_user_0014_scene_0003_cfg_0004_038522062288#TrajectoryPrediction_Task#8", + "task": "TrajectoryPrediction_Task", + "p_index": 8, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open a box', and now you are performing subtask 'push the lid on the bottom of the box.'\nYour initial coordinate is [172, 138]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[172, 138], [142, 135], [169, 147], [202, 92], [213, 101], [220, 87], [221, 99], [199, 79], [180, 94], [185, 118]]}" + } + ], + "images": "RH20T_cfg4_task_0094_user_0014_scene_0003_cfg_0004_038522062288#373", + "gt": "[[172, 138], [142, 135], [169, 147], [202, 92], [213, 101], [220, 87], [221, 99], [199, 79], [180, 94], [185, 118]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0058_user_0007_scene_0002_cfg_0005_037522062165#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press a row of two power strip buttons to turn off the power strips', and now you are performing subtask 'press the first button on the power socket, press the second button on the power socket.'\nStart at [247, 229]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[247, 229], [251, 225], [251, 229], [249, 228], [247, 230], [247, 229], [249, 227], [249, 225], [253, 223], [253, 223]]}" + } + ], + "images": "RH20T_cfg5_task_0058_user_0007_scene_0002_cfg_0005_037522062165#211", + "gt": "[[247, 229], [251, 225], [251, 229], [249, 228], [247, 230], [247, 229], [249, 227], [249, 225], [253, 223], [253, 223]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "83567_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the wooden block on top of the orange block', and now you are performing subtask 'put the wooden block on top of the orange block.'\nWith start location [134, 0], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[134, 0], [126, 54], [145, 82], [132, 106], [112, 110], [122, 117], [111, 113], [118, 97], [142, 101], [140, 87]]}" + } + ], + "images": "83567_exterior_image_2_left#0", + "gt": "[[134, 0], [126, 54], [145, 82], [132, 106], [112, 110], [122, 117], [111, 113], [118, 97], [142, 101], [140, 87]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "81812_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the marker from the mug, put the marker in the mug', and now you are performing subtask 'place the marker in the cup.'\nBegin at [241, 15] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[241, 15], [216, 50], [164, 65], [177, 69], [177, 73], [163, 30], [152, 32], [144, 48], [144, 61], [156, 95]]}" + } + ], + "images": "81812_exterior_image_1_left#0", + "gt": "[[241, 15], [216, 50], [164, 65], [177, 69], [177, 73], [163, 30], [152, 32], [144, 48], [144, 61], [156, 95]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg2_task_0080_user_0014_scene_0006_cfg_0002_105422061350#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'flip over and spread out the paper that is laid flat on the table', and now you are performing subtask 'flip over and spread out the paper that is laid flat on the table.'\nWith start location [301, 98], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[301, 98], [177, 86], [200, 114], [186, 117], [204, 83], [237, 81], [220, 59], [231, 23], [217, 81], [217, 81]]}" + } + ], + "images": "RH20T_cfg2_task_0080_user_0014_scene_0006_cfg_0002_105422061350#0", + "gt": "[[301, 98], [177, 86], [200, 114], [186, 117], [204, 83], [237, 81], [220, 59], [231, 23], [217, 81], [217, 81]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0066_user_0014_scene_0005_cfg_0007_104122061330#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with large Megabloks for the nth time with n blocks', and now you are performing subtask 'pick up the block on the flat surface, transfer the block from the flat surface to the block board, place the block on the block board.'\nYou begin at [266, 103]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[266, 103], [335, 193], [347, 230], [341, 252], [334, 254], [339, 262], [321, 237], [300, 179], [292, 187], [312, 188]]}" + } + ], + "images": "RH20T_cfg7_task_0066_user_0014_scene_0005_cfg_0007_104122061330#0", + "gt": "[[266, 103], [335, 193], [347, 230], [341, 252], [334, 254], [339, 262], [321, 237], [300, 179], [292, 187], [312, 188]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0003_user_0008_scene_0002_cfg_0001_039422060546#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press three buttons from left to right in sequence', and now you are performing subtask 'press the third button on the desk.'\nYou start from [295, 113]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[295, 113], [337, 50], [347, 54], [340, 44], [350, 61], [341, 28], [325, 19], [332, 55], [296, 66], [272, 107]]}" + } + ], + "images": "RH20T_cfg1_task_0003_user_0008_scene_0002_cfg_0001_039422060546#280", + "gt": "[[295, 113], [337, 50], [347, 54], [340, 44], [350, 61], [341, 28], [325, 19], [332, 55], [296, 66], [272, 107]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0003_user_0014_scene_0006_cfg_0005_105422061350#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press three buttons from left to right in sequence', and now you are performing subtask 'press the red button on the black and white base, press the green button on the gray and white base.'\nYour initial coordinate is [227, 30]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[227, 30], [230, 59], [247, 57], [242, 50], [237, 54], [236, 51], [237, 66], [233, 66], [240, 67], [242, 55]]}" + } + ], + "images": "RH20T_cfg5_task_0003_user_0014_scene_0006_cfg_0005_105422061350#289", + "gt": "[[227, 30], [230, 59], [247, 57], [242, 50], [237, 54], [236, 51], [237, 66], [233, 66], [240, 67], [242, 55]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "28265_exterior_image_2_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the cloth on the table', and now you are performing subtask 'unfold the cloth on the table.'\nStart at [146, 143]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[146, 143], [175, 164], [174, 150], [169, 142], [163, 136], [143, 130], [134, 123], [131, 135], [117, 141], [113, 147]]}" + } + ], + "images": "28265_exterior_image_2_left#224", + "gt": "[[146, 143], [175, 164], [174, 150], [169, 142], [163, 136], [143, 130], [134, 123], [131, 135], [117, 141], [113, 147]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg2_task_0057_user_0016_scene_0001_cfg_0002_036422060215#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn on the power strips', and now you are performing subtask 'press the button of the power strip, press the button of the second row socket, press the button of the third row socket.'\nStarting at [336, 156], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[336, 156], [336, 155], [335, 156], [335, 153], [334, 154], [326, 153], [324, 149], [321, 149], [321, 148], [318, 149]]}" + } + ], + "images": "RH20T_cfg2_task_0057_user_0016_scene_0001_cfg_0002_036422060215#385", + "gt": "[[336, 156], [336, 155], [335, 156], [335, 153], [334, 154], [326, 153], [324, 149], [321, 149], [321, 148], [318, 149]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0066_user_0014_scene_0008_cfg_0001_035622060973#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'putting a portion of the Lego blocks on the Lego baseplate', and now you are performing subtask 'pick up the red Lego brick from the table, transfer the red Lego brick from the table to the Lego base, insert the red Lego brick into the Lego base.'\nYou start from [247, 131]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[247, 131], [200, 90], [175, 96], [179, 108], [177, 97], [190, 81], [227, 98], [227, 114], [219, 104], [219, 104]]}" + } + ], + "images": "RH20T_cfg1_task_0066_user_0014_scene_0008_cfg_0001_035622060973#0", + "gt": "[[247, 131], [200, 90], [175, 96], [179, 108], [177, 97], [190, 81], [227, 98], [227, 114], [219, 104], [219, 104]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "69906_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the drawer, take out the black object, and place it on the countertop, pick up the pen on the countertop, put it back in the drawer, close the drawer', and now you are performing subtask 'pick up the black object in the drawer.'\nBegin at [75, 137] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[75, 137], [83, 136], [88, 138], [89, 142], [90, 141], [87, 144], [88, 150], [86, 147], [89, 145], [91, 149]]}" + } + ], + "images": "69906_exterior_image_1_left#233", + "gt": "[[75, 137], [83, 136], [88, 138], [89, 142], [90, 141], [87, 144], [88, 150], [86, 147], [89, 145], [91, 149]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "73211_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the earphone case and move it to the window sill', and now you are performing subtask 'pick up the earphone case and move it to the window sill.'\nYou begin at [191, 0]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[191, 0], [169, 32], [145, 36], [147, 46], [170, 36], [199, 48], [237, 34], [236, 25], [219, 26], [256, 4]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/73211_exterior_image_1_left#0.jpg", + "gt": "[[191, 0], [169, 32], [145, 36], [147, 46], [170, 36], [199, 48], [237, 34], [236, 25], [219, 26], [256, 4]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "71329_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the marker in the mug and then remove it and put it back on the table', and now you are performing subtask 'pick up the marker on the table.'\nStarting at [116, 3], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[116, 3], [89, 35], [87, 39], [92, 38], [72, 72], [70, 101], [58, 129], [65, 127], [76, 133], [78, 122]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/71329_exterior_image_2_left#0.jpg", + "gt": "[[116, 3], [89, 35], [87, 39], [92, 38], [72, 72], [70, 101], [58, 129], [65, 127], [76, 133], [78, 122]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0081_user_0010_scene_0009_cfg_0001_819112071037#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the leg of the glasses (with one hand)', and now you are performing subtask 'fold the leg of the glasses to unfold, fold the leg of the glasses to unfold.'\nYour starting position is [575, 0]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[575, 0], [621, 0], [582, 5], [575, 35], [592, 4], [549, 27], [566, 0], [555, 0], [578, 0], [476, 0]]}" + } + ], + "images": "RH20T_cfg1_task_0081_user_0010_scene_0009_cfg_0001_819112071037#166", + "gt": "[[575, 0], [621, 0], [582, 5], [575, 35], [592, 4], [549, 27], [566, 0], [555, 0], [578, 0], [476, 0]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "88295_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the lid from the table and put it on the pot', and now you are performing subtask 'pick up the lid from the table and put it on the pot.'\nBegin at [112, 0] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[112, 0], [118, 50], [109, 75], [124, 93], [108, 79], [117, 69], [135, 89], [151, 88], [170, 101], [142, 86]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/88295_exterior_image_1_left#0.jpg", + "gt": "[[112, 0], [118, 50], [109, 75], [124, 93], [108, 79], [117, 69], [135, 89], [151, 88], [170, 101], [142, 86]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0063_user_0020_scene_0008_cfg_0007_104122061018#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'use a shovel to scoop up an object', and now you are performing subtask 'use a shovel to scoop up an object.'\nThe trajectory starts at [363, 30]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[363, 30], [361, 73], [385, 140], [364, 217], [362, 190], [321, 137], [342, 146], [309, 123], [345, 166], [324, 64]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg7_task_0063_user_0020_scene_0008_cfg_0007_104122061018#0.jpg", + "gt": "[[363, 30], [361, 73], [385, 140], [364, 217], [362, 190], [321, 137], [342, 146], [309, 123], [345, 166], [324, 64]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "80330_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pour the contents from the cup into the bowl', and now you are performing subtask 'pour the contents from the cup into the bowl.'\nYour starting position is [151, 110]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[151, 110], [139, 109], [133, 105], [137, 109], [136, 115], [146, 111], [125, 105], [129, 98], [133, 98], [129, 95]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/80330_exterior_image_2_left#0.jpg", + "gt": "[[151, 110], [139, 109], [133, 105], [137, 109], [136, 115], [146, 111], [125, 105], [129, 98], [133, 98], [129, 95]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "38943_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the tomato in the pot', and now you are performing subtask 'put the tomato in the pot.'\nThe trajectory starts at [125, 1]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[125, 1], [149, 23], [169, 84], [179, 91], [172, 94], [177, 104], [172, 51], [157, 33], [153, 78], [145, 32]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/38943_exterior_image_1_left#0.jpg", + "gt": "[[125, 1], [149, 23], [169, 84], [179, 91], [172, 94], [177, 104], [172, 51], [157, 33], [153, 78], [145, 32]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0094_user_0007_scene_0003_cfg_0004_104122062295#TrajectoryPrediction_Task#8", + "task": "TrajectoryPrediction_Task", + "p_index": 8, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the box', and now you are performing subtask 'push the lid of the box, push the lid of the box.'\nYour starting position is [264, 104]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[264, 104], [225, 117], [197, 103], [204, 55], [199, 23], [186, 37], [181, 64], [183, 67], [198, 63], [227, 109]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg4_task_0094_user_0007_scene_0003_cfg_0004_104122062295#271.jpg", + "gt": "[[264, 104], [225, 117], [197, 103], [204, 55], [199, 23], [186, 37], [181, 64], [183, 67], [198, 63], [227, 109]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "24199_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'use the towel to wipe the pan', and now you are performing subtask 'use the towel to wipe the pan.'\nFrom start point [181, 11], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[181, 11], [143, 60], [141, 89], [138, 67], [135, 97], [116, 114], [109, 98], [137, 67], [148, 84], [151, 67]]}" + } + ], + "images": "24199_exterior_image_2_left#0", + "gt": "[[181, 11], [143, 60], [141, 89], [138, 67], [135, 97], [116, 114], [109, 98], [137, 67], [148, 84], [151, 67]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0081_user_0010_scene_0001_cfg_0001_035622060973#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the leg of the glasses (with one hand)', and now you are performing subtask 'pull the leg of the glasses outward, pull the other leg of the glasses outward.'\nStart at [260, 198]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[260, 198], [267, 174], [264, 177], [268, 176], [269, 183], [265, 212], [269, 210], [268, 224], [270, 208], [267, 212]]}" + } + ], + "images": "RH20T_cfg1_task_0081_user_0010_scene_0001_cfg_0001_035622060973#291", + "gt": "[[260, 198], [267, 174], [264, 177], [268, 176], [269, 183], [265, 212], [269, 210], [268, 224], [270, 208], [267, 212]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0017_user_0014_scene_0002_cfg_0006_037522061512#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the pen into the pen holder', and now you are performing subtask 'pick up the pen from the table.'\nStart at [257, 83]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[257, 83], [261, 119], [281, 159], [288, 164], [285, 153], [262, 131], [264, 151], [258, 170], [257, 205], [265, 171]]}" + } + ], + "images": "RH20T_cfg6_task_0017_user_0014_scene_0002_cfg_0006_037522061512#0", + "gt": "[[257, 83], [261, 119], [281, 159], [288, 164], [285, 153], [262, 131], [264, 151], [258, 170], [257, 205], [265, 171]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0009_user_0014_scene_0004_cfg_0001_038522063145#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take out a Hanoi block and throw it aside', and now you are performing subtask 'take out a Hanoi block and throw it aside.'\nThe trajectory starts at [441, 97]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[441, 97], [433, 89], [442, 66], [418, 109], [423, 80], [436, 80], [455, 93], [462, 129], [452, 141], [444, 81]]}" + } + ], + "images": "RH20T_cfg1_task_0009_user_0014_scene_0004_cfg_0001_038522063145#0", + "gt": "[[441, 97], [433, 89], [442, 66], [418, 109], [423, 80], [436, 80], [455, 93], [462, 129], [452, 141], [444, 81]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0066_user_0014_scene_0005_cfg_0007_104122063633#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with large Megabloks for the nth time with n blocks', and now you are performing subtask 'pick up the block on the flat surface, transfer the block from the flat surface to the block board, place the block on the block board.'\nYour initial coordinate is [234, 121]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[234, 121], [158, 118], [155, 125], [169, 141], [167, 148], [168, 138], [186, 122], [217, 163], [198, 151], [172, 150]]}" + } + ], + "images": "RH20T_cfg7_task_0066_user_0014_scene_0005_cfg_0007_104122063633#0", + "gt": "[[234, 121], [158, 118], [155, 125], [169, 141], [167, 148], [168, 138], [186, 122], [217, 163], [198, 151], [172, 150]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "57480_exterior_image_1_left#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the cup backwards, empty the bowl then sweep the table', and now you are performing subtask 'place the broom on the countertop.'\nYou start from [166, 114]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[166, 114], [190, 124], [163, 137], [171, 110], [154, 145], [164, 110], [181, 121], [156, 133], [167, 111], [167, 111]]}" + } + ], + "images": "57480_exterior_image_1_left#483", + "gt": "[[166, 114], [190, 124], [163, 137], [171, 110], [154, 145], [164, 110], [181, 121], [156, 133], [167, 111], [167, 111]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0065_user_0016_scene_0005_cfg_0004_104122063550#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with small Lego blocks for the nth time with n blocks', and now you are performing subtask 'place the third block on the Lego base, pick up the fourth block from the table, transfer the fourth block from the table to the Lego base, place the fourth block on the Lego base, pick up the fifth block from the table, transfer the fifth block from the table to the Lego base, place the fifth block on the Lego base.'\nYour initial coordinate is [372, 244]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[372, 244], [381, 250], [396, 224], [373, 229], [351, 262], [333, 264], [381, 201], [376, 215], [338, 235], [369, 210]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg4_task_0065_user_0016_scene_0005_cfg_0004_104122063550#305.jpg", + "gt": "[[372, 244], [381, 250], [396, 224], [373, 229], [351, 262], [333, 264], [381, 201], [376, 215], [338, 235], [369, 210]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0005_user_0008_scene_0001_cfg_0001_035622060973#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'approach and touch the side of the small block', and now you are performing subtask 'approach and touch the side of the small block.'\nThe trajectory starts at [247, 131]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[247, 131], [241, 149], [235, 137], [223, 134], [218, 128], [217, 121], [227, 130], [233, 131], [234, 128], [232, 130]]}" + } + ], + "images": "RH20T_cfg1_task_0005_user_0008_scene_0001_cfg_0001_035622060973#0", + "gt": "[[247, 131], [241, 149], [235, 137], [223, 134], [218, 128], [217, 121], [227, 130], [233, 131], [234, 128], [232, 130]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0121_user_0010_scene_0002_cfg_0001_819112070044#TrajectoryPrediction_Task#10", + "task": "TrajectoryPrediction_Task", + "p_index": 10, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'taking out the light bulb by rotating it', and now you are performing subtask 'twist the light bulb counterclockwise to loosen it, pick up the light bulb, transfer the light bulb from the table to the table, place the light bulb on the table.'\nYour initial coordinate is [395, 132]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[395, 132], [387, 129], [392, 123], [394, 133], [393, 124], [336, 155], [339, 179], [360, 145], [389, 126], [399, 146]]}" + } + ], + "images": "RH20T_cfg1_task_0121_user_0010_scene_0002_cfg_0001_819112070044#464", + "gt": "[[395, 132], [387, 129], [392, 123], [394, 133], [393, 124], [336, 155], [339, 179], [360, 145], [389, 126], [399, 146]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0032_user_0016_scene_0002_cfg_0004_104122062823#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'slide the outer casing onto the gift box', and now you are performing subtask 'slide the outer casing onto the gift box.'\nWith start location [285, 52], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[285, 52], [284, 51], [278, 51], [270, 52], [269, 53], [270, 54], [280, 53], [287, 49], [297, 41], [292, 43]]}" + } + ], + "images": "RH20T_cfg4_task_0032_user_0016_scene_0002_cfg_0004_104122062823#164", + "gt": "[[285, 52], [284, 51], [278, 51], [270, 52], [269, 53], [270, 54], [280, 53], [287, 49], [297, 41], [292, 43]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0001_user_0020_scene_0001_cfg_0005_105422061350#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the green button on the yellow base', and now you are performing subtask 'press the green button on the yellow base.'\nStart at [272, 51]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[272, 51], [249, 38], [230, 43], [231, 50], [224, 42], [231, 64], [219, 60], [237, 79], [232, 86], [243, 60]]}" + } + ], + "images": "RH20T_cfg5_task_0001_user_0020_scene_0001_cfg_0005_105422061350#0", + "gt": "[[272, 51], [249, 38], [230, 43], [231, 50], [224, 42], [231, 64], [219, 60], [237, 79], [232, 86], [243, 60]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0037_user_0007_scene_0004_cfg_0005_036422060215#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'pick up the first block from the surface, place the first block on the vertical stack on the surface, pick up the second block from the surface.'\nYour initial coordinate is [286, 108]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[286, 108], [291, 89], [296, 99], [296, 126], [308, 136], [303, 156], [287, 130], [268, 135], [263, 154], [254, 120]]}" + } + ], + "images": "RH20T_cfg5_task_0037_user_0007_scene_0004_cfg_0005_036422060215#0", + "gt": "[[286, 108], [291, 89], [296, 99], [296, 126], [308, 136], [303, 156], [287, 130], [268, 135], [263, 154], [254, 120]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "27562_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'fold the towel then remove the object from the drawer', and now you are performing subtask 'pick up the object from the drawer.'\nYou start from [102, 0]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[102, 0], [179, 72], [197, 108], [200, 76], [196, 66], [178, 66], [169, 81], [165, 57], [159, 49], [147, 44]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/27562_exterior_image_1_left#0.jpg", + "gt": "[[102, 0], [179, 72], [197, 108], [200, 76], [196, 66], [178, 66], [169, 81], [165, 57], [159, 49], [147, 44]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "4134_exterior_image_1_left#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'insert the small object into the green building block', and now you are performing subtask 'press the blue block onto the green block.'\nWith start location [214.5, 61.0], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[214.5, 61.0], [215.5, 51.0], [219.5, 44.0], [217.5, 51.0], [217.5, 72.0], [208.5, 53.0], [209.5, 48.0], [204.5, 47.0], [198.5, 50.0], [198.5, 50.0]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/4134_exterior_image_1_left#621.jpg", + "gt": "[[214.5, 61.0], [215.5, 51.0], [219.5, 44.0], [217.5, 51.0], [217.5, 72.0], [208.5, 53.0], [209.5, 48.0], [204.5, 47.0], [198.5, 50.0], [198.5, 50.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "51220_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the orange object inside the sink', and now you are performing subtask 'put the orange object inside the sink.'\nYou start from [111, 93]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[111, 93], [102, 108], [108, 138], [113, 122], [126, 118], [158, 124], [168, 139], [151, 163], [143, 141], [120, 136]]}" + } + ], + "images": "51220_exterior_image_1_left#0", + "gt": "[[111, 93], [102, 108], [108, 138], [113, 122], [126, 118], [158, 124], [168, 139], [151, 163], [143, 141], [120, 136]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "49601_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick the bottle up and move it to the right side of the table', and now you are performing subtask 'place the bottle on the right side of the table.'\nThe trajectory starts at [272, 10]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[272, 10], [230, 16], [208, 39], [202, 51], [200, 72], [217, 39], [225, 43], [220, 60], [213, 62], [219, 54]]}" + } + ], + "images": "49601_exterior_image_1_left#0", + "gt": "[[272, 10], [230, 16], [208, 39], [202, 51], [200, 72], [217, 39], [225, 43], [220, 60], [213, 62], [219, 54]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "35872_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the switch of the extension cord', and now you are performing subtask 'press the switch of the extension cord.'\nWith start location [85, 21], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[85, 21], [151, 80], [151, 74], [160, 88], [197, 89], [201, 93], [222, 91], [198, 101], [189, 99], [189, 91]]}" + } + ], + "images": "35872_exterior_image_1_left#0", + "gt": "[[85, 21], [151, 80], [151, 74], [160, 88], [197, 89], [201, 93], [222, 91], [198, 101], [189, 99], [189, 91]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "86836_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'fold the towel', and now you are performing subtask 'fold the towel on the table.'\nYour starting position is [67, 164]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[67, 164], [123, 120], [141, 138], [140, 167], [133, 147], [144, 100], [137, 155], [142, 133], [149, 153], [127, 170]]}" + } + ], + "images": "86836_exterior_image_1_left#236", + "gt": "[[67, 164], [123, 120], [141, 138], [140, 167], [133, 147], [144, 100], [137, 155], [142, 133], [149, 153], [127, 170]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "90585_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn off the faucet of the sink', and now you are performing subtask 'turn off the faucet of the sink.'\nYou begin at [189, 49]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[189, 49], [139, 63], [67, 54], [55, 63], [80, 87], [66, 65], [77, 81], [74, 70], [124, 66], [155, 35]]}" + } + ], + "images": "90585_exterior_image_1_left#0", + "gt": "[[189, 49], [139, 63], [67, 54], [55, 63], [80, 87], [66, 65], [77, 81], [74, 70], [124, 66], [155, 35]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "17711_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the white paper in the black bin then put the orange object in the open drawer then close the drawer', and now you are performing subtask 'transfer the white paper from the table to the black bin.'\nYou start from [123.5, 46.5]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[123.5, 46.5], [121.5, 47.5], [128.5, 53.5], [127.5, 55.5], [133.5, 53.5], [139.5, 57.5], [138.5, 51.5], [152.5, 35.5], [168.5, 24.5], [176.5, 23.5]]}" + } + ], + "images": "17711_exterior_image_1_left#0", + "gt": "[[123.5, 46.5], [121.5, 47.5], [128.5, 53.5], [127.5, 55.5], [133.5, 53.5], [139.5, 57.5], [138.5, 51.5], [152.5, 35.5], [168.5, 24.5], [176.5, 23.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0096_user_0014_scene_0001_cfg_0001_750612070851#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take something out of a drawer', and now you are performing subtask 'pull the drawer handle to the outside of the table.'\nWith start location [312, 169], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[312, 169], [365, 167], [405, 172], [446, 167], [473, 168], [485, 165], [479, 161], [484, 163], [402, 176], [411, 156]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0096_user_0014_scene_0001_cfg_0001_750612070851#0.jpg", + "gt": "[[312, 169], [365, 167], [405, 172], [446, 167], [473, 168], [485, 165], [479, 161], [484, 163], [402, 176], [411, 156]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "18143_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the orange plush toy slightly to the left', and now you are performing subtask 'move the orange plush toy slightly to the left.'\nWith start location [220, 4], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[220, 4], [206, 18], [200, 29], [193, 55], [187, 63], [189, 67], [184, 54], [151, 65], [155, 46], [170, 52]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/18143_exterior_image_1_left#0.jpg", + "gt": "[[220, 4], [206, 18], [200, 29], [193, 55], [187, 63], [189, 67], [184, 54], [151, 65], [155, 46], [170, 52]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0009_user_0010_scene_0006_cfg_0004_036422060909#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take out a Hanoi block and throw it aside', and now you are performing subtask 'pick up the Hanoi block from the surface of the wooden table.'\nFrom start point [337, 78], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[337, 78], [339, 69], [335, 82], [331, 83], [333, 89], [322, 99], [316, 95], [323, 113], [320, 116], [327, 115]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg4_task_0009_user_0010_scene_0006_cfg_0004_036422060909#0.jpg", + "gt": "[[337, 78], [339, 69], [335, 82], [331, 83], [333, 89], [322, 99], [316, 95], [323, 113], [320, 116], [327, 115]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg3_task_0057_user_0010_scene_0005_cfg_0003_104122062823#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn them on', and now you are performing subtask 'press the first button on the power board.'\nYou begin at [246, 0]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[246, 0], [220, 2], [220, 22], [192, 18], [230, 14], [245, 40], [229, 59], [242, 55], [232, 70], [227, 49]]}" + } + ], + "images": "RH20T_cfg3_task_0057_user_0010_scene_0005_cfg_0003_104122062823#0", + "gt": "[[246, 0], [220, 2], [220, 22], [192, 18], [230, 14], [245, 40], [229, 59], [242, 55], [232, 70], [227, 49]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0026_user_0014_scene_0007_cfg_0006_037522061512#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'use the gripper to push and close the drawer', and now you are performing subtask 'use the gripper to push and close the drawer.'\nYour initial coordinate is [257, 83]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[257, 83], [251, 84], [221, 126], [221, 142], [208, 169], [206, 198], [203, 183], [209, 155], [221, 118], [227, 114]]}" + } + ], + "images": "RH20T_cfg6_task_0026_user_0014_scene_0007_cfg_0006_037522061512#0", + "gt": "[[257, 83], [251, 84], [221, 126], [221, 142], [208, 169], [206, 198], [203, 183], [209, 155], [221, 118], [227, 114]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0061_user_0020_scene_0002_cfg_0007_104122064161#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take everything out of the gift box', and now you are performing subtask 'grab the object in the box, transfer the object from the box to the tabletop, place the object on the tabletop.'\nBegin at [372, 132] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[372, 132], [361, 142], [372, 128], [374, 160], [378, 134], [386, 157], [376, 206], [379, 220], [388, 216], [392, 165]]}" + } + ], + "images": "RH20T_cfg7_task_0061_user_0020_scene_0002_cfg_0007_104122064161#207", + "gt": "[[372, 132], [361, 142], [372, 128], [374, 160], [378, 134], [386, 157], [376, 206], [379, 220], [388, 216], [392, 165]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "92163_exterior_image_1_left#TrajectoryPrediction_Task#12", + "task": "TrajectoryPrediction_Task", + "p_index": 12, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the towel', and now you are performing subtask 'fold the towel on the table.'\nWith start location [182, 69], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[182, 69], [147, 80], [136, 79], [110, 92], [103, 89], [117, 104], [119, 83], [111, 82], [111, 78], [161, 78]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/92163_exterior_image_1_left#1284.jpg", + "gt": "[[182, 69], [147, 80], [136, 79], [110, 92], [103, 89], [117, 104], [119, 83], [111, 82], [111, 78], [161, 78]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "71273_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'rotate the object on the table counterclockwise', and now you are performing subtask 'rotate the object on the table counterclockwise.'\nBegin at [180.5, 144.5] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[180.5, 144.5], [172.5, 130.5], [171.5, 126.5], [174.5, 129.5], [169.5, 131.5], [181.5, 136.5], [179.5, 133.5], [172.5, 134.5], [180.5, 133.5], [170.5, 136.5]]}" + } + ], + "images": "71273_exterior_image_1_left#0", + "gt": "[[180.5, 144.5], [172.5, 130.5], [171.5, 126.5], [174.5, 129.5], [169.5, 131.5], [181.5, 136.5], [179.5, 133.5], [172.5, 134.5], [180.5, 133.5], [170.5, 136.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0073_user_0020_scene_0003_cfg_0006_037522061512#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the things in the drawer', and now you are performing subtask 'pull the drawer to the open position.'\nFrom start point [256, 84], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[256, 84], [252, 96], [240, 100], [239, 109], [214, 121], [205, 156], [210, 138], [227, 124], [226, 109], [250, 75]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg6_task_0073_user_0020_scene_0003_cfg_0006_037522061512#0.jpg", + "gt": "[[256, 84], [252, 96], [240, 100], [239, 109], [214, 121], [205, 156], [210, 138], [227, 124], [226, 109], [250, 75]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "10884_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the marker into the cup', and now you are performing subtask 'put the marker into the cup.'\nThe trajectory starts at [91, 48]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[91, 48], [109, 58], [128, 84], [117, 120], [120, 138], [143, 153], [157, 119], [167, 147], [181, 161], [170, 142]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/10884_exterior_image_1_left#0.jpg", + "gt": "[[91, 48], [109, 58], [128, 84], [117, 120], [120, 138], [143, 153], [157, 119], [167, 147], [181, 161], [170, 142]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "72859_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pour the brown object from the transparent jar into the bowl', and now you are performing subtask 'pour the brown object from the transparent jar into the bowl.'\nYour initial coordinate is [183, 35]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[183, 35], [135, 119], [166, 106], [164, 86], [159, 106], [170, 109], [151, 122], [159, 103], [145, 95], [145, 95]]}" + } + ], + "images": "72859_exterior_image_1_left#0", + "gt": "[[183, 35], [135, 119], [166, 106], [164, 86], [159, 106], [170, 109], [151, 122], [159, 103], [145, 95], [145, 95]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0034_user_0016_scene_0009_cfg_0004_104122062823#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the squares into a pyramid shape', and now you are performing subtask 'place the first block on the three blocks, pick up the second block on the cardboard, transfer the second block from the cardboard to the three blocks, place the second block on top of the three blocks.'\nFrom start point [378, 80], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[378, 80], [335, 90], [314, 102], [279, 155], [346, 77], [360, 67], [364, 76], [355, 81], [365, 79], [365, 86]]}" + } + ], + "images": "RH20T_cfg4_task_0034_user_0016_scene_0009_cfg_0004_104122062823#226", + "gt": "[[378, 80], [335, 90], [314, 102], [279, 155], [346, 77], [360, 67], [364, 76], [355, 81], [365, 79], [365, 86]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0012_user_0010_scene_0005_cfg_0004_104122062823#TrajectoryPrediction_Task#10", + "task": "TrajectoryPrediction_Task", + "p_index": 10, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'push the soccer ball into the goal', and now you are performing subtask 'push the soccer ball toward the goal.'\nStarting at [247, 192], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[247, 192], [257, 190], [231, 183], [225, 204], [251, 222], [275, 226], [235, 172], [239, 107], [255, 77], [270, 64]]}" + } + ], + "images": "RH20T_cfg4_task_0012_user_0010_scene_0005_cfg_0004_104122062823#255", + "gt": "[[247, 192], [257, 190], [231, 183], [225, 204], [251, 222], [275, 226], [235, 172], [239, 107], [255, 77], [270, 64]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "68725_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close the plastic box on the table', and now you are performing subtask 'close the plastic box on the table.'\nStart at [106, 0]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[106, 0], [105, 25], [91, 44], [101, 60], [100, 88], [102, 55], [118, 49], [133, 63], [124, 68], [120, 62]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/68725_exterior_image_2_left#0.jpg", + "gt": "[[106, 0], [105, 25], [91, 44], [101, 60], [100, 88], [102, 55], [118, 49], [133, 63], [124, 68], [120, 62]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0038_user_0014_scene_0006_cfg_0006_104122060811#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the cup', and now you are performing subtask 'pick up the cup.'\nBegin at [385, 127] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[385, 127], [381, 125], [386, 121], [386, 116], [383, 115], [389, 120], [393, 112], [389, 107], [385, 106], [385, 106]]}" + } + ], + "images": "RH20T_cfg6_task_0038_user_0014_scene_0006_cfg_0006_104122060811#0", + "gt": "[[385, 127], [381, 125], [386, 121], [386, 116], [383, 115], [389, 120], [393, 112], [389, 107], [385, 106], [385, 106]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "7263_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close the clear container', and now you are performing subtask 'close the clear container.'\nYour starting position is [206.5, 5.5]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[206.5, 5.5], [222.5, 79.5], [212.5, 110.5], [201.5, 115.5], [193.5, 106.5], [180.5, 121.5], [160.5, 116.5], [163.5, 69.5], [237.5, 42.5], [220.5, 37.5]]}" + } + ], + "images": "7263_exterior_image_1_left#0", + "gt": "[[206.5, 5.5], [222.5, 79.5], [212.5, 110.5], [201.5, 115.5], [193.5, 106.5], [180.5, 121.5], [160.5, 116.5], [163.5, 69.5], [237.5, 42.5], [220.5, 37.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0015_user_0008_scene_0008_cfg_0001_038522062547#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'play the drum', and now you are performing subtask 'pick up the drumstick on the table, transfer the drumstick from the right side of the table to the top of the drum, strike the drum with the drumstick, place the drumstick on the table.'\nYour initial coordinate is [466, 188]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[466, 188], [493, 184], [510, 137], [454, 32], [415, 41], [439, 69], [434, 53], [381, 146], [395, 104], [379, 69]]}" + } + ], + "images": "RH20T_cfg1_task_0015_user_0008_scene_0008_cfg_0001_038522062547#209", + "gt": "[[466, 188], [493, 184], [510, 137], [454, 32], [415, 41], [439, 69], [434, 53], [381, 146], [395, 104], [379, 69]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0045_user_0020_scene_0010_cfg_0006_104122064161#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'place the brush on the pen rack', and now you are performing subtask 'place the brush on the pen rack.'\nYou begin at [338, 110]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[338, 110], [343, 170], [377, 198], [377, 224], [400, 147], [387, 109], [402, 100], [399, 87], [383, 87], [410, 90]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg6_task_0045_user_0020_scene_0010_cfg_0006_104122064161#0.jpg", + "gt": "[[338, 110], [343, 170], [377, 198], [377, 224], [400, 147], [387, 109], [402, 100], [399, 87], [383, 87], [410, 90]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "24423_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the marker in the mug on the table', and now you are performing subtask 'put the marker in the mug on the table.'\nYou start from [137.0, 28.5]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[137.0, 28.5], [140.0, 34.5], [124.0, 42.5], [137.0, 53.5], [130.0, 61.5], [131.0, 71.5], [114.0, 47.5], [101.0, 42.5], [99.0, 52.5], [109.0, 81.5]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/24423_exterior_image_1_left#0.jpg", + "gt": "[[137.0, 28.5], [140.0, 34.5], [124.0, 42.5], [137.0, 53.5], [130.0, 61.5], [131.0, 71.5], [114.0, 47.5], [101.0, 42.5], [99.0, 52.5], [109.0, 81.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "17113_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'hang the cloth on the chair', and now you are performing subtask 'hang the cloth on the chair.'\nThe trajectory starts at [182.5, 56.0]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[182.5, 56.0], [176.5, 62.0], [184.5, 59.0], [183.5, 79.0], [165.5, 116.0], [178.5, 34.0], [191.5, 31.0], [222.5, 49.0], [210.5, 26.0], [201.5, 35.0]]}" + } + ], + "images": "17113_exterior_image_1_left#0", + "gt": "[[182.5, 56.0], [176.5, 62.0], [184.5, 59.0], [183.5, 79.0], [165.5, 116.0], [178.5, 34.0], [191.5, 31.0], [222.5, 49.0], [210.5, 26.0], [201.5, 35.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "41728_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the cup from the countertop and pour its contents into the bowl', and now you are performing subtask 'pick up the cup from the countertop and pour its contents into the bowl.'\nStarting at [143, 113], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[143, 113], [147, 114], [148, 103], [151, 99], [161, 101], [164, 106], [164, 111], [159, 107], [139, 104], [134, 91]]}" + } + ], + "images": "41728_exterior_image_2_left#0", + "gt": "[[143, 113], [147, 114], [148, 103], [151, 99], [161, 101], [164, 106], [164, 111], [159, 107], [139, 104], [134, 91]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "50909_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the toy out of the bowl', and now you are performing subtask 'take the toy out of the bowl.'\nWith start location [36.0, 70.0], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[36.0, 70.0], [94.0, 62.0], [141.0, 71.0], [181.0, 117.0], [178.0, 150.0], [173.0, 113.0], [190.0, 90.0], [201.0, 104.0], [201.0, 119.0], [195.0, 113.0]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/50909_exterior_image_1_left#0.jpg", + "gt": "[[36.0, 70.0], [94.0, 62.0], [141.0, 71.0], [181.0, 117.0], [178.0, 150.0], [173.0, 113.0], [190.0, 90.0], [201.0, 104.0], [201.0, 119.0], [195.0, 113.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0201_user_0015_scene_0007_cfg_0001_750612070853#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'the medium pipette tip is inserted into the holder for medium pipette tips', and now you are performing subtask 'place the tip of the medium pipette into the holder for medium pipette tips.'\nStarting at [413, 119], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[413, 119], [411, 125], [407, 126], [409, 129], [412, 129], [412, 110], [410, 110], [401, 125], [405, 132], [405, 145]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0201_user_0015_scene_0007_cfg_0001_750612070853#264.jpg", + "gt": "[[413, 119], [411, 125], [407, 126], [409, 129], [412, 129], [412, 110], [410, 110], [401, 125], [405, 132], [405, 145]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "73797_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the marker into the black cup', and now you are performing subtask 'put the marker into the black cup.'\nStart at [144, 20]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[144, 20], [160, 51], [176, 63], [172, 74], [179, 76], [173, 70], [168, 80], [191, 38], [164, 39], [141, 0]]}" + } + ], + "images": "73797_exterior_image_2_left#0", + "gt": "[[144, 20], [160, 51], [176, 63], [172, 74], [179, 76], [173, 70], [168, 80], [191, 38], [164, 39], [141, 0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "77278_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the object and put it in the pot in the sink', and now you are performing subtask 'take the object and put it in the pot in the sink.'\nBegin at [39, 40] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[39, 40], [93, 45], [106, 41], [95, 33], [102, 28], [135, 93], [158, 97], [183, 127], [165, 92], [165, 92]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/77278_exterior_image_1_left#0.jpg", + "gt": "[[39, 40], [93, 45], [106, 41], [95, 33], [102, 28], [135, 93], [158, 97], [183, 127], [165, 92], [165, 92]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg2_task_0042_user_0007_scene_0002_cfg_0002_037522062165#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'screw the lid onto the jar (needs to be rotated)', and now you are performing subtask 'twist the lid clockwise to the jar.'\nYour starting position is [249, 264]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[249, 264], [242, 263], [242, 261], [246, 261], [248, 255], [250, 257], [251, 255], [253, 259], [250, 261], [253, 262]]}" + } + ], + "images": "RH20T_cfg2_task_0042_user_0007_scene_0002_cfg_0002_037522062165#1039", + "gt": "[[249, 264], [242, 263], [242, 261], [246, 261], [248, 255], [250, 257], [251, 255], [253, 259], [250, 261], [253, 262]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "87674_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the microwave door', and now you are performing subtask 'pull the handle of the microwave door to open the microwave door.'\nStarting at [236, 102], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[236, 102], [209, 104], [212, 101], [204, 111], [188, 118], [193, 116], [192, 119], [173, 107], [171, 119], [171, 101]]}" + } + ], + "images": "87674_exterior_image_1_left#0", + "gt": "[[236, 102], [209, 104], [212, 101], [204, 111], [188, 118], [193, 116], [192, 119], [173, 107], [171, 119], [171, 101]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "59148_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the bowl to the right', and now you are performing subtask 'move the bowl to the right.'\nYour starting position is [146.0, 4.0]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[146.0, 4.0], [159.0, 21.0], [173.0, 71.0], [170.0, 72.0], [185.0, 86.0], [180.0, 94.0], [186.0, 92.0], [223.0, 104.0], [206.0, 77.0], [183.0, 63.0]]}" + } + ], + "images": "59148_exterior_image_1_left#0", + "gt": "[[146.0, 4.0], [159.0, 21.0], [173.0, 71.0], [170.0, 72.0], [185.0, 86.0], [180.0, 94.0], [186.0, 92.0], [223.0, 104.0], [206.0, 77.0], [183.0, 63.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0126_user_0014_scene_0006_cfg_0006_104122061018#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'plug in the power cord to the socket', and now you are performing subtask 'plug in the power cord to the socket.'\nStarting at [367, 28], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[367, 28], [349, 78], [316, 115], [272, 128], [255, 156], [269, 129], [267, 96], [264, 109], [273, 98], [289, 105]]}" + } + ], + "images": "RH20T_cfg6_task_0126_user_0014_scene_0006_cfg_0006_104122061018#0", + "gt": "[[367, 28], [349, 78], [316, 115], [272, 128], [255, 156], [269, 129], [267, 96], [264, 109], [273, 98], [289, 105]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg2_task_0062_user_0007_scene_0001_cfg_0002_036422060215#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the toilet paper on its holder', and now you are performing subtask 'put the toilet paper on its holder.'\nStart at [294, 161]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[294, 161], [272, 139], [244, 129], [249, 140], [237, 144], [225, 182], [233, 190], [240, 181], [219, 216], [255, 152]]}" + } + ], + "images": "RH20T_cfg2_task_0062_user_0007_scene_0001_cfg_0002_036422060215#0", + "gt": "[[294, 161], [272, 139], [244, 129], [249, 140], [237, 144], [225, 182], [233, 190], [240, 181], [219, 216], [255, 152]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "36381_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the pencil to the right', and now you are performing subtask 'move the pencil to the right.'\nBegin at [50.0, 5.5] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[50.0, 5.5], [75.0, 25.5], [99.0, 56.5], [102.0, 50.5], [114.0, 48.5], [147.0, 59.5], [157.0, 69.5], [154.0, 61.5], [147.0, 70.5], [146.0, 66.5]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/36381_exterior_image_1_left#0.jpg", + "gt": "[[50.0, 5.5], [75.0, 25.5], [99.0, 56.5], [102.0, 50.5], [114.0, 48.5], [147.0, 59.5], [157.0, 69.5], [154.0, 61.5], [147.0, 70.5], [146.0, 66.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "66931_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the plush toy behind the shelf', and now you are performing subtask 'put the plush toy behind the shelf.'\nBegin at [66.0, 114.5] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[66.0, 114.5], [108.0, 121.5], [145.0, 134.5], [158.0, 140.5], [171.0, 155.5], [164.0, 140.5], [164.0, 104.5], [157.0, 93.5], [153.0, 102.5], [154.0, 94.5]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/66931_exterior_image_1_left#0.jpg", + "gt": "[[66.0, 114.5], [108.0, 121.5], [145.0, 134.5], [158.0, 140.5], [171.0, 155.5], [164.0, 140.5], [164.0, 104.5], [157.0, 93.5], [153.0, 102.5], [154.0, 94.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "71190_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'fold the orange cloth', and now you are performing subtask 'fold the orange cloth on the table.'\nThe trajectory starts at [117, 92]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[117, 92], [140, 114], [131, 139], [120, 133], [128, 137], [128, 148], [135, 136], [145, 173], [154, 180], [154, 152]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/71190_exterior_image_2_left#0.jpg", + "gt": "[[117, 92], [140, 114], [131, 139], [120, 133], [128, 137], [128, 148], [135, 136], [145, 173], [154, 180], [154, 152]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0066_user_0014_scene_0005_cfg_0001_038522063145#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with large Megabloks for the nth time with n blocks', and now you are performing subtask 'place the first Megablock on the green base, pick up the second Megablock from the left side of the table, place the second Megablock on the green base.'\nYou begin at [473, 161]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[473, 161], [492, 144], [510, 145], [517, 151], [510, 157], [533, 135], [555, 127], [471, 116], [450, 129], [437, 152]]}" + } + ], + "images": "RH20T_cfg1_task_0066_user_0014_scene_0005_cfg_0001_038522063145#184", + "gt": "[[473, 161], [492, 144], [510, 145], [517, 151], [510, 157], [533, 135], [555, 127], [471, 116], [450, 129], [437, 152]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0017_user_0014_scene_0002_cfg_0006_037522061512#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the pen into the pen holder', and now you are performing subtask 'pick up the pen from the table, transfer the pen from the table to the position of the pen holder, place the pen in the pen holder.'\nYou start from [265, 171]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[265, 171], [279, 173], [291, 188], [272, 155], [266, 162], [266, 191], [281, 187], [274, 217], [273, 176], [268, 181]]}" + } + ], + "images": "RH20T_cfg6_task_0017_user_0014_scene_0002_cfg_0006_037522061512#245", + "gt": "[[265, 171], [279, 173], [291, 188], [272, 155], [266, 162], [266, 191], [281, 187], [274, 217], [273, 176], [268, 181]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "34771_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close the clear container', and now you are performing subtask 'close the clear container.'\nBegin at [216, 24] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[216, 24], [213, 40], [233, 66], [211, 117], [223, 121], [214, 122], [205, 103], [227, 101], [230, 79], [224, 83]]}" + } + ], + "images": "34771_exterior_image_1_left#0", + "gt": "[[216, 24], [213, 40], [233, 66], [211, 117], [223, 121], [214, 122], [205, 103], [227, 101], [230, 79], [224, 83]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "16307_exterior_image_1_left#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'line up the empty water bottles', and now you are performing subtask 'place the fifth empty water bottle in the designated position.'\nFrom start point [168, 144], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[168, 144], [148, 122], [129, 120], [112, 128], [107, 146], [136, 169], [122, 141], [118, 117], [142, 112], [155, 119]]}" + } + ], + "images": "16307_exterior_image_1_left#785", + "gt": "[[168, 144], [148, 122], [129, 120], [112, 128], [107, 146], [136, 169], [122, 141], [118, 117], [142, 112], [155, 119]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "72914_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take out a tissue from the tissue box and place it on the table', and now you are performing subtask 'take out a tissue from the tissue box and place it on the table.'\nYou begin at [306, 113]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[306, 113], [228, 105], [196, 95], [135, 91], [126, 98], [164, 81], [188, 89], [219, 116], [189, 129], [172, 117]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/72914_exterior_image_1_left#0.jpg", + "gt": "[[306, 113], [228, 105], [196, 95], [135, 91], [126, 98], [164, 81], [188, 89], [219, 116], [189, 129], [172, 117]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "77732_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press down on the white lid, remove the lid from the food container', and now you are performing subtask 'pick up the lid on the square box.'\nBegin at [237, 2] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[237, 2], [223, 46], [227, 48], [214, 48], [210, 60], [213, 74], [219, 75], [218, 38], [207, 56], [219, 55]]}" + } + ], + "images": "77732_exterior_image_1_left#0", + "gt": "[[237, 2], [223, 46], [227, 48], [214, 48], [210, 60], [213, 74], [219, 75], [218, 38], [207, 56], [219, 55]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0073_user_0001_scene_0003_cfg_0001_038522062547#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the things in the drawer', and now you are performing subtask 'place the block in the drawer, push the drawer handle to close the drawer.'\nYour starting position is [376, 103]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[376, 103], [370, 89], [355, 91], [353, 87], [344, 96], [355, 139], [354, 178], [378, 139], [407, 113], [410, 117]]}" + } + ], + "images": "RH20T_cfg1_task_0073_user_0001_scene_0003_cfg_0001_038522062547#319", + "gt": "[[376, 103], [370, 89], [355, 91], [353, 87], [344, 96], [355, 139], [354, 178], [378, 139], [407, 113], [410, 117]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "1768_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the marker on the table', and now you are performing subtask 'put the marker on the table.'\nYour starting position is [119.0, 49.5]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[119.0, 49.5], [136.0, 47.5], [146.0, 51.5], [156.0, 60.5], [163.0, 80.5], [171.0, 87.5], [168.0, 71.5], [167.0, 87.5], [161.0, 97.5], [167.0, 104.5]]}" + } + ], + "images": "1768_exterior_image_1_left#0", + "gt": "[[119.0, 49.5], [136.0, 47.5], [146.0, 51.5], [156.0, 60.5], [163.0, 80.5], [171.0, 87.5], [168.0, 71.5], [167.0, 87.5], [161.0, 97.5], [167.0, 104.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "75030_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn the knob on the microwave to the right', and now you are performing subtask 'turn the knob on the microwave to the right.'\nFrom start point [125.0, 64.5], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[125.0, 64.5], [157.0, 75.5], [169.0, 84.5], [176.0, 82.5], [177.0, 77.5], [177.0, 80.5], [190.0, 85.5], [190.0, 75.5], [186.0, 74.5], [183.0, 78.5]]}" + } + ], + "images": "75030_exterior_image_1_left#0", + "gt": "[[125.0, 64.5], [157.0, 75.5], [169.0, 84.5], [176.0, 82.5], [177.0, 77.5], [177.0, 80.5], [190.0, 85.5], [190.0, 75.5], [186.0, 74.5], [183.0, 78.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "62246_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the marker in the bowl', and now you are performing subtask 'put the marker in the bowl.'\nStart at [251, 4]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[251, 4], [240, 24], [222, 39], [214, 48], [208, 60], [197, 72], [193, 65], [190, 32], [184, 25], [182, 35]]}" + } + ], + "images": "62246_exterior_image_2_left#0", + "gt": "[[251, 4], [240, 24], [222, 39], [214, 48], [208, 60], [197, 72], [193, 65], [190, 32], [184, 25], [182, 35]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "13358_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the three cloves of garlic from the glass bowl and put them on the countertop', and now you are performing subtask 'pick up the garlic from the bowl.'\nThe trajectory starts at [309, 56]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[309, 56], [269, 92], [243, 105], [248, 130], [243, 104], [233, 99], [207, 127], [220, 97], [241, 104], [239, 120]]}" + } + ], + "images": "13358_exterior_image_1_left#0", + "gt": "[[309, 56], [269, 92], [243, 105], [248, 130], [243, 104], [233, 99], [207, 127], [220, 97], [241, 104], [239, 120]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0037_user_0007_scene_0010_cfg_0005_104122061850#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'place the first block on top of the second block, pick up the third block on the table, transfer the third block from the table to the position above the first block, place the third block on top of the first block.'\nStarting at [330, 172], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[330, 172], [338, 167], [363, 174], [373, 183], [373, 197], [361, 155], [337, 140], [326, 151], [321, 150], [315, 154]]}" + } + ], + "images": "RH20T_cfg5_task_0037_user_0007_scene_0010_cfg_0005_104122061850#341", + "gt": "[[330, 172], [338, 167], [363, 174], [373, 183], [373, 197], [361, 155], [337, 140], [326, 151], [321, 150], [315, 154]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0130_user_0014_scene_0004_cfg_0006_104122061018#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'plug in the bulb holder with a bulb to the socket and turn on the switch of the bulb', and now you are performing subtask 'pick up the lamp holder and the light bulb from the table, transfer the lamp holder from the table to the socket, insert the lamp holder into the socket.'\nYour starting position is [367, 28]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[367, 28], [336, 79], [345, 101], [315, 158], [302, 167], [298, 161], [312, 131], [308, 100], [298, 115], [304, 105]]}" + } + ], + "images": "RH20T_cfg6_task_0130_user_0014_scene_0004_cfg_0006_104122061018#0", + "gt": "[[367, 28], [336, 79], [345, 101], [315, 158], [302, 167], [298, 161], [312, 131], [308, 100], [298, 115], [304, 105]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0123_user_0010_scene_0004_cfg_0005_037522062165#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the knife on the knife rack', and now you are performing subtask 'pick up the knife on the table, transfer the knife from the table to the knife rack, place the knife on the knife rack.'\nThe trajectory starts at [298, 144]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[298, 144], [303, 153], [297, 182], [300, 217], [295, 280], [245, 215], [244, 208], [231, 210], [227, 205], [218, 204]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0123_user_0010_scene_0004_cfg_0005_037522062165#0.jpg", + "gt": "[[298, 144], [303, 153], [297, 182], [300, 217], [295, 280], [245, 215], [244, 208], [231, 210], [227, 205], [218, 204]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "29645_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close the left door of the cabinet', and now you are performing subtask 'close the left door of the cabinet.'\nYour starting position is [8.0, 38.0]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[8.0, 38.0], [46.0, 54.0], [80.0, 85.0], [125.0, 90.0], [152.0, 102.0], [163.0, 97.0], [168.0, 99.0], [136.0, 105.0], [99.0, 120.0], [76.0, 99.0]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/29645_exterior_image_1_left#0.jpg", + "gt": "[[8.0, 38.0], [46.0, 54.0], [80.0, 85.0], [125.0, 90.0], [152.0, 102.0], [163.0, 97.0], [168.0, 99.0], [136.0, 105.0], [99.0, 120.0], [76.0, 99.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "70402_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the top cabinet door', and now you are performing subtask 'open the top cabinet door.'\nYou start from [315, 16]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[315, 16], [293, 22], [186, 66], [180, 70], [178, 75], [182, 85], [197, 102], [198, 100], [205, 101], [197, 88]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/70402_exterior_image_2_left#0.jpg", + "gt": "[[315, 16], [293, 22], [186, 66], [180, 70], [178, 75], [182, 85], [197, 102], [198, 100], [205, 101], [197, 88]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg3_task_0003_user_0016_scene_0006_cfg_0003_104122062823#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press three buttons from left to right in sequence', and now you are performing subtask 'press the green button on the right, press the red button in the middle.'\nWith start location [372, 77], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[372, 77], [353, 55], [324, 43], [312, 44], [294, 53], [288, 52], [278, 44], [281, 52], [274, 64], [273, 56]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg3_task_0003_user_0016_scene_0006_cfg_0003_104122062823#163.jpg", + "gt": "[[372, 77], [353, 55], [324, 43], [312, 44], [294, 53], [288, 52], [278, 44], [281, 52], [274, 64], [273, 56]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "31401_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the purple packet out of the sink and place it on the countertop', and now you are performing subtask 'take the purple packet out of the sink and place it on the countertop.'\nFrom start point [230, 60], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[230, 60], [216, 140], [224, 147], [221, 150], [216, 140], [221, 133], [226, 134], [200, 158], [200, 143], [205, 140]]}" + } + ], + "images": "31401_exterior_image_2_left#0", + "gt": "[[230, 60], [216, 140], [224, 147], [221, 150], [216, 140], [221, 133], [226, 134], [200, 158], [200, 143], [205, 140]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "40510_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the glue stick from the cup, place it on the box, then on the table, back into the cup, and lastly on the table', and now you are performing subtask 'place glue stick on the box.'\nYou begin at [315, 120]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[315, 120], [283, 136], [252, 123], [233, 128], [258, 113], [281, 126], [283, 130], [276, 136], [282, 124], [282, 124]]}" + } + ], + "images": "40510_exterior_image_1_left#0", + "gt": "[[315, 120], [283, 136], [252, 123], [233, 128], [258, 113], [281, 126], [283, 130], [276, 136], [282, 124], [282, 124]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "50349_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the glass lid on the black pot', and now you are performing subtask 'put the glass lid on the black pot.'\nBegin at [215, 33] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[215, 33], [199, 55], [178, 102], [166, 115], [161, 133], [163, 111], [181, 94], [185, 98], [182, 101], [181, 93]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/50349_exterior_image_2_left#0.jpg", + "gt": "[[215, 33], [199, 55], [178, 102], [166, 115], [161, 133], [163, 111], [181, 94], [185, 98], [182, 101], [181, 93]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0073_user_0001_scene_0003_cfg_0001_038522062547#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the things in the drawer', and now you are performing subtask 'pick up the block on the drawer, transfer the block from above the drawer to inside the drawer, place the block in the drawer.'\nFrom start point [406, 134], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[406, 134], [416, 118], [376, 145], [389, 197], [379, 204], [387, 139], [385, 131], [379, 136], [375, 158], [376, 103]]}" + } + ], + "images": "RH20T_cfg1_task_0073_user_0001_scene_0003_cfg_0001_038522062547#0", + "gt": "[[406, 134], [416, 118], [376, 145], [389, 197], [379, 204], [387, 139], [385, 131], [379, 136], [375, 158], [376, 103]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0047_user_0014_scene_0005_cfg_0004_104122062823#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the cup off the cup rack', and now you are performing subtask 'pick up the cup from the cup rack, transfer the cup from the cup rack to the table, put the cup on the table, push the cup to the edge of the table.'\nYour starting position is [243, 0]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[243, 0], [275, 0], [262, 0], [273, 0], [276, 6], [282, 0], [297, 0], [137, 0], [192, 2], [240, 0]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg4_task_0047_user_0014_scene_0005_cfg_0004_104122062823#0.jpg", + "gt": "[[243, 0], [275, 0], [262, 0], [273, 0], [276, 6], [282, 0], [297, 0], [137, 0], [192, 2], [240, 0]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg3_task_0018_user_0010_scene_0003_cfg_0003_038522062288#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'transfer the wooden block from the block pile to the tabletop', and now you are performing subtask 'transfer the wooden block from the block pile to the tabletop.'\nYou start from [236, 129]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[236, 129], [209, 141], [240, 147], [231, 146], [206, 190], [204, 215], [206, 231], [232, 223], [200, 250], [165, 233]]}" + } + ], + "images": "RH20T_cfg3_task_0018_user_0010_scene_0003_cfg_0003_038522062288#0", + "gt": "[[236, 129], [209, 141], [240, 147], [231, 146], [206, 190], [204, 215], [206, 231], [232, 223], [200, 250], [165, 233]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "47445_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the marker from the box and place it on the table', and now you are performing subtask 'remove the marker from the box and place it on the table.'\nYou begin at [132, 82]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[132, 82], [152, 79], [171, 87], [166, 88], [189, 105], [191, 116], [185, 108], [184, 88], [173, 94], [180, 112]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/47445_exterior_image_2_left#0.jpg", + "gt": "[[132, 82], [152, 79], [171, 87], [166, 88], [189, 105], [191, 116], [185, 108], [184, 88], [173, 94], [180, 112]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0089_user_0014_scene_0001_cfg_0004_104122062823#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'push an object with obstacles', and now you are performing subtask 'push the block upward.'\nThe trajectory starts at [454, 109]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[454, 109], [458, 111], [460, 113], [460, 115], [458, 113], [452, 103], [450, 102], [445, 96], [445, 95], [451, 93]]}" + } + ], + "images": "RH20T_cfg4_task_0089_user_0014_scene_0001_cfg_0004_104122062823#260", + "gt": "[[454, 109], [458, 111], [460, 113], [460, 115], [458, 113], [452, 103], [450, 102], [445, 96], [445, 95], [451, 93]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "19989_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close the box', and now you are performing subtask 'close the box.'\nYou start from [179, 45]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[179, 45], [225, 89], [219, 118], [181, 131], [183, 119], [169, 119], [176, 87], [184, 118], [171, 121], [180, 97]]}" + } + ], + "images": "19989_exterior_image_2_left#0", + "gt": "[[179, 45], [225, 89], [219, 118], [181, 131], [183, 119], [169, 119], [176, 87], [184, 118], [171, 121], [180, 97]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "46993_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'rotate the rod', and now you are performing subtask 'rotate the rod.'\nThe trajectory starts at [173.5, 63.0]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[173.5, 63.0], [186.5, 78.0], [183.5, 97.0], [191.5, 100.0], [188.5, 101.0], [191.5, 104.0], [195.5, 96.0], [196.5, 100.0], [188.5, 99.0], [181.5, 81.0]]}" + } + ], + "images": "46993_exterior_image_1_left#0", + "gt": "[[173.5, 63.0], [186.5, 78.0], [183.5, 97.0], [191.5, 100.0], [188.5, 101.0], [191.5, 104.0], [195.5, 96.0], [196.5, 100.0], [188.5, 99.0], [181.5, 81.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0094_user_0007_scene_0009_cfg_0005_036422060215#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open a box', and now you are performing subtask 'press the cardboard box on the side.'\nWith start location [287, 132], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[287, 132], [286, 133], [282, 128], [271, 105], [260, 92], [253, 107], [256, 97], [258, 96], [279, 116], [286, 120]]}" + } + ], + "images": "RH20T_cfg5_task_0094_user_0007_scene_0009_cfg_0005_036422060215#430", + "gt": "[[287, 132], [286, 133], [282, 128], [271, 105], [260, 92], [253, 107], [256, 97], [258, 96], [279, 116], [286, 120]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0037_user_0016_scene_0002_cfg_0004_036422060909#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'place the first block on the second block, pick up the third block on the surface.'\nStart at [293, 120]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[293, 120], [283, 118], [282, 115], [282, 109], [292, 94], [297, 98], [299, 105], [298, 111], [293, 112], [345, 128]]}" + } + ], + "images": "RH20T_cfg4_task_0037_user_0016_scene_0002_cfg_0004_036422060909#104", + "gt": "[[293, 120], [283, 118], [282, 115], [282, 109], [292, 94], [297, 98], [299, 105], [298, 111], [293, 112], [345, 128]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "89978_exterior_image_2_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'arrange the water bottles in a straight line', and now you are performing subtask 'place the fourth bottle of water in the specified position in a straight line.'\nStart at [209, 126]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[209, 126], [196, 116], [189, 129], [192, 121], [185, 120], [186, 128], [189, 132], [201, 134], [197, 123], [200, 108]]}" + } + ], + "images": "89978_exterior_image_2_left#352", + "gt": "[[209, 126], [196, 116], [189, 129], [192, 121], [185, 120], [186, 128], [189, 132], [201, 134], [197, 123], [200, 108]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "86744_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the button of the toaster', and now you are performing subtask 'press the button of the toaster.'\nStarting at [0, 0], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[0, 0], [77, 25], [98, 37], [115, 52], [130, 58], [149, 86], [149, 81], [146, 82], [126, 68], [79, 53]]}" + } + ], + "images": "86744_exterior_image_1_left#0", + "gt": "[[0, 0], [77, 25], [98, 37], [115, 52], [130, 58], [149, 86], [149, 81], [146, 82], [126, 68], [79, 53]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0015_user_0007_scene_0006_cfg_0005_104422070044#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'play the drum', and now you are performing subtask 'play the drum.'\nThe trajectory starts at [375, 134]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[375, 134], [386, 122], [435, 156], [447, 123], [456, 122], [443, 115], [425, 124], [423, 134], [444, 150], [409, 124]]}" + } + ], + "images": "RH20T_cfg5_task_0015_user_0007_scene_0006_cfg_0005_104422070044#0", + "gt": "[[375, 134], [386, 122], [435, 156], [447, 123], [456, 122], [443, 115], [425, 124], [423, 134], [444, 150], [409, 124]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0038_user_0014_scene_0004_cfg_0001_035622060973#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the cup', and now you are performing subtask 'pick up the cup.'\nThe trajectory starts at [246, 130]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[246, 130], [247, 136], [259, 152], [285, 171], [299, 195], [311, 200], [309, 206], [299, 174], [276, 130], [282, 110]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0038_user_0014_scene_0004_cfg_0001_035622060973#0.jpg", + "gt": "[[246, 130], [247, 136], [259, 152], [285, 171], [299, 195], [311, 200], [309, 206], [299, 174], [276, 130], [282, 110]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "79230_exterior_image_2_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the green bottle to the right of the silver bowl', and now you are performing subtask 'place the green bottle on the right side of the silver basin.'\nFrom start point [155, 69], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[155, 69], [136, 69], [169, 50], [182, 31], [173, 20], [189, 11], [202, 24], [206, 53], [210, 47], [210, 47]]}" + } + ], + "images": "79230_exterior_image_2_left#109", + "gt": "[[155, 69], [136, 69], [169, 50], [182, 31], [173, 20], [189, 11], [202, 24], [206, 53], [210, 47], [210, 47]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "12219_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the marker from the table then put it into the red cup then take it out of the red cup and put it back on the table', and now you are performing subtask 'take the marker from the table then put it into the red cup then take it out of the red cup and put it back on the table.'\nYour starting position is [209, 37]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[209, 37], [157, 71], [151, 116], [179, 84], [171, 75], [186, 80], [178, 97], [191, 86], [175, 86], [165, 106]]}" + } + ], + "images": "12219_exterior_image_2_left#0", + "gt": "[[209, 37], [157, 71], [151, 116], [179, 84], [171, 75], [186, 80], [178, 97], [191, 86], [175, 86], [165, 106]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0005_user_0010_scene_0004_cfg_0004_104422070011#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'approach and touch the side of the small block', and now you are performing subtask 'approach and touch the side of the small block.'\nStarting at [338, 103], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[338, 103], [343, 161], [321, 147], [336, 152], [275, 173], [242, 194], [253, 202], [297, 179], [303, 178], [301, 184]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg4_task_0005_user_0010_scene_0004_cfg_0004_104422070011#0.jpg", + "gt": "[[338, 103], [343, 161], [321, 147], [336, 152], [275, 173], [242, 194], [253, 202], [297, 179], [303, 178], [301, 184]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "86672_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pour the contents of the orange cup into the grey bowl', and now you are performing subtask 'pour the contents of the orange cup into the grey bowl.'\nStarting at [186, 99], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[186, 99], [173, 106], [171, 108], [171, 111], [169, 112], [155, 92], [140, 92], [134, 78], [132, 67], [136, 75]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/86672_exterior_image_1_left#0.jpg", + "gt": "[[186, 99], [173, 106], [171, 108], [171, 111], [169, 112], [155, 92], [140, 92], [134, 78], [132, 67], [136, 75]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0003_user_0010_scene_0005_cfg_0005_104122063678#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press three buttons from left to right in sequence', and now you are performing subtask 'press the red button in the middle, press the yellow button on the left.'\nStarting at [338, 196], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[338, 196], [340, 164], [315, 124], [329, 140], [317, 146], [324, 148], [335, 130], [364, 163], [351, 118], [349, 141]]}" + } + ], + "images": "RH20T_cfg5_task_0003_user_0010_scene_0005_cfg_0005_104122063678#358", + "gt": "[[338, 196], [340, 164], [315, 124], [329, 140], [317, 146], [324, 148], [335, 130], [364, 163], [351, 118], [349, 141]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "57351_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close the top drawer of the white file cabinet', and now you are performing subtask 'close the top drawer of the white file cabinet.'\nFrom start point [250, 180], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[250, 180], [244, 164], [237, 133], [229, 122], [217, 115], [195, 109], [181, 102], [166, 101], [149, 95], [140, 96]]}" + } + ], + "images": "57351_exterior_image_1_left#0", + "gt": "[[250, 180], [244, 164], [237, 133], [229, 122], [217, 115], [195, 109], [181, 102], [166, 101], [149, 95], [140, 96]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0103_user_0007_scene_0002_cfg_0005_104422070044#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'slide the plate into the goal post', and now you are performing subtask 'slide the plate into the goal post.'\nYour starting position is [374, 132]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[374, 132], [390, 128], [400, 174], [418, 181], [441, 177], [439, 182], [463, 186], [445, 172], [458, 175], [430, 163]]}" + } + ], + "images": "RH20T_cfg5_task_0103_user_0007_scene_0002_cfg_0005_104422070044#0", + "gt": "[[374, 132], [390, 128], [400, 174], [418, 181], [441, 177], [439, 182], [463, 186], [445, 172], [458, 175], [430, 163]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0057_user_0007_scene_0002_cfg_0005_037522062165#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press a row of four power strip buttons to turn on the power strips', and now you are performing subtask 'press the first button on the power socket, press the second button on the power socket.'\nStarting at [299, 229], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[299, 229], [290, 227], [289, 228], [285, 228], [284, 229], [285, 232], [284, 232], [286, 223], [285, 221], [281, 221]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0057_user_0007_scene_0002_cfg_0005_037522062165#419.jpg", + "gt": "[[299, 229], [290, 227], [289, 228], [285, 228], [284, 229], [285, 232], [284, 232], [286, 223], [285, 221], [281, 221]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0105_user_0020_scene_0001_cfg_0006_104122060811#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the object on the shelf', and now you are performing subtask 'pick up the bottle on the table, transfer the object from the table to the shelf, place the bottle on the shelf.'\nWith start location [385, 127], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[385, 127], [380, 123], [330, 130], [324, 124], [323, 132], [333, 116], [369, 87], [405, 80], [410, 74], [443, 63]]}" + } + ], + "images": "RH20T_cfg6_task_0105_user_0020_scene_0001_cfg_0006_104122060811#0", + "gt": "[[385, 127], [380, 123], [330, 130], [324, 124], [323, 132], [333, 116], [369, 87], [405, 80], [410, 74], [443, 63]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "54774_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the mug to the right', and now you are performing subtask 'move the mug to the right.'\nStarting at [203, 46], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[203, 46], [136, 94], [141, 96], [127, 105], [129, 114], [131, 92], [154, 81], [156, 91], [153, 82], [153, 82]]}" + } + ], + "images": "54774_exterior_image_2_left#0", + "gt": "[[203, 46], [136, 94], [141, 96], [127, 105], [129, 114], [131, 92], [154, 81], [156, 91], [153, 82], [153, 82]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "79403_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the cauliflower, red ball, and light blue object into the silver bowl', and now you are performing subtask 'pick up the red ball from the blue bowl.'\nWith start location [143, 16], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[143, 16], [190, 51], [210, 80], [211, 105], [212, 79], [173, 55], [156, 84], [190, 70], [204, 84], [197, 96]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/79403_exterior_image_1_left#0.jpg", + "gt": "[[143, 16], [190, 51], [210, 80], [211, 105], [212, 79], [173, 55], [156, 84], [190, 70], [204, 84], [197, 96]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "16560_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'wipe the left side of the table with the green towel', and now you are performing subtask 'wipe the left side of the table with the green towel.'\nYour starting position is [220, 0]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[220, 0], [212, 48], [218, 50], [170, 94], [165, 113], [158, 93], [190, 105], [175, 84], [187, 114], [175, 90]]}" + } + ], + "images": "16560_exterior_image_2_left#0", + "gt": "[[220, 0], [212, 48], [218, 50], [170, 94], [165, 113], [158, 93], [190, 105], [175, 84], [187, 114], [175, 90]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "28802_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'switch the extension cord on', and now you are performing subtask 'press the switch of the extension cord to the \"on\" position.'\nBegin at [157, 1] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[157, 1], [163, 42], [162, 39], [150, 55], [138, 61], [111, 64], [109, 67], [111, 62], [115, 62], [110, 62]]}" + } + ], + "images": "28802_exterior_image_2_left#0", + "gt": "[[157, 1], [163, 42], [162, 39], [150, 55], [138, 61], [111, 64], [109, 67], [111, 62], [115, 62], [110, 62]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0037_user_0020_scene_0006_cfg_0007_104122060811#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'transfer the first block from the table to above the second block, pick up the third block from the table, transfer the third block from the table to above the first block.'\nWith start location [358, 121], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[358, 121], [374, 114], [380, 117], [381, 123], [377, 129], [380, 123], [379, 115], [370, 111], [358, 113], [360, 117]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg7_task_0037_user_0020_scene_0006_cfg_0007_104122060811#189.jpg", + "gt": "[[358, 121], [374, 114], [380, 117], [381, 123], [377, 129], [380, 123], [379, 115], [370, 111], [358, 113], [360, 117]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "20196_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'arrange the cushions in front of the armrest', and now you are performing subtask 'pick up the second cushion on the sofa.'\nBegin at [214, 80] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[214, 80], [198, 80], [184, 89], [185, 97], [178, 103], [184, 124], [211, 100], [191, 97], [166, 103], [166, 103]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/20196_exterior_image_1_left#0.jpg", + "gt": "[[214, 80], [198, 80], [184, 89], [185, 97], [178, 103], [184, 124], [211, 100], [191, 97], [166, 103], [166, 103]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0070_user_0014_scene_0008_cfg_0001_035622060973#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open a sliding window', and now you are performing subtask 'open a sliding window.'\nStarting at [247, 130], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[247, 130], [229, 149], [226, 174], [223, 171], [217, 182], [215, 168], [231, 168], [253, 160], [253, 164], [255, 163]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0070_user_0014_scene_0008_cfg_0001_035622060973#0.jpg", + "gt": "[[247, 130], [229, 149], [226, 174], [223, 171], [217, 182], [215, 168], [231, 168], [253, 160], [253, 164], [255, 163]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0034_user_0014_scene_0007_cfg_0007_104122064161#TrajectoryPrediction_Task#10", + "task": "TrajectoryPrediction_Task", + "p_index": 10, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the squares into a pyramid shape', and now you are performing subtask 'place the fifth block on top of the right block, pick up the sixth block from the desktop, transfer the sixth block from the desktop to the top of the right block, place the sixth block on top of the right block.'\nWith start location [378, 273], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[378, 273], [390, 219], [356, 174], [330, 175], [356, 180], [356, 200], [371, 208], [367, 257], [373, 206], [344, 172]]}" + } + ], + "images": "RH20T_cfg7_task_0034_user_0014_scene_0007_cfg_0007_104122064161#682", + "gt": "[[378, 273], [390, 219], [356, 174], [330, 175], [356, 180], [356, 200], [371, 208], [367, 257], [373, 206], [344, 172]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "90585_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn off the faucet of the sink', and now you are performing subtask 'turn off the faucet of the sink.'\nYour starting position is [192, 53]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[192, 53], [203, 57], [217, 39], [216, 55], [225, 51], [218, 66], [224, 50], [216, 60], [219, 47], [194, 34]]}" + } + ], + "images": "90585_exterior_image_2_left#0", + "gt": "[[192, 53], [203, 57], [217, 39], [216, 55], [225, 51], [218, 66], [224, 50], [216, 60], [219, 47], [194, 34]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0037_user_0016_scene_0009_cfg_0001_038522062547#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'pick up the first block from the desktop, transfer the first block from the desktop to the second position above the first block, place the first block on top of the second position.'\nFrom start point [405, 133], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[405, 133], [423, 136], [440, 172], [467, 183], [469, 195], [477, 200], [461, 207], [458, 147], [451, 139], [442, 140]]}" + } + ], + "images": "RH20T_cfg1_task_0037_user_0016_scene_0009_cfg_0001_038522062547#0", + "gt": "[[405, 133], [423, 136], [440, 172], [467, 183], [469, 195], [477, 200], [461, 207], [458, 147], [451, 139], [442, 140]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg2_task_0065_user_0007_scene_0003_cfg_0002_104122063678#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with small Lego blocks for the nth time with n blocks', and now you are performing subtask 'pick up the pink Lego block from the table, transfer the pink Lego block from the table to the Lego base, place the pink Lego block on the Lego base.'\nThe trajectory starts at [400, 190]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[400, 190], [451, 212], [469, 229], [531, 250], [534, 258], [523, 261], [530, 245], [513, 238], [480, 238], [469, 259]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg2_task_0065_user_0007_scene_0003_cfg_0002_104122063678#0.jpg", + "gt": "[[400, 190], [451, 212], [469, 229], [531, 250], [534, 258], [523, 261], [530, 245], [513, 238], [480, 238], [469, 259]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0037_user_0014_scene_0002_cfg_0007_104122063633#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'pick up the fourth block from the tabletop, transfer the fourth block from the tabletop to the third block, place the fourth block on the third block.'\nWith start location [177, 162], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[177, 162], [160, 178], [157, 197], [162, 200], [184, 134], [203, 126], [220, 136], [204, 123], [180, 140], [171, 154]]}" + } + ], + "images": "RH20T_cfg7_task_0037_user_0014_scene_0002_cfg_0007_104122063633#267", + "gt": "[[177, 162], [160, 178], [157, 197], [162, 200], [184, 134], [203, 126], [220, 136], [204, 123], [180, 140], [171, 154]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "42662_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'fold the green cloth diagonally and then move the can forward', and now you are performing subtask 'place the can in the designated position.'\nYou begin at [128, 73]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[128, 73], [139, 72], [146, 80], [129, 72], [115, 72], [103, 76], [101, 82], [100, 74], [91, 69], [97, 71]]}" + } + ], + "images": "42662_exterior_image_1_left#134", + "gt": "[[128, 73], [139, 72], [146, 80], [129, 72], [115, 72], [103, 76], [101, 82], [100, 74], [91, 69], [97, 71]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg3_task_0003_user_0016_scene_0005_cfg_0003_104122062823#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press three buttons in sequence', and now you are performing subtask 'press the green button on the yellow and white base.'\nStarting at [242, 0], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[242, 0], [308, 2], [326, 12], [344, 28], [359, 52], [370, 80], [347, 106], [366, 111], [345, 102], [340, 103]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg3_task_0003_user_0016_scene_0005_cfg_0003_104122062823#0.jpg", + "gt": "[[242, 0], [308, 2], [326, 12], [344, 28], [359, 52], [370, 80], [347, 106], [366, 111], [345, 102], [340, 103]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg3_task_0035_user_0010_scene_0001_cfg_0003_104122062823#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up a small block', and now you are performing subtask 'pick up a small block.'\nYou start from [197, 41]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[197, 41], [182, 86], [208, 86], [178, 90], [236, 79], [323, 87], [317, 95], [346, 137], [311, 191], [337, 129]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg3_task_0035_user_0010_scene_0001_cfg_0003_104122062823#0.jpg", + "gt": "[[197, 41], [182, 86], [208, 86], [178, 90], [236, 79], [323, 87], [317, 95], [346, 137], [311, 191], [337, 129]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0061_user_0020_scene_0003_cfg_0007_037522061512#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take everything out of the gift box', and now you are performing subtask 'pick up the lid on the container, transfer the lid from the container to the table, place the lid on the table.'\nWith start location [261, 86], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[261, 86], [235, 109], [213, 155], [206, 137], [195, 141], [194, 167], [162, 199], [172, 228], [172, 179], [195, 157]]}" + } + ], + "images": "RH20T_cfg7_task_0061_user_0020_scene_0003_cfg_0007_037522061512#0", + "gt": "[[261, 86], [235, 109], [213, 155], [206, 137], [195, 141], [194, 167], [162, 199], [172, 228], [172, 179], [195, 157]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0014_user_0014_scene_0001_cfg_0001_038522062547#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the block from the scale', and now you are performing subtask 'remove the block from the scale.'\nFrom start point [406, 137], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[406, 137], [417, 124], [413, 123], [417, 123], [410, 113], [412, 80], [403, 102], [407, 96], [408, 110], [399, 160]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0014_user_0014_scene_0001_cfg_0001_038522062547#0.jpg", + "gt": "[[406, 137], [417, 124], [413, 123], [417, 123], [410, 113], [412, 80], [403, 102], [407, 96], [408, 110], [399, 160]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0105_user_0020_scene_0007_cfg_0006_104122063633#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the object on the shelf', and now you are performing subtask 'place the object at the specified location, pick up the object from the tabletop, transfer the object from the tabletop to the specified location, place the object at the specified location.'\nThe trajectory starts at [215, 226]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[215, 226], [169, 170], [174, 141], [159, 132], [154, 151], [144, 144], [130, 255], [128, 167], [176, 134], [176, 134]]}" + } + ], + "images": "RH20T_cfg6_task_0105_user_0020_scene_0007_cfg_0006_104122063633#651", + "gt": "[[215, 226], [169, 170], [174, 141], [159, 132], [154, 151], [144, 144], [130, 255], [128, 167], [176, 134], [176, 134]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0094_user_0001_scene_0009_cfg_0001_038522062547#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open a box', and now you are performing subtask 'pull the lid of the box upwards to open the box.'\nYou start from [423, 296]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[423, 296], [378, 261], [363, 270], [355, 237], [343, 237], [369, 276], [354, 230], [318, 218], [371, 248], [384, 175]]}" + } + ], + "images": "RH20T_cfg1_task_0094_user_0001_scene_0009_cfg_0001_038522062547#466", + "gt": "[[423, 296], [378, 261], [363, 270], [355, 237], [343, 237], [369, 276], [354, 230], [318, 218], [371, 248], [384, 175]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0034_user_0007_scene_0006_cfg_0005_104122063678#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the squares into a line', and now you are performing subtask 'place the second block beside the first block, pick up the third block from the table, transfer the third block from the table to beside the first block, place the third block beside the first block.'\nWith start location [341, 209], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[341, 209], [348, 198], [406, 244], [424, 283], [423, 293], [379, 259], [357, 261], [356, 258], [366, 248], [424, 240]]}" + } + ], + "images": "RH20T_cfg5_task_0034_user_0007_scene_0006_cfg_0005_104122063678#597", + "gt": "[[341, 209], [348, 198], [406, 244], [424, 283], [423, 293], [379, 259], [357, 261], [356, 258], [366, 248], [424, 240]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "88471_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'fold the grey towel from the right to the left', and now you are performing subtask 'fold the grey towel from the right to the left.'\nStart at [299, 53]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[299, 53], [275, 45], [235, 92], [238, 50], [219, 54], [213, 64], [227, 81], [206, 101], [207, 65], [207, 65]]}" + } + ], + "images": "88471_exterior_image_1_left#0", + "gt": "[[299, 53], [275, 45], [235, 92], [238, 50], [219, 54], [213, 64], [227, 81], [206, 101], [207, 65], [207, 65]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0051_user_0015_scene_0002_cfg_0001_038522063145#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the dish off the dish rack', and now you are performing subtask 'take the dish off the dish rack.'\nYou start from [443, 98]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[443, 98], [503, 108], [480, 122], [486, 105], [473, 103], [468, 66], [421, 35], [381, 26], [357, 46], [411, 69]]}" + } + ], + "images": "RH20T_cfg1_task_0051_user_0015_scene_0002_cfg_0001_038522063145#0", + "gt": "[[443, 98], [503, 108], [480, 122], [486, 105], [473, 103], [468, 66], [421, 35], [381, 26], [357, 46], [411, 69]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "24218_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the towel to the right then wipe the countertop', and now you are performing subtask 'move the towel to the right then wipe the countertop.'\nBegin at [314.0, 32.5] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[314.0, 32.5], [202.0, 96.5], [158.0, 147.5], [214.0, 113.5], [215.0, 93.5], [209.0, 115.5], [150.0, 126.5], [206.0, 110.5], [191.0, 100.5], [242.0, 63.5]]}" + } + ], + "images": "24218_exterior_image_1_left#0", + "gt": "[[314.0, 32.5], [202.0, 96.5], [158.0, 147.5], [214.0, 113.5], [215.0, 93.5], [209.0, 115.5], [150.0, 126.5], [206.0, 110.5], [191.0, 100.5], [242.0, 63.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0118_user_0007_scene_0010_cfg_0005_104122061850#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn on the water tap', and now you are performing subtask 'turn on the water tap.'\nFrom start point [311, 50], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[311, 50], [330, 61], [376, 105], [397, 144], [415, 162], [423, 160], [431, 140], [398, 126], [376, 126], [342, 83]]}" + } + ], + "images": "RH20T_cfg5_task_0118_user_0007_scene_0010_cfg_0005_104122061850#0", + "gt": "[[311, 50], [330, 61], [376, 105], [397, 144], [415, 162], [423, 160], [431, 140], [398, 126], [376, 126], [342, 83]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "58537_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the blue clip from the upper hook on the wooden stand and place it on the lower hook', and now you are performing subtask 'remove the blue clip from the upper hook on the wooden stand and place it on the lower hook.'\nBegin at [296.0, 102.0] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[296.0, 102.0], [236.0, 82.0], [224.0, 86.0], [221.0, 96.0], [217.0, 94.0], [222.0, 92.0], [215.0, 99.0], [214.0, 114.0], [236.0, 105.0], [237.0, 87.0]]}" + } + ], + "images": "58537_exterior_image_1_left#0", + "gt": "[[296.0, 102.0], [236.0, 82.0], [224.0, 86.0], [221.0, 96.0], [217.0, 94.0], [222.0, 92.0], [215.0, 99.0], [214.0, 114.0], [236.0, 105.0], [237.0, 87.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0034_user_0016_scene_0009_cfg_0004_104122062823#TrajectoryPrediction_Task#8", + "task": "TrajectoryPrediction_Task", + "p_index": 8, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the squares into a pyramid shape', and now you are performing subtask 'place the second block on top of the three blocks, pick up the third block on the cardboard.'\nYou start from [365, 86]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[365, 86], [373, 78], [382, 73], [403, 71], [428, 63], [430, 67], [425, 77], [416, 84], [401, 89], [416, 84]]}" + } + ], + "images": "RH20T_cfg4_task_0034_user_0016_scene_0009_cfg_0004_104122062823#294", + "gt": "[[365, 86], [373, 78], [382, 73], [403, 71], [428, 63], [430, 67], [425, 77], [416, 84], [401, 89], [416, 84]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "74509_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the peg from the table and hang it on the black stand', and now you are performing subtask 'take the peg from the table and hang it on the black stand.'\nYou start from [139, 79]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[139, 79], [142, 91], [166, 103], [180, 129], [198, 143], [201, 105], [179, 97], [186, 94], [186, 82], [170, 85]]}" + } + ], + "images": "74509_exterior_image_2_left#0", + "gt": "[[139, 79], [142, 91], [166, 103], [180, 129], [198, 143], [201, 105], [179, 97], [186, 94], [186, 82], [170, 85]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0057_user_0014_scene_0008_cfg_0004_038522062288#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn on the power strips', and now you are performing subtask 'press the button on the second power strip.'\nFrom start point [281, 154], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[281, 154], [281, 155], [280, 156], [274, 158], [274, 160], [275, 160], [276, 157], [276, 150], [275, 148], [275, 148]]}" + } + ], + "images": "RH20T_cfg4_task_0057_user_0014_scene_0008_cfg_0004_038522062288#150", + "gt": "[[281, 154], [281, 155], [280, 156], [274, 158], [274, 160], [275, 160], [276, 157], [276, 150], [275, 148], [275, 148]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "30710_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the white cloth from the glass panel', and now you are performing subtask 'remove the white cloth from the glass panel.'\nYou start from [206, 48]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[206, 48], [193, 46], [182, 39], [168, 27], [165, 23], [166, 18], [159, 24], [153, 38], [145, 38], [182, 84]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/30710_exterior_image_1_left#0.jpg", + "gt": "[[206, 48], [193, 46], [182, 39], [168, 27], [165, 23], [166, 18], [159, 24], [153, 38], [145, 38], [182, 84]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "81486_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn off the second switch from the left of the power socket', and now you are performing subtask 'turn off the second switch from the left of the power socket.'\nYou start from [155.5, 12.0]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[155.5, 12.0], [159.5, 31.0], [174.5, 52.0], [175.5, 63.0], [178.5, 63.0], [179.5, 74.0], [183.5, 81.0], [180.5, 88.0], [184.5, 92.0], [172.5, 81.0]]}" + } + ], + "images": "81486_exterior_image_1_left#0", + "gt": "[[155.5, 12.0], [159.5, 31.0], [174.5, 52.0], [175.5, 63.0], [178.5, 63.0], [179.5, 74.0], [183.5, 81.0], [180.5, 88.0], [184.5, 92.0], [172.5, 81.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "8718_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the box', and now you are performing subtask 'pick up the lid on the box.'\nYour initial coordinate is [106, 0]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[106, 0], [103, 31], [95, 23], [95, 29], [124, 105], [120, 125], [107, 112], [108, 107], [121, 107], [121, 107]]}" + } + ], + "images": "8718_exterior_image_1_left#0", + "gt": "[[106, 0], [103, 31], [95, 23], [95, 29], [124, 105], [120, 125], [107, 112], [108, 107], [121, 107], [121, 107]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0061_user_0020_scene_0002_cfg_0007_104122061018#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take everything out of the gift box', and now you are performing subtask 'place the object on the tabletop, pick up the object in the box, transfer the object from the box to the tabletop, place the object on the tabletop.'\nWith start location [262, 103], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[262, 103], [265, 78], [287, 103], [288, 117], [282, 146], [283, 129], [292, 104], [280, 66], [272, 54], [270, 61]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg7_task_0061_user_0020_scene_0002_cfg_0007_104122061018#374.jpg", + "gt": "[[262, 103], [265, 78], [287, 103], [288, 117], [282, 146], [283, 129], [292, 104], [280, 66], [272, 54], [270, 61]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "20551_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the marker from the desk and put it into the pot', and now you are performing subtask 'pick up the marker from the desk and put it into the pot.'\nWith start location [72.0, 17.0], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[72.0, 17.0], [97.0, 39.0], [179.0, 68.0], [205.0, 105.0], [196.0, 108.0], [197.0, 78.0], [187.0, 50.0], [162.0, 64.0], [168.0, 85.0], [164.0, 70.0]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/20551_exterior_image_1_left#0.jpg", + "gt": "[[72.0, 17.0], [97.0, 39.0], [179.0, 68.0], [205.0, 105.0], [196.0, 108.0], [197.0, 78.0], [187.0, 50.0], [162.0, 64.0], [168.0, 85.0], [164.0, 70.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "45040_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the drawer and put some of the plush toys in the drawer and close it', and now you are performing subtask 'pull the drawer handle to open the drawer.'\nYou start from [217.5, 25.5]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[217.5, 25.5], [186.5, 21.5], [179.5, 39.5], [146.5, 45.5], [152.5, 60.5], [136.5, 73.5], [173.5, 75.5], [147.5, 49.5], [136.5, 69.5], [158.5, 55.5]]}" + } + ], + "images": "45040_exterior_image_1_left#0", + "gt": "[[217.5, 25.5], [186.5, 21.5], [179.5, 39.5], [146.5, 45.5], [152.5, 60.5], [136.5, 73.5], [173.5, 75.5], [147.5, 49.5], [136.5, 69.5], [158.5, 55.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "88961_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'place the hamburger plush toy on the left side of the table, stand the pear plush toy upright, then place the strawberry plush toy on the tray', and now you are performing subtask 'stand the pear plush toy upright on the tabletop.'\nStarting at [181, 66], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[181, 66], [193, 52], [205, 65], [197, 69], [206, 54], [197, 47], [197, 60], [211, 61], [206, 65], [203, 61]]}" + } + ], + "images": "88961_exterior_image_1_left#201", + "gt": "[[181, 66], [193, 52], [205, 65], [197, 69], [206, 54], [197, 47], [197, 60], [211, 61], [206, 65], [203, 61]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "15475_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the can on the counter from the sink', and now you are performing subtask 'put the can on the counter from the sink.'\nYour starting position is [188, 81]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[188, 81], [239, 82], [238, 116], [231, 118], [234, 131], [228, 130], [221, 109], [205, 115], [204, 128], [205, 104]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/15475_exterior_image_2_left#0.jpg", + "gt": "[[188, 81], [239, 82], [238, 116], [231, 118], [234, 131], [228, 130], [221, 109], [205, 115], [204, 128], [205, 104]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "17981_exterior_image_2_left#TrajectoryPrediction_Task#14", + "task": "TrajectoryPrediction_Task", + "p_index": 14, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the orange cloth', and now you are performing subtask 'fold the cloth on the table for the last time.'\nBegin at [203, 132] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[203, 132], [207, 132], [217, 138], [220, 143], [226, 147], [199, 140], [201, 139], [207, 141], [208, 139], [206, 135]]}" + } + ], + "images": "17981_exterior_image_2_left#395", + "gt": "[[203, 132], [207, 132], [217, 138], [220, 143], [226, 147], [199, 140], [201, 139], [207, 141], [208, 139], [206, 135]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "45684_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the pen from inside the mug and place it on the desk', and now you are performing subtask 'remove the pen from inside the mug and place it on the desk.'\nWith start location [110.5, 15.5], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[110.5, 15.5], [135.5, 65.5], [136.5, 84.5], [156.5, 131.5], [168.5, 87.5], [154.5, 91.5], [154.5, 117.5], [160.5, 111.5], [151.5, 88.5], [144.5, 84.5]]}" + } + ], + "images": "45684_exterior_image_1_left#0", + "gt": "[[110.5, 15.5], [135.5, 65.5], [136.5, 84.5], [156.5, 131.5], [168.5, 87.5], [154.5, 91.5], [154.5, 117.5], [160.5, 111.5], [151.5, 88.5], [144.5, 84.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0073_user_0020_scene_0003_cfg_0006_104122060811#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the things in the drawer', and now you are performing subtask 'pull the drawer to the open position, pick up the cube on the table.'\nThe trajectory starts at [385, 127]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[385, 127], [367, 133], [349, 131], [334, 141], [358, 132], [373, 119], [392, 117], [396, 111], [402, 113], [401, 125]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg6_task_0073_user_0020_scene_0003_cfg_0006_104122060811#0.jpg", + "gt": "[[385, 127], [367, 133], [349, 131], [334, 141], [358, 132], [373, 119], [392, 117], [396, 111], [402, 113], [401, 125]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "2876_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the black block on the green block', and now you are performing subtask 'put the black block on the green block.'\nStarting at [78, 93], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[78, 93], [99, 106], [100, 121], [96, 126], [94, 125], [93, 121], [99, 104], [107, 95], [106, 105], [101, 108]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/2876_exterior_image_2_left#0.jpg", + "gt": "[[78, 93], [99, 106], [100, 121], [96, 126], [94, 125], [93, 121], [99, 104], [107, 95], [106, 105], [101, 108]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "57236_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the clear lid on the white plate', and now you are performing subtask 'put the clear lid on the white plate.'\nYour starting position is [196, 0]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[196, 0], [190, 29], [220, 72], [217, 93], [205, 102], [206, 95], [210, 113], [204, 115], [203, 92], [196, 92]]}" + } + ], + "images": "57236_exterior_image_2_left#0", + "gt": "[[196, 0], [190, 29], [220, 72], [217, 93], [205, 102], [206, 95], [210, 113], [204, 115], [203, 92], [196, 92]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "71119_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the bulbs of garlic from the glass bowl and place them on the countertop', and now you are performing subtask 'place the bulb of garlic on the countertop.'\nYour starting position is [242, 117]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[242, 117], [229, 124], [240, 119], [240, 111], [237, 106], [228, 107], [219, 117], [211, 135], [227, 111], [221, 114]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/71119_exterior_image_1_left#319.jpg", + "gt": "[[242, 117], [229, 124], [240, 119], [240, 111], [237, 106], [228, 107], [219, 117], [211, 135], [227, 111], [221, 114]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "79049_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the spoon from the table and use it to mix the objects in the bowl', and now you are performing subtask 'pick up the spoon from the table and use it to mix the objects in the bowl.'\nWith start location [171.5, 77.5], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[171.5, 77.5], [195.5, 91.5], [193.5, 115.5], [169.5, 80.5], [158.5, 110.5], [149.5, 105.5], [150.5, 113.5], [164.5, 96.5], [186.5, 104.5], [186.5, 104.5]]}" + } + ], + "images": "79049_exterior_image_1_left#0", + "gt": "[[171.5, 77.5], [195.5, 91.5], [193.5, 115.5], [169.5, 80.5], [158.5, 110.5], [149.5, 105.5], [150.5, 113.5], [164.5, 96.5], [186.5, 104.5], [186.5, 104.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "54874_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the marker in the cup', and now you are performing subtask 'put the marker in the cup.'\nYou begin at [158, 0]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[158, 0], [149, 4], [149, 18], [136, 31], [146, 55], [134, 45], [151, 1], [168, 0], [172, 15], [165, 14]]}" + } + ], + "images": "54874_exterior_image_2_left#0", + "gt": "[[158, 0], [149, 4], [149, 18], [136, 31], [146, 55], [134, 45], [151, 1], [168, 0], [172, 15], [165, 14]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "32511_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the towel', and now you are performing subtask 'pick up the towel.'\nYou begin at [85, 0]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[85, 0], [104, 26], [117, 65], [118, 81], [128, 90], [124, 48], [115, 27], [125, 84], [121, 58], [125, 62]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/32511_exterior_image_1_left#0.jpg", + "gt": "[[85, 0], [104, 26], [117, 65], [118, 81], [128, 90], [124, 48], [115, 27], [125, 84], [121, 58], [125, 62]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0044_user_0010_scene_0008_cfg_0005_036422060215#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up a bag of things', and now you are performing subtask 'pick up a bag of things.'\nYour initial coordinate is [286, 106]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[286, 106], [280, 115], [278, 110], [276, 116], [273, 114], [287, 116], [283, 139], [278, 129], [279, 117], [299, 50]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0044_user_0010_scene_0008_cfg_0005_036422060215#0.jpg", + "gt": "[[286, 106], [280, 115], [278, 110], [276, 116], [273, 114], [287, 116], [283, 139], [278, 129], [279, 117], [299, 50]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0003_user_0010_scene_0001_cfg_0005_104122063678#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press three buttons from left to right in sequence', and now you are performing subtask 'press the red button in the middle, press the green button on the left.'\nYou start from [342, 192]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[342, 192], [342, 189], [338, 193], [339, 196], [341, 196], [338, 194], [343, 176], [343, 160], [338, 159], [331, 142]]}" + } + ], + "images": "RH20T_cfg5_task_0003_user_0010_scene_0001_cfg_0005_104122063678#304", + "gt": "[[342, 192], [342, 189], [338, 193], [339, 196], [341, 196], [338, 194], [343, 176], [343, 160], [338, 159], [331, 142]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "63275_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the white cloth and put it on the table', and now you are performing subtask 'pick up the white cloth and put it on the table.'\nYou start from [230, 32]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[230, 32], [187, 27], [151, 29], [149, 32], [153, 33], [136, 52], [162, 41], [170, 44], [170, 50], [177, 53]]}" + } + ], + "images": "63275_exterior_image_1_left#0", + "gt": "[[230, 32], [187, 27], [151, 29], [149, 32], [153, 33], [136, 52], [162, 41], [170, 44], [170, 50], [177, 53]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0037_user_0016_scene_0009_cfg_0001_038522062547#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'place the third block on top of the second block, pick up the fourth block from the surface, transfer the fourth block from the desktop to the second position above the third block, place the fourth block on top of the third block.'\nYour initial coordinate is [461, 96]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[461, 96], [482, 67], [476, 58], [508, 53], [506, 82], [482, 115], [504, 61], [466, 34], [469, 24], [466, 67]]}" + } + ], + "images": "RH20T_cfg1_task_0037_user_0016_scene_0009_cfg_0001_038522062547#528", + "gt": "[[461, 96], [482, 67], [476, 58], [508, 53], [506, 82], [482, 115], [504, 61], [466, 34], [469, 24], [466, 67]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0038_user_0014_scene_0004_cfg_0001_038522062547#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the cup', and now you are performing subtask 'pick up the cup.'\nBegin at [406, 134] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[406, 134], [410, 124], [407, 93], [383, 60], [379, 44], [366, 49], [370, 63], [379, 68], [388, 57], [375, 53]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0038_user_0014_scene_0004_cfg_0001_038522062547#0.jpg", + "gt": "[[406, 134], [410, 124], [407, 93], [383, 60], [379, 44], [366, 49], [370, 63], [379, 68], [388, 57], [375, 53]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0081_user_0015_scene_0002_cfg_0004_104422070011#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the leg of the glasses (with one hand)', and now you are performing subtask 'pick up the glasses on the table.'\nYou begin at [277, 182]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[277, 182], [272, 186], [266, 186], [262, 188], [268, 188], [265, 188], [271, 190], [289, 185], [285, 190], [282, 191]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg4_task_0081_user_0015_scene_0002_cfg_0004_104422070011#227.jpg", + "gt": "[[277, 182], [272, 186], [266, 186], [262, 188], [268, 188], [265, 188], [271, 190], [289, 185], [285, 190], [282, 191]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "86836_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'fold the towel', and now you are performing subtask 'fold the towel on the table.'\nYou begin at [127, 170]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[127, 170], [125, 179], [112, 180], [123, 138], [125, 110], [124, 117], [134, 121], [134, 126], [138, 117], [135, 111]]}" + } + ], + "images": "86836_exterior_image_1_left#383", + "gt": "[[127, 170], [125, 179], [112, 180], [123, 138], [125, 110], [124, 117], [134, 121], [134, 126], [138, 117], [135, 111]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0033_user_0020_scene_0001_cfg_0007_104122064161#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pushing another small block to the designated position while grasping one small block', and now you are performing subtask 'pushing another small block to the designated position while grasping one small block.'\nFrom start point [337, 115], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[337, 115], [350, 127], [374, 89], [391, 100], [385, 117], [396, 119], [399, 146], [382, 210], [385, 142], [370, 126]]}" + } + ], + "images": "RH20T_cfg7_task_0033_user_0020_scene_0001_cfg_0007_104122064161#0", + "gt": "[[337, 115], [350, 127], [374, 89], [391, 100], [385, 117], [396, 119], [399, 146], [382, 210], [385, 142], [370, 126]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "89777_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'push the faucet to the left', and now you are performing subtask 'push the faucet to the left.'\nYour starting position is [105.5, 15.5]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[105.5, 15.5], [167.5, 67.5], [190.5, 95.5], [191.5, 99.5], [186.5, 92.5], [185.5, 96.5], [191.5, 86.5], [176.5, 87.5], [184.5, 89.5], [179.5, 90.5]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/89777_exterior_image_1_left#0.jpg", + "gt": "[[105.5, 15.5], [167.5, 67.5], [190.5, 95.5], [191.5, 99.5], [186.5, 92.5], [185.5, 96.5], [191.5, 86.5], [176.5, 87.5], [184.5, 89.5], [179.5, 90.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0061_user_0020_scene_0003_cfg_0007_104122064161#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take everything out of the gift box', and now you are performing subtask 'pick up the lid on the container, transfer the lid from the container to the table, place the lid on the table.'\nYour initial coordinate is [337, 115]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[337, 115], [338, 111], [357, 119], [355, 126], [373, 133], [375, 143], [374, 101], [359, 92], [363, 74], [359, 97]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg7_task_0061_user_0020_scene_0003_cfg_0007_104122064161#0.jpg", + "gt": "[[337, 115], [338, 111], [357, 119], [355, 126], [373, 133], [375, 143], [374, 101], [359, 92], [363, 74], [359, 97]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "92217_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the third switch from the right', and now you are performing subtask 'press the third switch from the right.'\nThe trajectory starts at [158.0, 2.0]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[158.0, 2.0], [166.0, 45.0], [169.0, 42.0], [170.0, 44.0], [169.0, 42.0], [164.0, 54.0], [164.0, 61.0], [170.0, 71.0], [168.0, 77.0], [172.0, 82.0]]}" + } + ], + "images": "92217_exterior_image_1_left#0", + "gt": "[[158.0, 2.0], [166.0, 45.0], [169.0, 42.0], [170.0, 44.0], [169.0, 42.0], [164.0, 54.0], [164.0, 61.0], [170.0, 71.0], [168.0, 77.0], [172.0, 82.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "47725_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the button on the kettle', and now you are performing subtask 'press the button on the kettle.'\nWith start location [120, 49], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[120, 49], [133, 53], [148, 71], [148, 81], [142, 86], [134, 86], [135, 89], [129, 93], [132, 110], [123, 90]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/47725_exterior_image_2_left#0.jpg", + "gt": "[[120, 49], [133, 53], [148, 71], [148, 81], [142, 86], [134, 86], [135, 89], [129, 93], [132, 110], [123, 90]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "41219_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the can out of the sink on the left and put it on the countertop', and now you are performing subtask 'take the can out of the sink on the left and put it on the countertop.'\nStart at [230, 72]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[230, 72], [242, 95], [247, 125], [242, 131], [238, 110], [234, 110], [214, 119], [214, 126], [215, 115], [220, 110]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/41219_exterior_image_2_left#0.jpg", + "gt": "[[230, 72], [242, 95], [247, 125], [242, 131], [238, 110], [234, 110], [214, 119], [214, 126], [215, 115], [220, 110]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0058_user_0015_scene_0003_cfg_0001_819112070044#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn off the power strips', and now you are performing subtask 'press the second button on the power socket.'\nWith start location [483, 194], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[483, 194], [483, 196], [481, 199], [483, 198], [482, 201], [483, 201], [483, 198], [485, 193], [484, 192], [474, 191]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0058_user_0015_scene_0003_cfg_0001_819112070044#184.jpg", + "gt": "[[483, 194], [483, 196], [481, 199], [483, 198], [482, 201], [483, 201], [483, 198], [485, 193], [484, 192], [474, 191]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0057_user_0007_scene_0002_cfg_0005_105422061350#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press a row of four power strip buttons to turn on the power strips', and now you are performing subtask 'press the second button on the power socket.'\nFrom start point [263, 141], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[263, 141], [263, 142], [263, 140], [262, 141], [260, 141], [261, 140], [268, 140], [268, 133], [266, 129], [265, 129]]}" + } + ], + "images": "RH20T_cfg5_task_0057_user_0007_scene_0002_cfg_0005_105422061350#493", + "gt": "[[263, 141], [263, 142], [263, 140], [262, 141], [260, 141], [261, 140], [268, 140], [268, 133], [266, 129], [265, 129]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0023_user_0014_scene_0002_cfg_0001_038522062547#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn on the power strip by pressing the button', and now you are performing subtask 'turn on the power strip by pressing the button.'\nYour initial coordinate is [406, 134]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[406, 134], [408, 130], [405, 130], [406, 133], [398, 125], [381, 123], [377, 137], [369, 136], [371, 141], [376, 129]]}" + } + ], + "images": "RH20T_cfg1_task_0023_user_0014_scene_0002_cfg_0001_038522062547#0", + "gt": "[[406, 134], [408, 130], [405, 130], [406, 133], [398, 125], [381, 123], [377, 137], [369, 136], [371, 141], [376, 129]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "52870_exterior_image_1_left#TrajectoryPrediction_Task#8", + "task": "TrajectoryPrediction_Task", + "p_index": 8, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the lemons and an apple out of the glass bowl and place them on the countertop', and now you are performing subtask 'place the apple on the tabletop.'\nThe trajectory starts at [189, 114]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[189, 114], [217, 87], [243, 110], [235, 117], [236, 92], [215, 87], [168, 110], [168, 119], [181, 97], [206, 80]]}" + } + ], + "images": "52870_exterior_image_1_left#467", + "gt": "[[189, 114], [217, 87], [243, 110], [235, 117], [236, 92], [215, 87], [168, 110], [168, 119], [181, 97], [206, 80]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "10380_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the marker from the mug, place it on the table then put it back in the mug', and now you are performing subtask 'pick up the marker from the table.'\nStart at [318.0, 50.0]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[318.0, 50.0], [256.0, 71.0], [232.0, 97.0], [230.0, 79.0], [238.0, 61.0], [255.0, 45.0], [276.0, 49.0], [299.0, 93.0], [287.0, 82.0], [283.0, 104.0]]}" + } + ], + "images": "10380_exterior_image_1_left#0", + "gt": "[[318.0, 50.0], [256.0, 71.0], [232.0, 97.0], [230.0, 79.0], [238.0, 61.0], [255.0, 45.0], [276.0, 49.0], [299.0, 93.0], [287.0, 82.0], [283.0, 104.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0081_user_0010_scene_0001_cfg_0001_038522062547#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the leg of the glasses (with one hand)', and now you are performing subtask 'pull the leg of the glasses outward, pull the other leg of the glasses outward.'\nYou begin at [404, 127]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[404, 127], [398, 115], [380, 131], [382, 120], [378, 120], [373, 131], [376, 118], [392, 97], [370, 108], [395, 88]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0081_user_0010_scene_0001_cfg_0001_038522062547#0.jpg", + "gt": "[[404, 127], [398, 115], [380, 131], [382, 120], [378, 120], [373, 131], [376, 118], [392, 97], [370, 108], [395, 88]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0057_user_0014_scene_0008_cfg_0006_104122061018#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn on the power strips', and now you are performing subtask 'press the first button on the power strip.'\nYou start from [360, 31]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[360, 31], [361, 26], [339, 40], [338, 56], [328, 68], [325, 99], [323, 101], [325, 93], [320, 90], [310, 94]]}" + } + ], + "images": "RH20T_cfg6_task_0057_user_0014_scene_0008_cfg_0006_104122061018#0", + "gt": "[[360, 31], [361, 26], [339, 40], [338, 56], [328, 68], [325, 99], [323, 101], [325, 93], [320, 90], [310, 94]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0061_user_0020_scene_0003_cfg_0007_037522061512#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take everything out of the gift box', and now you are performing subtask 'place the object on the surface, pick up the object in the container, transfer the object from the container to the surface, place the item on the table.'\nYour starting position is [231, 110]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[231, 110], [222, 135], [224, 157], [230, 165], [227, 126], [251, 105], [259, 118], [261, 133], [260, 124], [251, 117]]}" + } + ], + "images": "RH20T_cfg7_task_0061_user_0020_scene_0003_cfg_0007_037522061512#450", + "gt": "[[231, 110], [222, 135], [224, 157], [230, 165], [227, 126], [251, 105], [259, 118], [261, 133], [260, 124], [251, 117]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0025_user_0010_scene_0006_cfg_0005_036422060215#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold a piece of paper that has been folded once (one end is pressed down by a heavy object)', and now you are performing subtask 'unfold a piece of paper that has been folded once (one end is pressed down by a heavy object).'\nYou begin at [286, 108]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[286, 108], [291, 116], [259, 127], [268, 164], [279, 150], [306, 152], [336, 187], [296, 128], [293, 115], [299, 105]]}" + } + ], + "images": "RH20T_cfg5_task_0025_user_0010_scene_0006_cfg_0005_036422060215#0", + "gt": "[[286, 108], [291, 116], [259, 127], [268, 164], [279, 150], [306, 152], [336, 187], [296, 128], [293, 115], [299, 105]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0094_user_0007_scene_0006_cfg_0005_104122063678#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open a box', and now you are performing subtask 'press the part of the box, press the part of the box.'\nBegin at [375, 198] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[375, 198], [369, 203], [359, 204], [353, 185], [344, 181], [332, 185], [321, 197], [335, 188], [345, 186], [362, 197]]}" + } + ], + "images": "RH20T_cfg5_task_0094_user_0007_scene_0006_cfg_0005_104122063678#290", + "gt": "[[375, 198], [369, 203], [359, 204], [353, 185], [344, 181], [332, 185], [321, 197], [335, 188], [345, 186], [362, 197]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "26904_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the orange sharpie in the mug', and now you are performing subtask 'put the orange sharpie in the mug.'\nYour initial coordinate is [134.0, 23.5]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[134.0, 23.5], [173.0, 61.5], [192.0, 99.5], [199.0, 76.5], [194.0, 63.5], [163.0, 58.5], [151.0, 66.5], [152.0, 78.5], [162.0, 72.5], [157.0, 62.5]]}" + } + ], + "images": "26904_exterior_image_1_left#0", + "gt": "[[134.0, 23.5], [173.0, 61.5], [192.0, 99.5], [199.0, 76.5], [194.0, 63.5], [163.0, 58.5], [151.0, 66.5], [152.0, 78.5], [162.0, 72.5], [157.0, 62.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0082_user_0007_scene_0004_cfg_0005_104122063678#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'scoop water with a large spoon from one bowl to another', and now you are performing subtask 'scoop water with a large spoon from one bowl to another.'\nBegin at [323, 132] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[323, 132], [346, 141], [353, 165], [322, 192], [335, 167], [377, 162], [476, 202], [470, 233], [422, 175], [367, 188]]}" + } + ], + "images": "RH20T_cfg5_task_0082_user_0007_scene_0004_cfg_0005_104122063678#0", + "gt": "[[323, 132], [346, 141], [353, 165], [322, 192], [335, 167], [377, 162], [476, 202], [470, 233], [422, 175], [367, 188]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "87674_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the microwave door', and now you are performing subtask 'push the microwave door to open the microwave door.'\nWith start location [135, 115], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[135, 115], [147, 115], [150, 131], [160, 123], [173, 129], [140, 123], [149, 100], [168, 91], [171, 117], [171, 117]]}" + } + ], + "images": "87674_exterior_image_2_left#0", + "gt": "[[135, 115], [147, 115], [150, 131], [160, 123], [173, 129], [140, 123], [149, 100], [168, 91], [171, 117], [171, 117]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0057_user_0014_scene_0008_cfg_0004_038522062288#TrajectoryPrediction_Task#8", + "task": "TrajectoryPrediction_Task", + "p_index": 8, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn on the power strips', and now you are performing subtask 'press the button on the second power strip, press the button on the third power strip.'\nYour starting position is [260, 144]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[260, 144], [226, 99], [225, 106], [207, 97], [222, 93], [264, 132], [272, 147], [269, 153], [265, 139], [265, 139]]}" + } + ], + "images": "RH20T_cfg4_task_0057_user_0014_scene_0008_cfg_0004_038522062288#188", + "gt": "[[260, 144], [226, 99], [225, 106], [207, 97], [222, 93], [264, 132], [272, 147], [269, 153], [265, 139], [265, 139]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0066_user_0014_scene_0007_cfg_0007_104122064161#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with large Megabloks for the nth time with n blocks', and now you are performing subtask 'place the building blocks on the pile of building blocks on the building board, pick up the building blocks on the table, transfer the building block from the building board to the stack of building blocks, place the building blocks on the pile of building blocks on the building board.'\nYou begin at [329, 178]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[329, 178], [352, 168], [373, 176], [392, 164], [428, 178], [432, 194], [406, 159], [365, 169], [358, 177], [366, 176]]}" + } + ], + "images": "RH20T_cfg7_task_0066_user_0014_scene_0007_cfg_0007_104122064161#449", + "gt": "[[329, 178], [352, 168], [373, 176], [392, 164], [428, 178], [432, 194], [406, 159], [365, 169], [358, 177], [366, 176]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "14166_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the towel from the bar and put it on the seat', and now you are performing subtask 'pick up the towel from the bar.'\nYou begin at [161, 82]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[161, 82], [140, 90], [131, 76], [127, 78], [131, 81], [133, 62], [149, 47], [145, 74], [152, 79], [109, 81]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/14166_exterior_image_2_left#0.jpg", + "gt": "[[161, 82], [140, 90], [131, 76], [127, 78], [131, 81], [133, 62], [149, 47], [145, 74], [152, 79], [109, 81]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0079_user_0015_scene_0003_cfg_0001_038522062547#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the microwave door', and now you are performing subtask 'pull the handle of the microwave door to open the door.'\nYou start from [394, 39]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[394, 39], [381, 4], [347, 14], [359, 28], [419, 35], [427, 1], [415, 3], [428, 0], [461, 44], [493, 140]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0079_user_0015_scene_0003_cfg_0001_038522062547#170.jpg", + "gt": "[[394, 39], [381, 4], [347, 14], [359, 28], [419, 35], [427, 1], [415, 3], [428, 0], [461, 44], [493, 140]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0022_user_0014_scene_0007_cfg_0006_104122061018#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'wave the flag', and now you are performing subtask 'pick up the flag on the table.'\nYour starting position is [367, 28]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[367, 28], [324, 67], [272, 100], [302, 130], [329, 138], [345, 152], [348, 189], [343, 192], [333, 184], [332, 195]]}" + } + ], + "images": "RH20T_cfg6_task_0022_user_0014_scene_0007_cfg_0006_104122061018#0", + "gt": "[[367, 28], [324, 67], [272, 100], [302, 130], [329, 138], [345, 152], [348, 189], [343, 192], [333, 184], [332, 195]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "53689_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the napkin completely', and now you are performing subtask 'push the fabric on the table to the left.'\nYour starting position is [203, 114]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[203, 114], [212, 132], [204, 140], [178, 139], [156, 123], [143, 130], [183, 115], [195, 93], [195, 74], [198, 81]]}" + } + ], + "images": "53689_exterior_image_1_left#333", + "gt": "[[203, 114], [212, 132], [204, 140], [178, 139], [156, 123], [143, 130], [183, 115], [195, 93], [195, 74], [198, 81]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0037_user_0016_scene_0009_cfg_0001_035622060973#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'place the third block on top of the second block, pick up the fourth block from the surface.'\nBegin at [214, 147] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[214, 147], [216, 138], [209, 149], [207, 170], [207, 160], [213, 145], [194, 150], [190, 155], [190, 177], [186, 184]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0037_user_0016_scene_0009_cfg_0001_035622060973#484.jpg", + "gt": "[[214, 147], [216, 138], [209, 149], [207, 170], [207, 160], [213, 145], [194, 150], [190, 155], [190, 177], [186, 184]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "1291_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the cube in the bowl', and now you are performing subtask 'put the cube in the bowl.'\nYou begin at [319, 151]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[319, 151], [246, 80], [231, 75], [217, 81], [202, 121], [214, 100], [198, 80], [193, 101], [206, 97], [201, 94]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/1291_exterior_image_2_left#0.jpg", + "gt": "[[319, 151], [246, 80], [231, 75], [217, 81], [202, 121], [214, 100], [198, 80], [193, 101], [206, 97], [201, 94]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0039_user_0007_scene_0003_cfg_0005_037522062165#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pour the water from one cup into another empty cup', and now you are performing subtask 'pour the water from one cup into another empty cup.'\nYour starting position is [289, 152]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[289, 152], [298, 261], [305, 231], [245, 227], [240, 215], [210, 211], [258, 193], [286, 199], [301, 221], [296, 268]]}" + } + ], + "images": "RH20T_cfg5_task_0039_user_0007_scene_0003_cfg_0005_037522062165#0", + "gt": "[[289, 152], [298, 261], [305, 231], [245, 227], [240, 215], [210, 211], [258, 193], [286, 199], [301, 221], [296, 268]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0066_user_0014_scene_0005_cfg_0007_037522061512#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with large Megabloks for the nth time with n blocks', and now you are performing subtask 'place the block on the block board, pick up the block on the flat surface, transfer the block from the flat surface to the other blocks, place the block on the other blocks.'\nFrom start point [245, 172], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[245, 172], [223, 136], [201, 142], [211, 119], [234, 104], [258, 100], [274, 122], [276, 113], [277, 120], [241, 119]]}" + } + ], + "images": "RH20T_cfg7_task_0066_user_0014_scene_0005_cfg_0007_037522061512#436", + "gt": "[[245, 172], [223, 136], [201, 142], [211, 119], [234, 104], [258, 100], [274, 122], [276, 113], [277, 120], [241, 119]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "26333_exterior_image_2_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the button atop the lid then pick up the lid and put it on the table', and now you are performing subtask 'place the lid on the table.'\nYour initial coordinate is [145, 78]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[145, 78], [150, 78], [149, 83], [155, 65], [169, 57], [188, 56], [197, 61], [201, 80], [184, 128], [191, 88]]}" + } + ], + "images": "26333_exterior_image_2_left#187", + "gt": "[[145, 78], [150, 78], [149, 83], [155, 65], [169, 57], [188, 56], [197, 61], [201, 80], [184, 128], [191, 88]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "20823_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the banana inside the first drawer from the right then close the drawer', and now you are performing subtask 'push the first drawer on the right.'\nYou start from [219.0, 75.0]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[219.0, 75.0], [246.0, 134.0], [209.0, 154.0], [199.0, 144.0], [187.0, 145.0], [178.0, 164.0], [193.0, 150.0], [212.0, 157.0], [212.0, 140.0], [237.0, 149.0]]}" + } + ], + "images": "20823_exterior_image_1_left#0", + "gt": "[[219.0, 75.0], [246.0, 134.0], [209.0, 154.0], [199.0, 144.0], [187.0, 145.0], [178.0, 164.0], [193.0, 150.0], [212.0, 157.0], [212.0, 140.0], [237.0, 149.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "57940_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'slide the cloth to the left side of the desk', and now you are performing subtask 'slide the cloth to the left side of the desk.'\nFrom start point [139, 5], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[139, 5], [177, 50], [189, 73], [188, 77], [182, 79], [157, 78], [131, 80], [136, 71], [138, 62], [140, 66]]}" + } + ], + "images": "57940_exterior_image_1_left#0", + "gt": "[[139, 5], [177, 50], [189, 73], [188, 77], [182, 79], [157, 78], [131, 80], [136, 71], [138, 62], [140, 66]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "64234_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'fold the towel diagonally', and now you are performing subtask 'fold the towel diagonally.'\nFrom start point [287, 42], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[287, 42], [248, 74], [222, 111], [216, 113], [218, 102], [202, 101], [173, 113], [177, 123], [170, 124], [179, 119]]}" + } + ], + "images": "64234_exterior_image_1_left#0", + "gt": "[[287, 42], [248, 74], [222, 111], [216, 113], [218, 102], [202, 101], [173, 113], [177, 123], [170, 124], [179, 119]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg3_task_0058_user_0010_scene_0010_cfg_0003_104122063550#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn off the power strips', and now you are performing subtask 'press the button on the power strip above.'\nYou start from [418, 179]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[418, 179], [413, 180], [412, 183], [413, 172], [398, 154], [397, 144], [382, 169], [380, 167], [382, 171], [382, 171]]}" + } + ], + "images": "RH20T_cfg3_task_0058_user_0010_scene_0010_cfg_0003_104122063550#108", + "gt": "[[418, 179], [413, 180], [412, 183], [413, 172], [398, 154], [397, 144], [382, 169], [380, 167], [382, 171], [382, 171]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "79681_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the towel and lay it flat on the countertop', and now you are performing subtask 'pull a corner of the towel again to completely unfold the towel.'\nYour initial coordinate is [188, 102]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[188, 102], [200, 108], [199, 114], [195, 110], [197, 110], [201, 94], [203, 91], [208, 93], [206, 89], [201, 90]]}" + } + ], + "images": "79681_exterior_image_1_left#254", + "gt": "[[188, 102], [200, 108], [199, 114], [195, 110], [197, 110], [201, 94], [203, 91], [208, 93], [206, 89], [201, 90]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "88538_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'folding the towel', and now you are performing subtask 'fold the towel on the desk.'\nFrom start point [189, 26], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[189, 26], [217, 6], [232, 10], [235, 66], [251, 80], [237, 84], [222, 68], [208, 66], [188, 85], [197, 98]]}" + } + ], + "images": "88538_exterior_image_2_left#0", + "gt": "[[189, 26], [217, 6], [232, 10], [235, 66], [251, 80], [237, 84], [222, 68], [208, 66], [188, 85], [197, 98]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg2_task_0022_user_0003_scene_0004_cfg_0002_037522062165#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'wave the flag', and now you are performing subtask 'wave the flag.'\nStart at [284, 174]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[284, 174], [287, 185], [244, 212], [276, 222], [328, 317], [328, 249], [204, 196], [345, 258], [282, 221], [282, 208]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg2_task_0022_user_0003_scene_0004_cfg_0002_037522062165#0.jpg", + "gt": "[[284, 174], [287, 185], [244, 212], [276, 222], [328, 317], [328, 249], [204, 196], [345, 258], [282, 221], [282, 208]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0005_user_0015_scene_0007_cfg_0001_038522062547#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'push the block a little to the right', and now you are performing subtask 'push the block a little to the right.'\nStarting at [403, 131], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[403, 131], [403, 121], [409, 107], [406, 104], [393, 110], [383, 124], [382, 160], [390, 162], [393, 145], [391, 117]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0005_user_0015_scene_0007_cfg_0001_038522062547#0.jpg", + "gt": "[[403, 131], [403, 121], [409, 107], [406, 104], [393, 110], [383, 124], [382, 160], [390, 162], [393, 145], [391, 117]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0003_user_0010_scene_0010_cfg_0004_038522062288#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the three buttons in sequence', and now you are performing subtask 'do not press the dark green button, press the dark green button on the left.'\nFrom start point [273, 295], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[273, 295], [276, 306], [297, 286], [291, 306], [307, 282], [288, 284], [294, 275], [301, 285], [228, 254], [230, 204]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg4_task_0003_user_0010_scene_0010_cfg_0004_038522062288#191.jpg", + "gt": "[[273, 295], [276, 306], [297, 286], [291, 306], [307, 282], [288, 284], [294, 275], [301, 285], [228, 254], [230, 204]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0103_user_0007_scene_0002_cfg_0005_104122061850#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'slide the plate into the goal post', and now you are performing subtask 'slide the plate into the goal post.'\nWith start location [305, 50], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[305, 50], [331, 62], [370, 100], [362, 229], [364, 214], [383, 199], [375, 217], [373, 194], [354, 166], [314, 148]]}" + } + ], + "images": "RH20T_cfg5_task_0103_user_0007_scene_0002_cfg_0005_104122061850#0", + "gt": "[[305, 50], [331, 62], [370, 100], [362, 229], [364, 214], [383, 199], [375, 217], [373, 194], [354, 166], [314, 148]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "65299_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the tap nozzle to the left', and now you are performing subtask 'move the tap nozzle to the left.'\nFrom start point [188.5, 10.0], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[188.5, 10.0], [199.5, 61.0], [227.5, 116.0], [240.5, 133.0], [241.5, 144.0], [234.5, 137.0], [226.5, 141.0], [213.5, 139.0], [192.5, 129.0], [172.5, 144.0]]}" + } + ], + "images": "65299_exterior_image_1_left#0", + "gt": "[[188.5, 10.0], [199.5, 61.0], [227.5, 116.0], [240.5, 133.0], [241.5, 144.0], [234.5, 137.0], [226.5, 141.0], [213.5, 139.0], [192.5, 129.0], [172.5, 144.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "1962_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the marker out of the box and place it on the table', and now you are performing subtask 'take the marker out of the box and place it on the table.'\nBegin at [197, 66] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[197, 66], [184, 81], [185, 109], [191, 114], [184, 135], [194, 139], [183, 131], [175, 168], [166, 144], [170, 132]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/1962_exterior_image_1_left#0.jpg", + "gt": "[[197, 66], [184, 81], [185, 109], [191, 114], [184, 135], [194, 139], [183, 131], [175, 168], [166, 144], [170, 132]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "55040_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'throw the yellow square into the silver pot', and now you are performing subtask 'throw the yellow square into the silver pot.'\nYou begin at [252, 2]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[252, 2], [236, 47], [210, 85], [201, 92], [183, 91], [191, 102], [188, 109], [200, 99], [213, 106], [202, 102]]}" + } + ], + "images": "55040_exterior_image_2_left#0", + "gt": "[[252, 2], [236, 47], [210, 85], [201, 92], [183, 91], [191, 102], [188, 109], [200, 99], [213, 106], [202, 102]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0003_user_0015_scene_0008_cfg_0001_038522062547#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the three buttons from left to right in sequence', and now you are performing subtask 'press the orange button on the left, press the yellow button in the middle.'\nBegin at [419, 119] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[419, 119], [413, 101], [392, 112], [378, 111], [378, 117], [380, 107], [372, 94], [384, 90], [376, 78], [380, 50]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0003_user_0015_scene_0008_cfg_0001_038522062547#156.jpg", + "gt": "[[419, 119], [413, 101], [392, 112], [378, 111], [378, 117], [380, 107], [372, 94], [384, 90], [376, 78], [380, 50]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg3_task_0005_user_0016_scene_0010_cfg_0003_104122062823#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'approach and touch the side of the small block', and now you are performing subtask 'approach and touch the side of the small block.'\nStarting at [242, 0], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[242, 0], [271, 0], [255, 0], [275, 9], [327, 0], [281, 0], [275, 46], [285, 46], [298, 95], [334, 86]]}" + } + ], + "images": "RH20T_cfg3_task_0005_user_0016_scene_0010_cfg_0003_104122062823#0", + "gt": "[[242, 0], [271, 0], [255, 0], [275, 9], [327, 0], [281, 0], [275, 46], [285, 46], [298, 95], [334, 86]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "8718_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the box', and now you are performing subtask 'place the lid on the table.'\nWith start location [124, 106], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[124, 106], [117, 98], [115, 87], [123, 61], [133, 51], [152, 45], [165, 48], [178, 57], [189, 60], [193, 0]]}" + } + ], + "images": "8718_exterior_image_1_left#221", + "gt": "[[124, 106], [117, 98], [115, 87], [123, 61], [133, 51], [152, 45], [165, 48], [178, 57], [189, 60], [193, 0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0037_user_0020_scene_0008_cfg_0006_037522061512#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'pick up the fourth block on the table, transfer the fourth block from the table to above the third block, place the fourth block on top of the third block, pick up the fifth block on the table.'\nWith start location [247, 94], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[247, 94], [216, 84], [210, 109], [218, 144], [222, 98], [253, 51], [287, 67], [248, 42], [224, 89], [199, 104]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg6_task_0037_user_0020_scene_0008_cfg_0006_037522061512#1020.jpg", + "gt": "[[247, 94], [216, 84], [210, 109], [218, 144], [222, 98], [253, 51], [287, 67], [248, 42], [224, 89], [199, 104]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg2_task_0034_user_0003_scene_0006_cfg_0002_104422070044#TrajectoryPrediction_Task#8", + "task": "TrajectoryPrediction_Task", + "p_index": 8, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the squares into a pyramid shape', and now you are performing subtask 'place the fourth square on the first and third squares, slide the fifth square towards the middle of the countertop, pick up the fifth square from the countertop, transfer the fifth square from the countertop to the first and second squares.'\nYou begin at [405, 223]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[405, 223], [427, 210], [427, 199], [422, 209], [426, 214], [418, 208], [404, 219], [387, 206], [375, 218], [382, 232]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg2_task_0034_user_0003_scene_0006_cfg_0002_104422070044#543.jpg", + "gt": "[[405, 223], [427, 210], [427, 199], [422, 209], [426, 214], [418, 208], [404, 219], [387, 206], [375, 218], [382, 232]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "37214_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'the green towel on the folding table', and now you are performing subtask 'the green towel on the folding table.'\nYour initial coordinate is [260, 6]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[260, 6], [229, 44], [204, 99], [194, 73], [182, 61], [189, 74], [211, 89], [220, 103], [222, 74], [218, 78]]}" + } + ], + "images": "37214_exterior_image_2_left#0", + "gt": "[[260, 6], [229, 44], [204, 99], [194, 73], [182, 61], [189, 74], [211, 89], [220, 103], [222, 74], [218, 78]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0041_user_0007_scene_0006_cfg_0005_104122063678#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'clean the tabletop with a sponge', and now you are performing subtask 'slide the sponge on the tabletop to clean the surface, grab the sponge on the table, let the sponge slide on the tabletop, place the sponge on the tabletop.'\nYou begin at [326, 223]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[326, 223], [336, 233], [331, 220], [336, 214], [339, 237], [329, 215], [335, 205], [329, 208], [335, 223], [326, 228]]}" + } + ], + "images": "RH20T_cfg5_task_0041_user_0007_scene_0006_cfg_0005_104122063678#573", + "gt": "[[326, 223], [336, 233], [331, 220], [336, 214], [339, 237], [329, 215], [335, 205], [329, 208], [335, 223], [326, 228]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0130_user_0020_scene_0004_cfg_0006_104122064161#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'plug in the bulb holder with a bulb to the socket and turn on the switch of the bulb', and now you are performing subtask 'pick up the bulb on the table, transfer the bulb from the table to the socket, insert the bulb into the socket.'\nYou begin at [338, 111]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[338, 111], [341, 88], [349, 96], [376, 87], [407, 101], [417, 97], [421, 134], [419, 112], [386, 129], [380, 165]]}" + } + ], + "images": "RH20T_cfg6_task_0130_user_0020_scene_0004_cfg_0006_104122064161#0", + "gt": "[[338, 111], [341, 88], [349, 96], [376, 87], [407, 101], [417, 97], [421, 134], [419, 112], [386, 129], [380, 165]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "92204_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'sliding the towel to the left side of the table', and now you are performing subtask 'sliding the towel to the left side of the table.'\nFrom start point [116, 3], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[116, 3], [143, 10], [196, 47], [210, 63], [222, 87], [226, 108], [221, 126], [208, 91], [188, 76], [181, 64]]}" + } + ], + "images": "92204_exterior_image_1_left#0", + "gt": "[[116, 3], [143, 10], [196, 47], [210, 63], [222, 87], [226, 108], [221, 126], [208, 91], [188, 76], [181, 64]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "24360_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the marker in the mug', and now you are performing subtask 'put the marker in the mug.'\nYour starting position is [93, 0]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[93, 0], [98, 76], [113, 100], [90, 69], [97, 60], [116, 63], [124, 77], [115, 84], [134, 92], [128, 72]]}" + } + ], + "images": "24360_exterior_image_2_left#0", + "gt": "[[93, 0], [98, 76], [113, 100], [90, 69], [97, 60], [116, 63], [124, 77], [115, 84], [134, 92], [128, 72]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "951_exterior_image_1_left#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the drawer, then put the pineapple and banana plush toys in the drawer, then close the drawer', and now you are performing subtask 'push the handle of the drawer to close the drawer.'\nThe trajectory starts at [153.0, 60.5]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[153.0, 60.5], [179.0, 83.5], [180.0, 79.5], [191.0, 80.5], [165.0, 72.5], [186.0, 84.5], [187.0, 99.5], [157.0, 98.5], [164.0, 87.5], [163.0, 57.5]]}" + } + ], + "images": "951_exterior_image_1_left#384", + "gt": "[[153.0, 60.5], [179.0, 83.5], [180.0, 79.5], [191.0, 80.5], [165.0, 72.5], [186.0, 84.5], [187.0, 99.5], [157.0, 98.5], [164.0, 87.5], [163.0, 57.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "49916_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the lemon from the white plate and put it on the nightstand', and now you are performing subtask 'pick up the lemon from the white plate.'\nFrom start point [84, 47], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[84, 47], [88, 56], [88, 63], [90, 67], [89, 71], [108, 78], [112, 85], [115, 87], [113, 87], [113, 91]]}" + } + ], + "images": "49916_exterior_image_2_left#0", + "gt": "[[84, 47], [88, 56], [88, 63], [90, 67], [89, 71], [108, 78], [112, 85], [115, 87], [113, 87], [113, 91]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "44450_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the cupcake backward', and now you are performing subtask 'move the cupcake backward.'\nStarting at [279, 4], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[279, 4], [285, 31], [281, 67], [231, 112], [242, 92], [233, 71], [225, 74], [221, 88], [242, 81], [242, 81]]}" + } + ], + "images": "44450_exterior_image_1_left#0", + "gt": "[[279, 4], [285, 31], [281, 67], [231, 112], [242, 92], [233, 71], [225, 74], [221, 88], [242, 81], [242, 81]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "47445_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the marker from the box and place it on the table', and now you are performing subtask 'remove the marker from the box and place it on the table.'\nYour initial coordinate is [257, 65]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[257, 65], [235, 57], [212, 59], [181, 78], [177, 89], [183, 81], [174, 69], [169, 76], [164, 108], [164, 108]]}" + } + ], + "images": "47445_exterior_image_1_left#0", + "gt": "[[257, 65], [235, 57], [212, 59], [181, 78], [177, 89], [183, 81], [174, 69], [169, 76], [164, 108], [164, 108]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "19841_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'change the position of the donut on the counter', and now you are performing subtask 'change the position of the donut on the counter.'\nYou start from [261, 3]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[261, 3], [229, 49], [223, 66], [224, 82], [209, 98], [213, 99], [230, 83], [232, 71], [224, 79], [224, 79]]}" + } + ], + "images": "19841_exterior_image_2_left#0", + "gt": "[[261, 3], [229, 49], [223, 66], [224, 82], [209, 98], [213, 99], [230, 83], [232, 71], [224, 79], [224, 79]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg2_task_0003_user_0006_scene_0007_cfg_0002_104122063678#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the three buttons in sequence', and now you are performing subtask 'press the gray base green button, press the gray base red button.'\nYou begin at [315, 290]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[315, 290], [300, 291], [297, 275], [279, 250], [277, 236], [287, 245], [276, 224], [279, 229], [280, 219], [286, 216]]}" + } + ], + "images": "RH20T_cfg2_task_0003_user_0006_scene_0007_cfg_0002_104122063678#194", + "gt": "[[315, 290], [300, 291], [297, 275], [279, 250], [277, 236], [287, 245], [276, 224], [279, 229], [280, 219], [286, 216]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0009_user_0010_scene_0004_cfg_0004_104422070011#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take out a Hanoi block and place it on the table', and now you are performing subtask 'take out a Hanoi block and place it on the table.'\nFrom start point [340, 104], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[340, 104], [330, 114], [353, 116], [350, 160], [343, 172], [314, 167], [362, 150], [347, 151], [365, 156], [358, 212]]}" + } + ], + "images": "RH20T_cfg4_task_0009_user_0010_scene_0004_cfg_0004_104422070011#0", + "gt": "[[340, 104], [330, 114], [353, 116], [350, 160], [343, 172], [314, 167], [362, 150], [347, 151], [365, 156], [358, 212]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "64549_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the orange ball to the bottom of the cabinet', and now you are performing subtask 'move the orange ball to the bottom of the cabinet.'\nWith start location [214, 9], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[214, 9], [190, 11], [172, 9], [167, 17], [167, 24], [152, 22], [150, 24], [151, 32], [156, 20], [170, 14]]}" + } + ], + "images": "64549_exterior_image_1_left#0", + "gt": "[[214, 9], [190, 11], [172, 9], [167, 17], [167, 24], [152, 22], [150, 24], [151, 32], [156, 20], [170, 14]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0070_user_0020_scene_0003_cfg_0006_104122060811#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open a sliding window', and now you are performing subtask 'open a sliding window.'\nStart at [385, 127]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[385, 127], [369, 136], [373, 140], [369, 130], [366, 142], [372, 136], [387, 145], [386, 134], [384, 148], [385, 129]]}" + } + ], + "images": "RH20T_cfg6_task_0070_user_0020_scene_0003_cfg_0006_104122060811#0", + "gt": "[[385, 127], [369, 136], [373, 140], [369, 130], [366, 142], [372, 136], [387, 145], [386, 134], [384, 148], [385, 129]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0032_user_0016_scene_0002_cfg_0004_104122062295#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'slide the outer casing onto the gift box', and now you are performing subtask 'slide the outer casing onto the gift box.'\nYour initial coordinate is [214, 203]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[214, 203], [196, 197], [169, 198], [169, 223], [172, 226], [179, 205], [194, 199], [215, 198], [271, 203], [291, 211]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg4_task_0032_user_0016_scene_0002_cfg_0004_104122062295#173.jpg", + "gt": "[[214, 203], [196, 197], [169, 198], [169, 223], [172, 226], [179, 205], [194, 199], [215, 198], [271, 203], [291, 211]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg2_task_0037_user_0007_scene_0006_cfg_0002_104122063678#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'place the third block on the fourth block, pick up the fourth block on the table, transfer the fourth block from the table to the top of the fifth block, place the fourth block on the fifth block.'\nThe trajectory starts at [347, 196]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[347, 196], [328, 174], [334, 178], [332, 185], [336, 186], [330, 196], [330, 170], [351, 184], [347, 193], [351, 185]]}" + } + ], + "images": "RH20T_cfg2_task_0037_user_0007_scene_0006_cfg_0002_104122063678#695", + "gt": "[[347, 196], [328, 174], [334, 178], [332, 185], [336, 186], [330, 196], [330, 170], [351, 184], [347, 193], [351, 185]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "76266_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the bottle in the paper bag and then remove it and put it back on the table', and now you are performing subtask 'put the bottle in the paper bag and then remove it and put it back on the table.'\nStart at [225, 133]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[225, 133], [237, 114], [209, 111], [217, 79], [196, 31], [174, 11], [171, 90], [184, 14], [200, 2], [199, 83]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/76266_exterior_image_1_left#0.jpg", + "gt": "[[225, 133], [237, 114], [209, 111], [217, 79], [196, 31], [174, 11], [171, 90], [184, 14], [200, 2], [199, 83]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "17817_exterior_image_2_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the blue block on the tower', and now you are performing subtask 'press the blue block on the block tower.'\nThe trajectory starts at [104, 71]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[104, 71], [115, 73], [118, 78], [118, 84], [98, 75], [87, 74], [85, 77], [89, 94], [87, 96], [86, 94]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/17817_exterior_image_2_left#312.jpg", + "gt": "[[104, 71], [115, 73], [118, 78], [118, 84], [98, 75], [87, 74], [85, 77], [89, 94], [87, 96], [86, 94]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0034_user_0014_scene_0004_cfg_0001_038522062547#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the squares into a pyramid shape', and now you are performing subtask 'pick up the second square from the right side of the table, transfer the second square from the right side of the table to the top of the first square, place the second square beside the first square.'\nThe trajectory starts at [431, 200]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[431, 200], [472, 205], [472, 212], [464, 198], [410, 176], [397, 176], [400, 183], [391, 188], [397, 178], [426, 180]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0034_user_0014_scene_0004_cfg_0001_038522062547#226.jpg", + "gt": "[[431, 200], [472, 205], [472, 212], [464, 198], [410, 176], [397, 176], [400, 183], [391, 188], [397, 178], [426, 180]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "74509_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the peg from the table and hang it on the black stand', and now you are performing subtask 'take the peg from the table and hang it on the black stand.'\nWith start location [272.0, 68.0], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[272.0, 68.0], [278.0, 86.0], [263.0, 91.0], [251.0, 119.0], [230.0, 132.0], [238.0, 98.0], [236.0, 84.0], [226.0, 92.0], [236.0, 67.0], [249.0, 71.0]]}" + } + ], + "images": "74509_exterior_image_1_left#0", + "gt": "[[272.0, 68.0], [278.0, 86.0], [263.0, 91.0], [251.0, 119.0], [230.0, 132.0], [238.0, 98.0], [236.0, 84.0], [226.0, 92.0], [236.0, 67.0], [249.0, 71.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0040_user_0010_scene_0002_cfg_0001_038522062547#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the cups', and now you are performing subtask 'pick up the green cup on the table, transfer the green cup from the table to the blue cup, place the green cup on top of the blue cup.'\nFrom start point [406, 129], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[406, 129], [411, 157], [446, 162], [451, 239], [495, 240], [493, 223], [480, 233], [476, 187], [490, 94], [478, 105]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0040_user_0010_scene_0002_cfg_0001_038522062547#0.jpg", + "gt": "[[406, 129], [411, 157], [446, 162], [451, 239], [495, 240], [493, 223], [480, 233], [476, 187], [490, 94], [478, 105]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0094_user_0014_scene_0010_cfg_0001_038522062547#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open a box', and now you are performing subtask 'fold the first lid on the box on the table.'\nYou begin at [406, 132]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[406, 132], [379, 206], [357, 216], [349, 228], [354, 231], [349, 226], [364, 254], [360, 245], [363, 233], [377, 218]]}" + } + ], + "images": "RH20T_cfg1_task_0094_user_0014_scene_0010_cfg_0001_038522062547#0", + "gt": "[[406, 132], [379, 206], [357, 216], [349, 228], [354, 231], [349, 226], [364, 254], [360, 245], [363, 233], [377, 218]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "67778_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the staple remover to the left', and now you are performing subtask 'move the staple remover to the left.'\nYour starting position is [226.0, 1.5]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[226.0, 1.5], [268.0, 9.5], [273.0, 21.5], [254.0, 60.5], [223.0, 76.5], [236.0, 77.5], [199.0, 60.5], [188.0, 59.5], [183.0, 69.5], [167.0, 55.5]]}" + } + ], + "images": "67778_exterior_image_1_left#0", + "gt": "[[226.0, 1.5], [268.0, 9.5], [273.0, 21.5], [254.0, 60.5], [223.0, 76.5], [236.0, 77.5], [199.0, 60.5], [188.0, 59.5], [183.0, 69.5], [167.0, 55.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "28600_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the packet out of the sink and place it on the left side of the countertop', and now you are performing subtask 'take the packet out of the sink and place it on the left side of the countertop.'\nYou start from [209, 80]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[209, 80], [236, 88], [245, 109], [237, 124], [241, 149], [231, 125], [201, 133], [189, 146], [198, 133], [213, 132]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/28600_exterior_image_2_left#0.jpg", + "gt": "[[209, 80], [236, 88], [245, 109], [237, 124], [241, 149], [231, 125], [201, 133], [189, 146], [198, 133], [213, 132]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg3_task_0035_user_0010_scene_0001_cfg_0003_104122062295#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up a small block', and now you are performing subtask 'pick up a small block.'\nFrom start point [381, 70], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[381, 70], [389, 120], [365, 104], [402, 106], [341, 98], [258, 59], [215, 118], [252, 104], [271, 139], [256, 76]]}" + } + ], + "images": "RH20T_cfg3_task_0035_user_0010_scene_0001_cfg_0003_104122062295#0", + "gt": "[[381, 70], [389, 120], [365, 104], [402, 106], [341, 98], [258, 59], [215, 118], [252, 104], [271, 139], [256, 76]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "70297_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the marker in the mug', and now you are performing subtask 'put the marker in the mug.'\nStart at [154.0, 79.0]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[154.0, 79.0], [167.0, 109.0], [166.0, 128.0], [169.0, 129.0], [168.0, 119.0], [172.0, 109.0], [171.0, 101.0], [166.0, 107.0], [169.0, 98.0], [169.0, 98.0]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/70297_exterior_image_1_left#0.jpg", + "gt": "[[154.0, 79.0], [167.0, 109.0], [166.0, 128.0], [169.0, 129.0], [168.0, 119.0], [172.0, 109.0], [171.0, 101.0], [166.0, 107.0], [169.0, 98.0], [169.0, 98.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0130_user_0014_scene_0004_cfg_0006_104122061018#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'plug in the bulb holder with a bulb to the socket and turn on the switch of the bulb', and now you are performing subtask 'insert the lamp holder into the socket, press the lamp holder button to turn on the light.'\nYou start from [304, 105]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[304, 105], [302, 86], [305, 77], [304, 81], [335, 112], [338, 109], [342, 112], [347, 110], [356, 118], [349, 125]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg6_task_0130_user_0014_scene_0004_cfg_0006_104122061018#315.jpg", + "gt": "[[304, 105], [302, 86], [305, 77], [304, 81], [335, 112], [338, 109], [342, 112], [347, 110], [356, 118], [349, 125]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg2_task_0004_user_0006_scene_0003_cfg_0002_104122063678#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the small block on the left and move it to the right', and now you are performing subtask 'pick up the small block on the left and move it to the right.'\nWith start location [289, 196], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[289, 196], [358, 241], [371, 289], [322, 322], [325, 353], [331, 337], [303, 286], [297, 302], [289, 257], [289, 257]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg2_task_0004_user_0006_scene_0003_cfg_0002_104122063678#0.jpg", + "gt": "[[289, 196], [358, 241], [371, 289], [322, 322], [325, 353], [331, 337], [303, 286], [297, 302], [289, 257], [289, 257]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "35951_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the towel from right to left', and now you are performing subtask 'unfold the towel from right to left.'\nStart at [284, 1]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[284, 1], [274, 34], [279, 27], [283, 41], [290, 31], [312, 38], [268, 63], [251, 95], [224, 96], [221, 86]]}" + } + ], + "images": "35951_exterior_image_1_left#0", + "gt": "[[284, 1], [274, 34], [279, 27], [283, 41], [290, 31], [312, 38], [268, 63], [251, 95], [224, 96], [221, 86]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "59697_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the objects from the orange bowl to the black pot, then cover the black pot with the glass lid', and now you are performing subtask 'pick up the item from the orange bowl.'\nYour initial coordinate is [188, 4]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[188, 4], [186, 42], [190, 74], [183, 75], [190, 66], [180, 43], [174, 41], [168, 48], [171, 62], [170, 52]]}" + } + ], + "images": "59697_exterior_image_1_left#0", + "gt": "[[188, 4], [186, 42], [190, 74], [183, 75], [190, 66], [180, 43], [174, 41], [168, 48], [171, 62], [170, 52]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "35107_exterior_image_2_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the towel, then lay it out on the countertop', and now you are performing subtask 'fold the towel on the countertop.'\nYour starting position is [184, 98]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[184, 98], [202, 113], [193, 137], [184, 114], [181, 129], [168, 116], [178, 130], [159, 120], [196, 119], [171, 95]]}" + } + ], + "images": "35107_exterior_image_2_left#171", + "gt": "[[184, 98], [202, 113], [193, 137], [184, 114], [181, 129], [168, 116], [178, 130], [159, 120], [196, 119], [171, 95]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0064_user_0015_scene_0008_cfg_0001_038522063145#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the roll of paper to the shelf', and now you are performing subtask 'pick up the roll of paper from the desktop, transfer the roll of paper from the desktop to the shelf, place the roll of paper on the shelf.'\nWith start location [443, 98], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[443, 98], [370, 105], [336, 98], [342, 99], [330, 114], [351, 89], [402, 83], [416, 77], [418, 65], [418, 65]]}" + } + ], + "images": "RH20T_cfg1_task_0064_user_0015_scene_0008_cfg_0001_038522063145#0", + "gt": "[[443, 98], [370, 105], [336, 98], [342, 99], [330, 114], [351, 89], [402, 83], [416, 77], [418, 65], [418, 65]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0052_user_0007_scene_0010_cfg_0005_104122061850#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'grab a basketball, release it and shoot it into the basket', and now you are performing subtask 'grab a basketball, release it and shoot it into the basket.'\nYour initial coordinate is [305, 50]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[305, 50], [341, 46], [384, 125], [341, 85], [256, 64], [172, 108], [174, 140], [192, 161], [275, 70], [292, 28]]}" + } + ], + "images": "RH20T_cfg5_task_0052_user_0007_scene_0010_cfg_0005_104122061850#0", + "gt": "[[305, 50], [341, 46], [384, 125], [341, 85], [256, 64], [172, 108], [174, 140], [192, 161], [275, 70], [292, 28]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0108_user_0014_scene_0004_cfg_0001_750612070851#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'sharpen the pencil with a pencil sharpener', and now you are performing subtask 'sharpen the pencil with a pencil sharpener.'\nStarting at [413, 178], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[413, 178], [510, 225], [531, 209], [514, 218], [516, 209], [509, 222], [515, 232], [490, 271], [509, 231], [561, 213]]}" + } + ], + "images": "RH20T_cfg1_task_0108_user_0014_scene_0004_cfg_0001_750612070851#0", + "gt": "[[413, 178], [510, 225], [531, 209], [514, 218], [516, 209], [509, 222], [515, 232], [490, 271], [509, 231], [561, 213]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "26790_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'push the first small block to the left and use the second small block to push the third small block to the right', and now you are performing subtask 'push the third small object to the right with the second small object.'\nStarting at [134.0, 90.0], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[134.0, 90.0], [143.0, 64.0], [155.0, 67.0], [147.0, 75.0], [149.0, 85.0], [158.0, 77.0], [159.0, 66.0], [171.0, 74.0], [184.0, 50.0], [184.0, 50.0]]}" + } + ], + "images": "26790_exterior_image_1_left#118", + "gt": "[[134.0, 90.0], [143.0, 64.0], [155.0, 67.0], [147.0, 75.0], [149.0, 85.0], [158.0, 77.0], [159.0, 66.0], [171.0, 74.0], [184.0, 50.0], [184.0, 50.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "56499_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close the door on the first washing machine from the left', and now you are performing subtask 'close the door on the first washing machine from the left.'\nBegin at [123, 54] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[123, 54], [122, 84], [132, 92], [128, 96], [131, 101], [159, 86], [138, 90], [132, 84], [134, 53], [127, 21]]}" + } + ], + "images": "56499_exterior_image_1_left#0", + "gt": "[[123, 54], [122, 84], [132, 92], [128, 96], [131, 101], [159, 86], [138, 90], [132, 84], [134, 53], [127, 21]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "35595_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the carrot plush toy in the pot in the sink', and now you are performing subtask 'put the carrot plush toy in the pot in the sink.'\nYou begin at [36, 2]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[36, 2], [70, 25], [118, 43], [106, 46], [174, 106], [180, 104], [185, 121], [197, 130], [195, 110], [188, 107]]}" + } + ], + "images": "35595_exterior_image_1_left#0", + "gt": "[[36, 2], [70, 25], [118, 43], [106, 46], [174, 106], [180, 104], [185, 121], [197, 130], [195, 110], [188, 107]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0066_user_0014_scene_0005_cfg_0001_038522062547#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with large Megabloks for the nth time with n blocks', and now you are performing subtask 'place the second Megablock on the green base, pick up the third Megablock from the left side of the table, place the third Megablock on the green base.'\nYou start from [385, 173]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[385, 173], [461, 200], [470, 211], [463, 211], [463, 191], [449, 165], [414, 135], [421, 136], [385, 133], [384, 155]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0066_user_0014_scene_0005_cfg_0001_038522062547#337.jpg", + "gt": "[[385, 173], [461, 200], [470, 211], [463, 211], [463, 191], [449, 165], [414, 135], [421, 136], [385, 133], [384, 155]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0008_user_0010_scene_0010_cfg_0005_104422070044#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'grab the block and place it at the black dot', and now you are performing subtask 'grab the block and place it at the black dot.'\nStart at [374, 132]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[374, 132], [433, 208], [494, 216], [490, 195], [481, 219], [480, 209], [426, 186], [401, 179], [396, 186], [411, 152]]}" + } + ], + "images": "RH20T_cfg5_task_0008_user_0010_scene_0010_cfg_0005_104422070044#0", + "gt": "[[374, 132], [433, 208], [494, 216], [490, 195], [481, 219], [480, 209], [426, 186], [401, 179], [396, 186], [411, 152]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "15355_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the button on the power strip', and now you are performing subtask 'press the button on the power strip.'\nThe trajectory starts at [212, 0]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[212, 0], [206, 2], [195, 17], [189, 43], [196, 60], [186, 74], [184, 97], [180, 63], [198, 19], [198, 19]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/15355_exterior_image_1_left#0.jpg", + "gt": "[[212, 0], [206, 2], [195, 17], [189, 43], [196, 60], [186, 74], [184, 97], [180, 63], [198, 19], [198, 19]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "14341_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the brush inside the silver flask up and down', and now you are performing subtask 'move the brush inside the silver flask up and down.'\nFrom start point [316.5, 36.0], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[316.5, 36.0], [286.5, 52.0], [279.5, 82.0], [265.5, 59.0], [268.5, 80.0], [257.5, 29.0], [260.5, 74.0], [257.5, 21.0], [260.5, 84.0], [258.5, 40.0]]}" + } + ], + "images": "14341_exterior_image_1_left#0", + "gt": "[[316.5, 36.0], [286.5, 52.0], [279.5, 82.0], [265.5, 59.0], [268.5, 80.0], [257.5, 29.0], [260.5, 74.0], [257.5, 21.0], [260.5, 84.0], [258.5, 40.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg2_task_0002_user_0013_scene_0006_cfg_0002_104422070044#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pull out a napkin, place the napkin on the table', and now you are performing subtask 'pull out a napkin, place the napkin on the table.'\nYour initial coordinate is [311, 190]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[311, 190], [321, 193], [354, 191], [357, 199], [362, 183], [362, 175], [359, 175], [339, 189], [271, 203], [271, 203]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg2_task_0002_user_0013_scene_0006_cfg_0002_104422070044#0.jpg", + "gt": "[[311, 190], [321, 193], [354, 191], [357, 199], [362, 183], [362, 175], [359, 175], [339, 189], [271, 203], [271, 203]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "2330_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close the flask', and now you are performing subtask 'close the flask.'\nYour initial coordinate is [318.5, 95.5]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[318.5, 95.5], [309.5, 110.5], [293.5, 122.5], [298.5, 122.5], [290.5, 129.5], [276.5, 157.5], [292.5, 168.5], [281.5, 160.5], [283.5, 154.5], [271.5, 147.5]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/2330_exterior_image_1_left#0.jpg", + "gt": "[[318.5, 95.5], [309.5, 110.5], [293.5, 122.5], [298.5, 122.5], [290.5, 129.5], [276.5, 157.5], [292.5, 168.5], [281.5, 160.5], [283.5, 154.5], [271.5, 147.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0008_user_0007_scene_0001_cfg_0005_036422060215#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'grab the block and place it at the designated location', and now you are performing subtask 'grab the block and place it at the designated location.'\nYour initial coordinate is [286, 106]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[286, 106], [344, 104], [422, 124], [417, 148], [391, 168], [396, 149], [346, 133], [299, 135], [293, 144], [318, 106]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0008_user_0007_scene_0001_cfg_0005_036422060215#0.jpg", + "gt": "[[286, 106], [344, 104], [422, 124], [417, 148], [391, 168], [396, 149], [346, 133], [299, 135], [293, 144], [318, 106]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0066_user_0016_scene_0003_cfg_0004_104122062823#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'building blocks', and now you are performing subtask 'pick up the green block from the table, transfer the green block from the table to the block board, place the green block on the block board.'\nYou begin at [289, 0]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[289, 0], [409, 19], [431, 50], [415, 82], [429, 81], [437, 51], [426, 71], [428, 99], [419, 104], [421, 95]]}" + } + ], + "images": "RH20T_cfg4_task_0066_user_0016_scene_0003_cfg_0004_104122062823#0", + "gt": "[[289, 0], [409, 19], [431, 50], [415, 82], [429, 81], [437, 51], [426, 71], [428, 99], [419, 104], [421, 95]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "22312_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the curtain', and now you are performing subtask 'pull the curtain right.'\nYour initial coordinate is [204, 107]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[204, 107], [194, 108], [168, 98], [147, 55], [148, 50], [184, 80], [233, 107], [235, 110], [229, 109], [223, 104]]}" + } + ], + "images": "22312_exterior_image_1_left#157", + "gt": "[[204, 107], [194, 108], [168, 98], [147, 55], [148, 50], [184, 80], [233, 107], [235, 110], [229, 109], [223, 104]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0059_user_0016_scene_0003_cfg_0004_104122062823#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn the knob to increase the volume of the speaker', and now you are performing subtask 'turn the knob to increase the volume of the speaker.'\nThe trajectory starts at [289, 0]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[289, 0], [354, 0], [356, 42], [379, 27], [384, 40], [399, 16], [383, 28], [390, 33], [383, 22], [383, 22]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg4_task_0059_user_0016_scene_0003_cfg_0004_104122062823#0.jpg", + "gt": "[[289, 0], [354, 0], [356, 42], [379, 27], [384, 40], [399, 16], [383, 28], [390, 33], [383, 22], [383, 22]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0041_user_0007_scene_0006_cfg_0005_037522062165#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'clean the tabletop with a sponge', and now you are performing subtask 'slide the sponge on the tabletop to clean the surface, grab the sponge on the table, let the sponge slide on the tabletop, place the sponge on the tabletop.'\nYour starting position is [260, 246]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[260, 246], [242, 238], [244, 247], [262, 259], [257, 245], [238, 244], [272, 259], [273, 266], [252, 247], [252, 231]]}" + } + ], + "images": "RH20T_cfg5_task_0041_user_0007_scene_0006_cfg_0005_037522062165#483", + "gt": "[[260, 246], [242, 238], [244, 247], [262, 259], [257, 245], [238, 244], [272, 259], [273, 266], [252, 247], [252, 231]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0003_user_0015_scene_0008_cfg_0001_039422060546#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the three buttons from left to right in sequence', and now you are performing subtask 'press the green button on the right.'\nWith start location [265, 124], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[265, 124], [277, 111], [277, 158], [234, 193], [231, 184], [246, 183], [248, 199], [242, 170], [277, 143], [277, 143]]}" + } + ], + "images": "RH20T_cfg1_task_0003_user_0015_scene_0008_cfg_0001_039422060546#0", + "gt": "[[265, 124], [277, 111], [277, 158], [234, 193], [231, 184], [246, 183], [248, 199], [242, 170], [277, 143], [277, 143]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "19986_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the green object in the bowl', and now you are performing subtask 'put the green object in the bowl.'\nYour starting position is [210, 1]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[210, 1], [198, 20], [183, 73], [188, 54], [211, 45], [225, 56], [238, 75], [238, 84], [231, 80], [233, 57]]}" + } + ], + "images": "19986_exterior_image_2_left#0", + "gt": "[[210, 1], [198, 20], [183, 73], [188, 54], [211, 45], [225, 56], [238, 75], [238, 84], [231, 80], [233, 57]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0061_user_0001_scene_0005_cfg_0001_035622060973#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take everything out of the gift box', and now you are performing subtask 'pick up the big square from the gift box, transfer the big square from the gift box to above the fabric, place the big square on the fabric, pick up the small square from the gift box.'\nWith start location [246, 130], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[246, 130], [218, 128], [221, 135], [224, 123], [252, 168], [249, 181], [236, 188], [220, 144], [238, 133], [234, 125]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0061_user_0001_scene_0005_cfg_0001_035622060973#0.jpg", + "gt": "[[246, 130], [218, 128], [221, 135], [224, 123], [252, 168], [249, 181], [236, 188], [220, 144], [238, 133], [234, 125]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "51122_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'use the wooden spoon to divide the orange object', and now you are performing subtask 'use the wooden spoon to divide the orange object.'\nWith start location [320, 64], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[320, 64], [297, 71], [274, 91], [280, 78], [260, 79], [266, 100], [282, 78], [294, 82], [270, 87], [283, 66]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/51122_exterior_image_1_left#0.jpg", + "gt": "[[320, 64], [297, 71], [274, 91], [280, 78], [260, 79], [266, 100], [282, 78], [294, 82], [270, 87], [283, 66]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0001_user_0020_scene_0001_cfg_0005_104122061850#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the green button on the yellow base', and now you are performing subtask 'press the green button on the yellow base.'\nStarting at [311, 50], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[311, 50], [329, 54], [344, 67], [350, 102], [358, 116], [355, 132], [365, 129], [353, 139], [358, 140], [342, 116]]}" + } + ], + "images": "RH20T_cfg5_task_0001_user_0020_scene_0001_cfg_0005_104122061850#0", + "gt": "[[311, 50], [329, 54], [344, 67], [350, 102], [358, 116], [355, 132], [365, 129], [353, 139], [358, 140], [342, 116]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0003_user_0010_scene_0001_cfg_0005_105422061350#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press three buttons from left to right in sequence', and now you are performing subtask 'press the yellow button on the right, press the red button in the middle.'\nStart at [276, 47]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[276, 47], [266, 35], [280, 31], [264, 26], [264, 38], [267, 24], [260, 26], [257, 60], [252, 35], [240, 86]]}" + } + ], + "images": "RH20T_cfg5_task_0003_user_0010_scene_0001_cfg_0005_105422061350#0", + "gt": "[[276, 47], [266, 35], [280, 31], [264, 26], [264, 38], [267, 24], [260, 26], [257, 60], [252, 35], [240, 86]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0066_user_0014_scene_0007_cfg_0007_104122061018#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with large Megabloks for the nth time with n blocks', and now you are performing subtask 'pick up the building blocks on the table, transfer the building blocks from the desktop to the building board, place the building blocks on the building board.'\nStart at [247, 57]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[247, 57], [199, 80], [208, 102], [202, 114], [236, 47], [321, 106], [317, 119], [304, 99], [274, 97], [274, 97]]}" + } + ], + "images": "RH20T_cfg7_task_0066_user_0014_scene_0007_cfg_0007_104122061018#196", + "gt": "[[247, 57], [199, 80], [208, 102], [202, 114], [236, 47], [321, 106], [317, 119], [304, 99], [274, 97], [274, 97]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0090_user_0007_scene_0001_cfg_0001_038522062547#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the wooden block', and now you are performing subtask 'press the wooden block.'\nBegin at [406, 133] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[406, 133], [399, 171], [388, 196], [385, 215], [382, 216], [388, 224], [384, 258], [389, 274], [386, 216], [386, 216]]}" + } + ], + "images": "RH20T_cfg1_task_0090_user_0007_scene_0001_cfg_0001_038522062547#0", + "gt": "[[406, 133], [399, 171], [388, 196], [385, 215], [382, 216], [388, 224], [384, 258], [389, 274], [386, 216], [386, 216]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "11460_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the door', and now you are performing subtask 'pull the door handle to open the door.'\nYou start from [173, 101]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[173, 101], [165, 101], [161, 106], [176, 130], [171, 122], [182, 126], [261, 85], [263, 80], [259, 78], [248, 79]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/11460_exterior_image_1_left#208.jpg", + "gt": "[[173, 101], [165, 101], [161, 106], [176, 130], [171, 122], [182, 126], [261, 85], [263, 80], [259, 78], [248, 79]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "59697_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the objects from the orange bowl to the black pot, then cover the black pot with the glass lid', and now you are performing subtask 'place the item in the black pot.'\nYou begin at [170, 52]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[170, 52], [177, 46], [186, 49], [187, 77], [192, 66], [191, 55], [183, 47], [167, 51], [168, 66], [170, 49]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/59697_exterior_image_1_left#209.jpg", + "gt": "[[170, 52], [177, 46], [186, 49], [187, 77], [192, 66], [191, 55], [183, 47], [167, 51], [168, 66], [170, 49]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0041_user_0001_scene_0006_cfg_0001_038522062547#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'clean the tabletop with a sponge', and now you are performing subtask 'clean the tabletop with a sponge.'\nBegin at [405, 134] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[405, 134], [398, 143], [404, 132], [402, 150], [418, 155], [419, 178], [406, 162], [419, 169], [418, 191], [418, 158]]}" + } + ], + "images": "RH20T_cfg1_task_0041_user_0001_scene_0006_cfg_0001_038522062547#0", + "gt": "[[405, 134], [398, 143], [404, 132], [402, 150], [418, 155], [419, 178], [406, 162], [419, 169], [418, 191], [418, 158]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0003_user_0008_scene_0002_cfg_0001_819112070044#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press three buttons from left to right in sequence', and now you are performing subtask 'press the third button on the desk.'\nBegin at [309, 191] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[309, 191], [300, 188], [305, 192], [287, 205], [290, 214], [289, 196], [328, 168], [345, 175], [376, 172], [394, 159]]}" + } + ], + "images": "RH20T_cfg1_task_0003_user_0008_scene_0002_cfg_0001_819112070044#314", + "gt": "[[309, 191], [300, 188], [305, 192], [287, 205], [290, 214], [289, 196], [328, 168], [345, 175], [376, 172], [394, 159]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "7364_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the cup in the sink', and now you are performing subtask 'put the cup in the sink.'\nYou start from [318, 93]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[318, 93], [301, 83], [269, 85], [185, 136], [208, 113], [198, 114], [193, 123], [200, 114], [217, 123], [237, 113]]}" + } + ], + "images": "7364_exterior_image_2_left#0", + "gt": "[[318, 93], [301, 83], [269, 85], [185, 136], [208, 113], [198, 114], [193, 123], [200, 114], [217, 123], [237, 113]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0125_user_0007_scene_0004_cfg_0004_104422070011#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pull up the lever', and now you are performing subtask 'pull up the rod on the fixture.'\nYou start from [330, 139]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[330, 139], [324, 125], [333, 128], [348, 149], [345, 169], [340, 155], [339, 142], [323, 109], [323, 106], [330, 108]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg4_task_0125_user_0007_scene_0004_cfg_0004_104422070011#102.jpg", + "gt": "[[330, 139], [324, 125], [333, 128], [348, 149], [345, 169], [340, 155], [339, 142], [323, 109], [323, 106], [330, 108]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0060_user_0014_scene_0006_cfg_0006_104122064161#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn the knob to decrease the volume of the speaker', and now you are performing subtask 'turn the knob to decrease the volume of the speaker.'\nYou start from [337, 117]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[337, 117], [358, 149], [364, 164], [354, 159], [359, 164], [355, 180], [361, 171], [359, 159], [346, 136], [318, 103]]}" + } + ], + "images": "RH20T_cfg6_task_0060_user_0014_scene_0006_cfg_0006_104122064161#0", + "gt": "[[337, 117], [358, 149], [364, 164], [354, 159], [359, 164], [355, 180], [361, 171], [359, 159], [346, 136], [318, 103]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg3_task_0007_user_0016_scene_0006_cfg_0003_104122062823#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'holding a small block with the gripper and sweeping it from left to right on the table', and now you are performing subtask 'slide the small block from the left side of the table to the right side.'\nYou begin at [298, 85]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[298, 85], [273, 75], [269, 79], [246, 63], [235, 60], [237, 56], [249, 52], [278, 63], [286, 54], [305, 62]]}" + } + ], + "images": "RH20T_cfg3_task_0007_user_0016_scene_0006_cfg_0003_104122062823#244", + "gt": "[[298, 85], [273, 75], [269, 79], [246, 63], [235, 60], [237, 56], [249, 52], [278, 63], [286, 54], [305, 62]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0017_user_0014_scene_0002_cfg_0007_104122064161#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the pen into the pen holder', and now you are performing subtask 'put the pen into the pen holder.'\nFrom start point [337, 115], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[337, 115], [355, 117], [365, 138], [356, 161], [373, 155], [364, 157], [368, 227], [384, 162], [369, 138], [357, 136]]}" + } + ], + "images": "RH20T_cfg7_task_0017_user_0014_scene_0002_cfg_0007_104122064161#0", + "gt": "[[337, 115], [355, 117], [365, 138], [356, 161], [373, 155], [364, 157], [368, 227], [384, 162], [369, 138], [357, 136]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "4643_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'push the rod on the foosball table to the right', and now you are performing subtask 'push the rod on the foosball table to the right.'\nThe trajectory starts at [179.0, 67.0]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[179.0, 67.0], [186.0, 65.0], [193.0, 66.0], [200.0, 70.0], [205.0, 76.0], [204.0, 82.0], [206.0, 90.0], [232.0, 84.0], [216.0, 72.0], [212.0, 71.0]]}" + } + ], + "images": "4643_exterior_image_1_left#0", + "gt": "[[179.0, 67.0], [186.0, 65.0], [193.0, 66.0], [200.0, 70.0], [205.0, 76.0], [204.0, 82.0], [206.0, 90.0], [232.0, 84.0], [216.0, 72.0], [212.0, 71.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0025_user_0010_scene_0006_cfg_0005_105422061350#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold a piece of paper that has been folded once (one end is pressed down by a heavy object)', and now you are performing subtask 'unfold a piece of paper that has been folded once (one end is pressed down by a heavy object).'\nYour initial coordinate is [276, 47]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[276, 47], [216, 78], [223, 102], [243, 111], [252, 90], [283, 76], [347, 97], [325, 90], [289, 60], [292, 35]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0025_user_0010_scene_0006_cfg_0005_105422061350#0.jpg", + "gt": "[[276, 47], [216, 78], [223, 102], [243, 111], [252, 90], [283, 76], [347, 97], [325, 90], [289, 60], [292, 35]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg2_task_0003_user_0006_scene_0007_cfg_0002_105422061350#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the three buttons in sequence', and now you are performing subtask 'press the gray base red button.'\nThe trajectory starts at [417, 131]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[417, 131], [406, 152], [397, 157], [386, 171], [383, 167], [380, 169], [390, 159], [394, 159], [389, 163], [378, 158]]}" + } + ], + "images": "RH20T_cfg2_task_0003_user_0006_scene_0007_cfg_0002_105422061350#207", + "gt": "[[417, 131], [406, 152], [397, 157], [386, 171], [383, 167], [380, 169], [390, 159], [394, 159], [389, 163], [378, 158]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0009_user_0014_scene_0007_cfg_0001_039422060546#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take out a Hanoi block and throw it aside', and now you are performing subtask 'take out a Hanoi block and throw it aside.'\nBegin at [267, 121] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[267, 121], [328, 81], [313, 44], [318, 18], [310, 50], [334, 51], [336, 92], [326, 70], [322, 76], [327, 153]]}" + } + ], + "images": "RH20T_cfg1_task_0009_user_0014_scene_0007_cfg_0001_039422060546#0", + "gt": "[[267, 121], [328, 81], [313, 44], [318, 18], [310, 50], [334, 51], [336, 92], [326, 70], [322, 76], [327, 153]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0058_user_0015_scene_0003_cfg_0001_819112070044#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn off the power strips', and now you are performing subtask 'press the third button on the power socket, press the fourth button on the power socket.'\nFrom start point [474, 191], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[474, 191], [471, 190], [466, 191], [464, 195], [466, 196], [467, 189], [452, 185], [448, 186], [447, 189], [447, 189]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0058_user_0015_scene_0003_cfg_0001_819112070044#221.jpg", + "gt": "[[474, 191], [471, 190], [466, 191], [464, 195], [466, 196], [467, 189], [452, 185], [448, 186], [447, 189], [447, 189]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0044_user_0014_scene_0005_cfg_0007_104122061330#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up a bag of things', and now you are performing subtask 'pick up a bag of things.'\nWith start location [266, 103], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[266, 103], [277, 118], [287, 178], [283, 199], [272, 227], [274, 230], [277, 228], [277, 208], [264, 131], [243, 88]]}" + } + ], + "images": "RH20T_cfg7_task_0044_user_0014_scene_0005_cfg_0007_104122061330#0", + "gt": "[[266, 103], [277, 118], [287, 178], [283, 199], [272, 227], [274, 230], [277, 228], [277, 208], [264, 131], [243, 88]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0038_user_0020_scene_0001_cfg_0006_104122061018#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the cup', and now you are performing subtask 'pick up the cup.'\nStarting at [367, 28], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[367, 28], [355, 53], [382, 96], [366, 117], [308, 132], [304, 140], [319, 143], [305, 143], [322, 102], [329, 116]]}" + } + ], + "images": "RH20T_cfg6_task_0038_user_0020_scene_0001_cfg_0006_104122061018#0", + "gt": "[[367, 28], [355, 53], [382, 96], [366, 117], [308, 132], [304, 140], [319, 143], [305, 143], [322, 102], [329, 116]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0081_user_0010_scene_0001_cfg_0001_038522062547#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the leg of the glasses (with one hand)', and now you are performing subtask 'pull the other leg of the glasses outward.'\nBegin at [395, 88] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[395, 88], [395, 106], [397, 83], [402, 88], [397, 83], [388, 89], [393, 78], [438, 74], [436, 91], [427, 91]]}" + } + ], + "images": "RH20T_cfg1_task_0081_user_0010_scene_0001_cfg_0001_038522062547#332", + "gt": "[[395, 88], [395, 106], [397, 83], [402, 88], [397, 83], [388, 89], [393, 78], [438, 74], [436, 91], [427, 91]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "45999_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick the purple ball and put it in the bowl', and now you are performing subtask 'pick the purple ball and put it in the bowl.'\nStart at [165, 62]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[165, 62], [189, 85], [187, 105], [171, 121], [173, 107], [194, 102], [216, 109], [221, 126], [219, 119], [197, 102]]}" + } + ], + "images": "45999_exterior_image_2_left#0", + "gt": "[[165, 62], [189, 85], [187, 105], [171, 121], [173, 107], [194, 102], [216, 109], [221, 126], [219, 119], [197, 102]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "32179_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the cup to the right', and now you are performing subtask 'move the cup to the right.'\nYour initial coordinate is [196, 37]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[196, 37], [184, 34], [196, 40], [185, 40], [171, 33], [165, 52], [172, 36], [180, 35], [175, 32], [181, 37]]}" + } + ], + "images": "32179_exterior_image_1_left#0", + "gt": "[[196, 37], [184, 34], [196, 40], [185, 40], [171, 33], [165, 52], [172, 36], [180, 35], [175, 32], [181, 37]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "27100_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the rice cooker, lift the switch on the toaster, then close the rice cooker', and now you are performing subtask 'push the switch on the toaster up.'\nYour starting position is [104.0, 121.5]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[104.0, 121.5], [109.0, 115.5], [119.0, 115.5], [123.0, 121.5], [122.0, 107.5], [118.0, 97.5], [104.0, 103.5], [98.0, 100.5], [85.0, 120.5], [68.0, 135.5]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/27100_exterior_image_1_left#0.jpg", + "gt": "[[104.0, 121.5], [109.0, 115.5], [119.0, 115.5], [123.0, 121.5], [122.0, 107.5], [118.0, 97.5], [104.0, 103.5], [98.0, 100.5], [85.0, 120.5], [68.0, 135.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "58247_exterior_image_1_left#TrajectoryPrediction_Task#10", + "task": "TrajectoryPrediction_Task", + "p_index": 10, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the microwave door, place the bowl inside the microwave', and now you are performing subtask 'transfer the bowl from the countertop to the inside of the microwave.'\nYou start from [174, 60]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[174, 60], [174, 71], [168, 73], [161, 59], [163, 79], [143, 97], [162, 113], [159, 134], [136, 126], [147, 133]]}" + } + ], + "images": "58247_exterior_image_1_left#542", + "gt": "[[174, 60], [174, 71], [168, 73], [161, 59], [163, 79], [143, 97], [162, 113], [159, 134], [136, 126], [147, 133]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "17981_exterior_image_1_left#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the orange cloth', and now you are performing subtask 'fold the cloth on the table for the last time.'\nFrom start point [173, 51], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[173, 51], [167, 80], [171, 89], [185, 83], [171, 92], [189, 84], [166, 101], [172, 68], [197, 72], [181, 49]]}" + } + ], + "images": "17981_exterior_image_1_left#320", + "gt": "[[173, 51], [167, 80], [171, 89], [185, 83], [171, 92], [189, 84], [166, 101], [172, 68], [197, 72], [181, 49]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0045_user_0020_scene_0010_cfg_0006_104122061330#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'place the brush on the pen rack', and now you are performing subtask 'place the brush on the pen rack.'\nYou start from [265, 97]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[265, 97], [275, 106], [278, 160], [310, 225], [302, 217], [338, 103], [358, 92], [355, 68], [357, 83], [340, 89]]}" + } + ], + "images": "RH20T_cfg6_task_0045_user_0020_scene_0010_cfg_0006_104122061330#0", + "gt": "[[265, 97], [275, 106], [278, 160], [310, 225], [302, 217], [338, 103], [358, 92], [355, 68], [357, 83], [340, 89]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "45213_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the orange block on the green block', and now you are performing subtask 'put the orange block on the green block.'\nYou begin at [165, 76]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[165, 76], [169, 81], [172, 98], [171, 101], [167, 103], [164, 83], [167, 82], [171, 84], [170, 86], [170, 84]]}" + } + ], + "images": "45213_exterior_image_1_left#0", + "gt": "[[165, 76], [169, 81], [172, 98], [171, 101], [167, 103], [164, 83], [167, 82], [171, 84], [170, 86], [170, 84]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "61972_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the red mug next to the pot', and now you are performing subtask 'move the red mug next to the pot.'\nStart at [283, 42]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[283, 42], [261, 67], [254, 90], [264, 120], [265, 97], [231, 80], [187, 87], [190, 119], [195, 91], [226, 96]]}" + } + ], + "images": "61972_exterior_image_2_left#0", + "gt": "[[283, 42], [261, 67], [254, 90], [264, 120], [265, 97], [231, 80], [187, 87], [190, 119], [195, 91], [226, 96]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "51525_exterior_image_2_left#TrajectoryPrediction_Task#8", + "task": "TrajectoryPrediction_Task", + "p_index": 8, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close the microwave door, move the pink jar on the counter', and now you are performing subtask 'transfer the pink jar from the microwave to the countertop.'\nWith start location [134, 62], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[134, 62], [139, 64], [125, 72], [119, 78], [120, 82], [131, 92], [132, 95], [130, 94], [128, 83], [116, 72]]}" + } + ], + "images": "51525_exterior_image_2_left#205", + "gt": "[[134, 62], [139, 64], [125, 72], [119, 78], [120, 82], [131, 92], [132, 95], [130, 94], [128, 83], [116, 72]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0094_user_0007_scene_0006_cfg_0005_104122063678#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open a box', and now you are performing subtask 'press the part of the box, press the part of the box.'\nYour starting position is [362, 197]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[362, 197], [386, 204], [404, 202], [430, 194], [428, 203], [430, 191], [387, 184], [345, 188], [334, 191], [333, 189]]}" + } + ], + "images": "RH20T_cfg5_task_0094_user_0007_scene_0006_cfg_0005_104122063678#354", + "gt": "[[362, 197], [386, 204], [404, 202], [430, 194], [428, 203], [430, 191], [387, 184], [345, 188], [334, 191], [333, 189]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "28802_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'switch the extension cord on', and now you are performing subtask 'switch the extension cord on.'\nYou begin at [153, 77]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[153, 77], [146, 69], [152, 52], [191, 52], [197, 60], [193, 54], [204, 58], [206, 66], [178, 69], [173, 61]]}" + } + ], + "images": "28802_exterior_image_1_left#0", + "gt": "[[153, 77], [146, 69], [152, 52], [191, 52], [197, 60], [193, 54], [204, 58], [206, 66], [178, 69], [173, 61]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0094_user_0007_scene_0006_cfg_0005_105422061350#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open a box', and now you are performing subtask 'press the part of the box.'\nFrom start point [204, 62], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[204, 62], [211, 55], [216, 44], [226, 30], [232, 26], [232, 42], [231, 38], [223, 47], [224, 56], [226, 60]]}" + } + ], + "images": "RH20T_cfg5_task_0094_user_0007_scene_0006_cfg_0005_105422061350#201", + "gt": "[[204, 62], [211, 55], [216, 44], [226, 30], [232, 26], [232, 42], [231, 38], [223, 47], [224, 56], [226, 60]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "68797_exterior_image_2_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the peach cloth and sweatshirt from the backrest of the chair', and now you are performing subtask 'place the peach clothing on the seat of the chair.'\nStart at [229, 108]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[229, 108], [252, 94], [267, 94], [316, 138], [318, 125], [308, 105], [256, 53], [264, 68], [244, 94], [244, 94]]}" + } + ], + "images": "68797_exterior_image_2_left#104", + "gt": "[[229, 108], [252, 94], [267, 94], [316, 138], [318, 125], [308, 105], [256, 53], [264, 68], [244, 94], [244, 94]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0104_user_0007_scene_0007_cfg_0005_104122063678#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'drag the plate back after holding it down', and now you are performing subtask 'drag the plate back after holding it down.'\nWith start location [323, 132], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[323, 132], [364, 146], [369, 236], [380, 247], [371, 252], [372, 262], [365, 248], [366, 258], [366, 224], [385, 210]]}" + } + ], + "images": "RH20T_cfg5_task_0104_user_0007_scene_0007_cfg_0005_104122063678#0", + "gt": "[[323, 132], [364, 146], [369, 236], [380, 247], [371, 252], [372, 262], [365, 248], [366, 258], [366, 224], [385, 210]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg3_task_0058_user_0010_scene_0001_cfg_0003_104122062823#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn off the power strips', and now you are performing subtask 'press the button on the second power strip to turn off the power, press the button on the third power strip to turn off the power.'\nYou begin at [400, 186]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[400, 186], [410, 187], [410, 185], [414, 184], [411, 195], [408, 198], [409, 203], [407, 203], [418, 196], [434, 194]]}" + } + ], + "images": "RH20T_cfg3_task_0058_user_0010_scene_0001_cfg_0003_104122062823#284", + "gt": "[[400, 186], [410, 187], [410, 185], [414, 184], [411, 195], [408, 198], [409, 203], [407, 203], [418, 196], [434, 194]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0022_user_0014_scene_0007_cfg_0006_104122064161#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'wave the flag', and now you are performing subtask 'wave the flag.'\nYou begin at [338, 110]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[338, 110], [392, 177], [356, 161], [351, 149], [366, 151], [341, 132], [333, 84], [320, 78], [311, 133], [321, 84]]}" + } + ], + "images": "RH20T_cfg6_task_0022_user_0014_scene_0007_cfg_0006_104122064161#0", + "gt": "[[338, 110], [392, 177], [356, 161], [351, 149], [366, 151], [341, 132], [333, 84], [320, 78], [311, 133], [321, 84]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "64549_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the orange ball to the bottom of the cabinet', and now you are performing subtask 'move the orange ball to the bottom of the cabinet.'\nYour initial coordinate is [274, 12]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[274, 12], [143, 44], [128, 55], [125, 64], [156, 67], [158, 70], [152, 77], [145, 76], [145, 68], [131, 50]]}" + } + ], + "images": "64549_exterior_image_2_left#0", + "gt": "[[274, 12], [143, 44], [128, 55], [125, 64], [156, 67], [158, 70], [152, 77], [145, 76], [145, 68], [131, 50]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "83041_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pour the contents in the clear jug into a bowl', and now you are performing subtask 'pour the contents in the clear jug into a bowl.'\nBegin at [100, 91] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[100, 91], [117, 99], [145, 148], [130, 131], [135, 121], [149, 114], [129, 121], [138, 135], [155, 138], [141, 145]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/83041_exterior_image_1_left#0.jpg", + "gt": "[[100, 91], [117, 99], [145, 148], [130, 131], [135, 121], [149, 114], [129, 121], [138, 135], [155, 138], [141, 145]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "76865_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the black bin and move it to the left', and now you are performing subtask 'pick up the black bin and move it to the left.'\nYou begin at [230, 50]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[230, 50], [206, 35], [185, 40], [175, 52], [181, 45], [179, 38], [151, 34], [141, 44], [139, 56], [151, 23]]}" + } + ], + "images": "76865_exterior_image_2_left#0", + "gt": "[[230, 50], [206, 35], [185, 40], [175, 52], [181, 45], [179, 38], [151, 34], [141, 44], [139, 56], [151, 23]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0061_user_0020_scene_0002_cfg_0007_037522061512#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take everything out of the gift box', and now you are performing subtask 'grab the object in the box, transfer the object from the box to the tabletop.'\nWith start location [213, 144], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[213, 144], [231, 142], [213, 141], [211, 151], [218, 167], [213, 132], [222, 125], [232, 101], [257, 96], [257, 96]]}" + } + ], + "images": "RH20T_cfg7_task_0061_user_0020_scene_0002_cfg_0007_037522061512#292", + "gt": "[[213, 144], [231, 142], [213, 141], [211, 151], [218, 167], [213, 132], [222, 125], [232, 101], [257, 96], [257, 96]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "91740_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'push the plastic wrap off the container, then pick up the container and move it slightly up onto the table', and now you are performing subtask 'push the plastic wrap away from the container.'\nYour starting position is [162, 54]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[162, 54], [149, 81], [146, 108], [160, 111], [152, 121], [149, 102], [178, 119], [224, 83], [214, 112], [214, 112]]}" + } + ], + "images": "91740_exterior_image_2_left#0", + "gt": "[[162, 54], [149, 81], [146, 108], [160, 111], [152, 121], [149, 102], [178, 119], [224, 83], [214, 112], [214, 112]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg3_task_0058_user_0010_scene_0001_cfg_0003_104122062823#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn off the power strips', and now you are performing subtask 'press the button on the third power strip to turn off the power, press the button on the fourth power strip to turn off the power.'\nBegin at [434, 194] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[434, 194], [442, 200], [441, 208], [441, 201], [437, 192], [419, 162], [391, 136], [374, 126], [379, 128], [378, 131]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg3_task_0058_user_0010_scene_0001_cfg_0003_104122062823#323.jpg", + "gt": "[[434, 194], [442, 200], [441, 208], [441, 201], [437, 192], [419, 162], [391, 136], [374, 126], [379, 128], [378, 131]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0007_user_0014_scene_0005_cfg_0007_104122064161#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'push a wooden block towards the distance on the workbench', and now you are performing subtask 'push a wooden block towards the distance on the workbench.'\nThe trajectory starts at [337, 115]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[337, 115], [357, 135], [380, 173], [389, 202], [380, 221], [372, 198], [381, 178], [367, 141], [374, 131], [369, 129]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg7_task_0007_user_0014_scene_0005_cfg_0007_104122064161#0.jpg", + "gt": "[[337, 115], [357, 135], [380, 173], [389, 202], [380, 221], [372, 198], [381, 178], [367, 141], [374, 131], [369, 129]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "34463_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the marker from the cup and place it on the table, then move the cup to the left', and now you are performing subtask 'place the marker on the table.'\nWith start location [166.0, 56.5], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[166.0, 56.5], [192.0, 71.5], [191.0, 82.5], [204.0, 98.5], [199.0, 62.5], [188.0, 54.5], [184.0, 65.5], [187.0, 61.5], [190.0, 64.5], [190.0, 64.5]]}" + } + ], + "images": "34463_exterior_image_1_left#0", + "gt": "[[166.0, 56.5], [192.0, 71.5], [191.0, 82.5], [204.0, 98.5], [199.0, 62.5], [188.0, 54.5], [184.0, 65.5], [187.0, 61.5], [190.0, 64.5], [190.0, 64.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0037_user_0014_scene_0010_cfg_0001_038522062547#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'place the block from the table onto the three blocks standing upright, pick up the block from the right side of the table, transfer the block from the table to the four blocks standing upright, place the block from the table onto the four blocks standing upright.'\nThe trajectory starts at [462, 103]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[462, 103], [471, 77], [468, 68], [455, 84], [448, 103], [457, 77], [477, 95], [474, 97], [471, 69], [465, 63]]}" + } + ], + "images": "RH20T_cfg1_task_0037_user_0014_scene_0010_cfg_0001_038522062547#337", + "gt": "[[462, 103], [471, 77], [468, 68], [455, 84], [448, 103], [457, 77], [477, 95], [474, 97], [471, 69], [465, 63]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "13859_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the contents in the silver pot into the bowl', and now you are performing subtask 'put the contents in the silver pot into the bowl.'\nBegin at [258, 60] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[258, 60], [197, 63], [188, 98], [199, 68], [249, 60], [225, 62], [232, 44], [174, 86], [187, 95], [218, 51]]}" + } + ], + "images": "13859_exterior_image_2_left#0", + "gt": "[[258, 60], [197, 63], [188, 98], [199, 68], [249, 60], [225, 62], [232, 44], [174, 86], [187, 95], [218, 51]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "34036_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the pen from the table and put it in the bowl', and now you are performing subtask 'pick up the pen from the table and put it in the bowl.'\nYour starting position is [213, 53]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[213, 53], [194, 71], [183, 98], [186, 96], [186, 99], [179, 106], [175, 120], [163, 124], [161, 108], [167, 92]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/34036_exterior_image_2_left#0.jpg", + "gt": "[[213, 53], [194, 71], [183, 98], [186, 96], [186, 99], [179, 106], [175, 120], [163, 124], [161, 108], [167, 92]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0034_user_0014_scene_0004_cfg_0001_039422060546#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the squares into a pyramid shape', and now you are performing subtask 'place the second square beside the first square, pick up the third square from the right side of the table, transfer the third square from the right side of the table to the top of the second square, place the third square beside the second square.'\nYou begin at [268, 193]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[268, 193], [354, 243], [336, 219], [279, 187], [283, 180], [271, 174], [270, 192], [269, 182], [284, 178], [315, 191]]}" + } + ], + "images": "RH20T_cfg1_task_0034_user_0014_scene_0004_cfg_0001_039422060546#331", + "gt": "[[268, 193], [354, 243], [336, 219], [279, 187], [283, 180], [271, 174], [270, 192], [269, 182], [284, 178], [315, 191]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0034_user_0020_scene_0001_cfg_0006_104122064161#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the squares into a pyramid shape', and now you are performing subtask 'pick up the fourth square on the top, transfer the fourth square from the top to above the third square, place the fourth square above the third square.'\nWith start location [363, 90], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[363, 90], [383, 70], [386, 75], [384, 95], [382, 83], [378, 100], [347, 135], [356, 167], [370, 139], [368, 118]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg6_task_0034_user_0020_scene_0001_cfg_0006_104122064161#660.jpg", + "gt": "[[363, 90], [383, 70], [386, 75], [384, 95], [382, 83], [378, 100], [347, 135], [356, 167], [370, 139], [368, 118]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg2_task_0034_user_0003_scene_0006_cfg_0002_104122063678#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the squares into a pyramid shape', and now you are performing subtask 'place the second square to the left of the first square, pick up the third square from the large square, transfer the third square from the large square to the right side of the first square.'\nFrom start point [336, 304], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[336, 304], [363, 289], [361, 244], [319, 211], [293, 217], [274, 244], [280, 236], [344, 290], [375, 328], [355, 341]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg2_task_0034_user_0003_scene_0006_cfg_0002_104122063678#370.jpg", + "gt": "[[336, 304], [363, 289], [361, 244], [319, 211], [293, 217], [274, 244], [280, 236], [344, 290], [375, 328], [355, 341]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "50306_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the tissue box on top then place it back on the other box', and now you are performing subtask 'pick up the tissue box on top then place it back on the other box.'\nYour starting position is [228, 87]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[228, 87], [225, 80], [205, 78], [205, 99], [206, 85], [173, 81], [190, 90], [180, 94], [192, 102], [189, 74]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/50306_exterior_image_1_left#0.jpg", + "gt": "[[228, 87], [225, 80], [205, 78], [205, 99], [206, 85], [173, 81], [190, 90], [180, 94], [192, 102], [189, 74]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "29263_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the button on the power strip', and now you are performing subtask 'press the button on the power strip.'\nYou start from [255, 0]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[255, 0], [221, 32], [194, 47], [202, 50], [200, 52], [179, 53], [148, 63], [145, 81], [139, 79], [142, 89]]}" + } + ], + "images": "29263_exterior_image_1_left#0", + "gt": "[[255, 0], [221, 32], [194, 47], [202, 50], [200, 52], [179, 53], [148, 63], [145, 81], [139, 79], [142, 89]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "49096_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the pen on the left side of the bowl', and now you are performing subtask 'put the pen on the left side of the bowl.'\nFrom start point [159.5, 3.5], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[159.5, 3.5], [171.5, 27.5], [170.5, 45.5], [183.5, 86.5], [180.5, 96.5], [189.5, 80.5], [189.5, 62.5], [179.5, 44.5], [171.5, 58.5], [177.5, 42.5]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/49096_exterior_image_1_left#0.jpg", + "gt": "[[159.5, 3.5], [171.5, 27.5], [170.5, 45.5], [183.5, 86.5], [180.5, 96.5], [189.5, 80.5], [189.5, 62.5], [179.5, 44.5], [171.5, 58.5], [177.5, 42.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "19670_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'fold the green towel, move the grey tin to the left, remove the lid from the silver pot', and now you are performing subtask 'push the grey tin to the left on the table.'\nBegin at [164, 68] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[164, 68], [170, 62], [173, 62], [180, 66], [177, 68], [178, 71], [170, 64], [156, 58], [146, 58], [142, 63]]}" + } + ], + "images": "19670_exterior_image_1_left#129", + "gt": "[[164, 68], [170, 62], [173, 62], [180, 66], [177, 68], [178, 71], [170, 64], [156, 58], [146, 58], [142, 63]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "70898_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the tap to the left', and now you are performing subtask 'move the tap to the left.'\nYou start from [107.5, 7.5]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[107.5, 7.5], [131.5, 57.5], [131.5, 67.5], [127.5, 76.5], [143.5, 88.5], [152.5, 82.5], [172.5, 79.5], [152.5, 71.5], [162.5, 78.5], [155.5, 73.5]]}" + } + ], + "images": "70898_exterior_image_1_left#0", + "gt": "[[107.5, 7.5], [131.5, 57.5], [131.5, 67.5], [127.5, 76.5], [143.5, 88.5], [152.5, 82.5], [172.5, 79.5], [152.5, 71.5], [162.5, 78.5], [155.5, 73.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg2_task_0201_user_0007_scene_0008_cfg_0002_104122063678#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'the medium pipette is moved from the table to the holder for medium pipette tips', and now you are performing subtask 'the medium pipette is moved from the table to the holder for medium pipette tips.'\nFrom start point [400, 192], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[400, 192], [396, 191], [392, 180], [387, 178], [389, 183], [411, 183], [412, 187], [400, 193], [394, 183], [390, 187]]}" + } + ], + "images": "RH20T_cfg2_task_0201_user_0007_scene_0008_cfg_0002_104122063678#0", + "gt": "[[400, 192], [396, 191], [392, 180], [387, 178], [389, 183], [411, 183], [412, 187], [400, 193], [394, 183], [390, 187]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "57418_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the marker from the right side of the table to the center of the table', and now you are performing subtask 'move the marker from the right side of the table to the center of the table.'\nYour starting position is [236.0, 6.0]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[236.0, 6.0], [230.0, 36.0], [214.0, 70.0], [216.0, 95.0], [209.0, 94.0], [201.0, 84.0], [192.0, 80.0], [172.0, 83.0], [164.0, 99.0], [165.0, 90.0]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/57418_exterior_image_1_left#0.jpg", + "gt": "[[236.0, 6.0], [230.0, 36.0], [214.0, 70.0], [216.0, 95.0], [209.0, 94.0], [201.0, 84.0], [192.0, 80.0], [172.0, 83.0], [164.0, 99.0], [165.0, 90.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "779_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the drawer then take the plush toy from the drawer and put it in the box then close the drawer', and now you are performing subtask 'pull the drawer.'\nYour initial coordinate is [144, 19]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[144, 19], [151, 65], [172, 99], [198, 116], [174, 121], [176, 84], [192, 116], [158, 111], [154, 90], [164, 85]]}" + } + ], + "images": "779_exterior_image_2_left#0", + "gt": "[[144, 19], [151, 65], [172, 99], [198, 116], [174, 121], [176, 84], [192, 116], [158, 111], [154, 90], [164, 85]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "46001_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the green packet inside the sink', and now you are performing subtask 'put the green packet inside the sink.'\nWith start location [245, 87], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[245, 87], [181, 142], [154, 157], [157, 160], [153, 145], [172, 126], [205, 118], [213, 128], [209, 150], [202, 122]]}" + } + ], + "images": "46001_exterior_image_2_left#0", + "gt": "[[245, 87], [181, 142], [154, 157], [157, 160], [153, 145], [172, 126], [205, 118], [213, 128], [209, 150], [202, 122]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "76544_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the green marker from the table and put it in the bowl', and now you are performing subtask 'remove the green marker from the table and put it in the bowl.'\nBegin at [136.0, 0.0] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[136.0, 0.0], [129.0, 16.0], [146.0, 38.0], [143.0, 54.0], [145.0, 38.0], [131.0, 22.0], [129.0, 31.0], [136.0, 44.0], [126.0, 66.0], [117.0, 42.0]]}" + } + ], + "images": "76544_exterior_image_1_left#0", + "gt": "[[136.0, 0.0], [129.0, 16.0], [146.0, 38.0], [143.0, 54.0], [145.0, 38.0], [131.0, 22.0], [129.0, 31.0], [136.0, 44.0], [126.0, 66.0], [117.0, 42.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "92163_exterior_image_1_left#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the towel', and now you are performing subtask 'unfold the towel on the table one more time.'\nStart at [159, 105]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[159, 105], [138, 122], [144, 104], [134, 104], [139, 121], [147, 110], [114, 104], [130, 108], [129, 98], [115, 110]]}" + } + ], + "images": "92163_exterior_image_1_left#565", + "gt": "[[159, 105], [138, 122], [144, 104], [134, 104], [139, 121], [147, 110], [114, 104], [130, 108], [129, 98], [115, 110]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0033_user_0015_scene_0008_cfg_0001_039422060546#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the block', and now you are performing subtask 'push the square in front of the cardboard to the adjacent square in the middle of the cardboard.'\nThe trajectory starts at [265, 124]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[265, 124], [296, 141], [372, 169], [382, 183], [390, 182], [385, 182], [384, 176], [358, 181], [317, 170], [320, 166]]}" + } + ], + "images": "RH20T_cfg1_task_0033_user_0015_scene_0008_cfg_0001_039422060546#0", + "gt": "[[265, 124], [296, 141], [372, 169], [382, 183], [390, 182], [385, 182], [384, 176], [358, 181], [317, 170], [320, 166]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "29602_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the brush from the table and sweep the paper pieces', and now you are performing subtask 'pick up the brush from the table and sweep the paper pieces.'\nThe trajectory starts at [132, 101]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[132, 101], [157, 112], [154, 161], [145, 136], [179, 144], [204, 127], [165, 130], [155, 156], [160, 139], [160, 139]]}" + } + ], + "images": "29602_exterior_image_1_left#0", + "gt": "[[132, 101], [157, 112], [154, 161], [145, 136], [179, 144], [204, 127], [165, 130], [155, 156], [160, 139], [160, 139]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "48366_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the black pen in the grey bowl', and now you are performing subtask 'put the black pen in the grey bowl.'\nYour initial coordinate is [24, 20]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[24, 20], [65, 53], [104, 90], [117, 105], [120, 115], [119, 112], [126, 105], [161, 84], [174, 85], [179, 96]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/48366_exterior_image_1_left#0.jpg", + "gt": "[[24, 20], [65, 53], [104, 90], [117, 105], [120, 115], [119, 112], [126, 105], [161, 84], [174, 85], [179, 96]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "10276_exterior_image_2_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close the tap, put the bowl on the dish rack, and open the sink plug', and now you are performing subtask 'place the sink plug in the sink.'\nBegin at [202, 64] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[202, 64], [201, 70], [209, 67], [222, 73], [218, 72], [204, 83], [204, 91], [196, 102], [206, 92], [220, 88]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/10276_exterior_image_2_left#364.jpg", + "gt": "[[202, 64], [201, 70], [209, 67], [222, 73], [218, 72], [204, 83], [204, 91], [196, 102], [206, 92], [220, 88]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0032_user_0016_scene_0006_cfg_0004_104122062823#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'slide the outer casing onto the gift box', and now you are performing subtask 'slide the outer casing onto the gift box.'\nYour initial coordinate is [290, 0]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[290, 0], [304, 0], [300, 134], [236, 80], [266, 96], [206, 57], [167, 52], [198, 69], [229, 121], [301, 100]]}" + } + ], + "images": "RH20T_cfg4_task_0032_user_0016_scene_0006_cfg_0004_104122062823#0", + "gt": "[[290, 0], [304, 0], [300, 134], [236, 80], [266, 96], [206, 57], [167, 52], [198, 69], [229, 121], [301, 100]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "65067_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the lever on the right side of the toaster', and now you are performing subtask 'press the lever on the right side of the toaster.'\nThe trajectory starts at [151.0, 70.0]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[151.0, 70.0], [171.0, 66.0], [187.0, 79.0], [189.0, 89.0], [189.0, 93.0], [184.0, 82.0], [174.0, 69.0], [165.0, 65.0], [150.0, 52.0], [150.0, 52.0]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/65067_exterior_image_1_left#0.jpg", + "gt": "[[151.0, 70.0], [171.0, 66.0], [187.0, 79.0], [189.0, 89.0], [189.0, 93.0], [184.0, 82.0], [174.0, 69.0], [165.0, 65.0], [150.0, 52.0], [150.0, 52.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0033_user_0010_scene_0010_cfg_0005_104122063678#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'grasp a small block to sweep the other small block into the designated position', and now you are performing subtask 'push another block towards the mark.'\nStarting at [397, 228], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[397, 228], [397, 238], [388, 237], [386, 221], [387, 251], [420, 231], [419, 252], [405, 251], [403, 281], [373, 274]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0033_user_0010_scene_0010_cfg_0005_104122063678#536.jpg", + "gt": "[[397, 228], [397, 238], [388, 237], [386, 221], [387, 251], [420, 231], [419, 252], [405, 251], [403, 281], [373, 274]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "86543_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the glass lid from the black pot', and now you are performing subtask 'remove the glass lid from the black pot.'\nWith start location [201, 17], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[201, 17], [162, 68], [159, 113], [160, 104], [144, 91], [111, 88], [80, 104], [85, 133], [93, 132], [93, 132]]}" + } + ], + "images": "86543_exterior_image_2_left#0", + "gt": "[[201, 17], [162, 68], [159, 113], [160, 104], [144, 91], [111, 88], [80, 104], [85, 133], [93, 132], [93, 132]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0038_user_0014_scene_0006_cfg_0006_104122064161#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the cup', and now you are performing subtask 'pick up the cup.'\nBegin at [338, 110] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[338, 110], [336, 89], [336, 92], [340, 91], [349, 96], [356, 107], [374, 152], [373, 177], [368, 139], [367, 99]]}" + } + ], + "images": "RH20T_cfg6_task_0038_user_0014_scene_0006_cfg_0006_104122064161#0", + "gt": "[[338, 110], [336, 89], [336, 92], [340, 91], [349, 96], [356, 107], [374, 152], [373, 177], [368, 139], [367, 99]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "48523_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pour the contents of the black pot into the grey plate, and then put the pot back on the table', and now you are performing subtask 'pour the contents of the black pot into the grey plate, and then put the pot back on the table.'\nThe trajectory starts at [205, 105]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[205, 105], [201, 117], [215, 110], [216, 91], [219, 118], [241, 126], [214, 78], [195, 111], [204, 117], [230, 86]]}" + } + ], + "images": "48523_exterior_image_2_left#0", + "gt": "[[205, 105], [201, 117], [215, 110], [216, 91], [219, 118], [241, 126], [214, 78], [195, 111], [204, 117], [230, 86]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "4673_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'transfer the marker from the black cup to the table', and now you are performing subtask 'transfer the marker from the black cup to the table.'\nYou start from [153.0, 6.5]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[153.0, 6.5], [132.0, 19.5], [135.0, 19.5], [139.0, 33.5], [139.0, 56.5], [149.0, 59.5], [144.0, 61.5], [141.0, 33.5], [163.0, 78.5], [163.0, 65.5]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/4673_exterior_image_1_left#0.jpg", + "gt": "[[153.0, 6.5], [132.0, 19.5], [135.0, 19.5], [139.0, 33.5], [139.0, 56.5], [149.0, 59.5], [144.0, 61.5], [141.0, 33.5], [163.0, 78.5], [163.0, 65.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "81736_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close the middle drawer doors', and now you are performing subtask 'push the handle of the right-side middle cabinet door to close the cabinet door.'\nYour starting position is [136, 51]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[136, 51], [133, 50], [129, 46], [130, 45], [139, 42], [145, 45], [148, 62], [157, 70], [151, 71], [144, 67]]}" + } + ], + "images": "81736_exterior_image_1_left#96", + "gt": "[[136, 51], [133, 50], [129, 46], [130, 45], [139, 42], [145, 45], [148, 62], [157, 70], [151, 71], [144, 67]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0020_user_0016_scene_0002_cfg_0004_036422060909#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn on the desk lamp by pressing the button', and now you are performing subtask 'press the button on the desk lamp to turn on the light.'\nYou start from [337, 78]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[337, 78], [303, 93], [311, 103], [293, 141], [306, 143], [298, 132], [290, 133], [296, 153], [292, 197], [315, 175]]}" + } + ], + "images": "RH20T_cfg4_task_0020_user_0016_scene_0002_cfg_0004_036422060909#0", + "gt": "[[337, 78], [303, 93], [311, 103], [293, 141], [306, 143], [298, 132], [290, 133], [296, 153], [292, 197], [315, 175]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0071_user_0020_scene_0002_cfg_0006_104122064161#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close a sliding window', and now you are performing subtask 'pull the handle of the right sliding window to close the window, push the right sliding window to completely close.'\nYou start from [338, 111]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[338, 111], [352, 143], [349, 179], [371, 206], [371, 219], [352, 207], [365, 210], [374, 218], [368, 221], [372, 218]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg6_task_0071_user_0020_scene_0002_cfg_0006_104122064161#0.jpg", + "gt": "[[338, 111], [352, 143], [349, 179], [371, 206], [371, 219], [352, 207], [365, 210], [374, 218], [368, 221], [372, 218]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg3_task_0038_user_0010_scene_0003_cfg_0003_104122062823#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the cup to the top of the cup rack and then place it down', and now you are performing subtask 'move the cup to the top of the cup rack and then place it down.'\nFrom start point [197, 41], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[197, 41], [218, 18], [235, 34], [233, 84], [195, 111], [197, 128], [169, 131], [158, 154], [187, 102], [164, 82]]}" + } + ], + "images": "RH20T_cfg3_task_0038_user_0010_scene_0003_cfg_0003_104122062823#0", + "gt": "[[197, 41], [218, 18], [235, 34], [233, 84], [195, 111], [197, 128], [169, 131], [158, 154], [187, 102], [164, 82]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0023_user_0010_scene_0007_cfg_0005_104122061850#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn on the power strip by pressing the button', and now you are performing subtask 'turn on the power strip by pressing the button.'\nStarting at [305, 50], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[305, 50], [283, 75], [299, 61], [315, 60], [330, 82], [306, 94], [314, 65], [329, 66], [326, 72], [298, 74]]}" + } + ], + "images": "RH20T_cfg5_task_0023_user_0010_scene_0007_cfg_0005_104122061850#0", + "gt": "[[305, 50], [283, 75], [299, 61], [315, 60], [330, 82], [306, 94], [314, 65], [329, 66], [326, 72], [298, 74]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg2_task_0201_user_0007_scene_0008_cfg_0002_104122061850#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'the medium pipette is moved from the table to the holder for medium pipette tips', and now you are performing subtask 'the medium pipette is moved from the table to the holder for medium pipette tips.'\nBegin at [338, 109] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[338, 109], [352, 96], [360, 94], [368, 100], [410, 107], [415, 111], [405, 114], [392, 104], [370, 101], [366, 104]]}" + } + ], + "images": "RH20T_cfg2_task_0201_user_0007_scene_0008_cfg_0002_104122061850#0", + "gt": "[[338, 109], [352, 96], [360, 94], [368, 100], [410, 107], [415, 111], [405, 114], [392, 104], [370, 101], [366, 104]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "43916_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the lid from the table and put it on the pot', and now you are performing subtask 'pick up the lid from the table and put it on the pot.'\nFrom start point [29.0, 39.5], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[29.0, 39.5], [72.0, 30.5], [116.0, 47.5], [177.0, 121.5], [169.0, 120.5], [189.0, 158.5], [136.0, 116.5], [135.0, 126.5], [126.0, 126.5], [124.0, 113.5]]}" + } + ], + "images": "43916_exterior_image_1_left#0", + "gt": "[[29.0, 39.5], [72.0, 30.5], [116.0, 47.5], [177.0, 121.5], [169.0, 120.5], [189.0, 158.5], [136.0, 116.5], [135.0, 126.5], [126.0, 126.5], [124.0, 113.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg3_task_0058_user_0010_scene_0010_cfg_0003_104122063550#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn off the power strips', and now you are performing subtask 'press the button on the power strip above, press the button on the power strip above.'\nYou begin at [395, 182]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[395, 182], [393, 180], [396, 181], [394, 183], [394, 185], [394, 184], [391, 186], [390, 185], [403, 179], [418, 179]]}" + } + ], + "images": "RH20T_cfg3_task_0058_user_0010_scene_0010_cfg_0003_104122063550#88", + "gt": "[[395, 182], [393, 180], [396, 181], [394, 183], [394, 185], [394, 184], [391, 186], [390, 185], [403, 179], [418, 179]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "56042_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the mug to the left', and now you are performing subtask 'move the mug to the left.'\nYou begin at [172.0, 1.5]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[172.0, 1.5], [173.0, 31.5], [156.0, 48.5], [161.0, 58.5], [126.0, 54.5], [108.0, 60.5], [101.0, 73.5], [100.0, 104.5], [107.0, 97.5], [113.0, 69.5]]}" + } + ], + "images": "56042_exterior_image_1_left#0", + "gt": "[[172.0, 1.5], [173.0, 31.5], [156.0, 48.5], [161.0, 58.5], [126.0, 54.5], [108.0, 60.5], [101.0, 73.5], [100.0, 104.5], [107.0, 97.5], [113.0, 69.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "20823_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the banana inside the first drawer from the right then close the drawer', and now you are performing subtask 'push the first drawer on the right.'\nStart at [237.0, 149.0]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[237.0, 149.0], [245.0, 161.0], [243.0, 166.0], [204.0, 169.0], [211.0, 163.0], [215.0, 147.0], [211.0, 127.0], [208.0, 132.0], [208.0, 129.0], [227.0, 104.0]]}" + } + ], + "images": "20823_exterior_image_1_left#251", + "gt": "[[237.0, 149.0], [245.0, 161.0], [243.0, 166.0], [204.0, 169.0], [211.0, 163.0], [215.0, 147.0], [211.0, 127.0], [208.0, 132.0], [208.0, 129.0], [227.0, 104.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "66608_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'place the spoon with the other cutlery then put the red ball on the plate', and now you are performing subtask 'transfer the spoon from the table to the position with the other cutlery.'\nWith start location [278, 92], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[278, 92], [259, 6], [275, 38], [264, 23], [246, 39], [202, 138], [199, 109], [195, 102], [191, 109], [195, 97]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/66608_exterior_image_1_left#0.jpg", + "gt": "[[278, 92], [259, 6], [275, 38], [264, 23], [246, 39], [202, 138], [199, 109], [195, 102], [191, 109], [195, 97]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "24957_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the purple object in the bowl', and now you are performing subtask 'put the purple object in the bowl.'\nYour starting position is [182, 0]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[182, 0], [233, 43], [221, 100], [207, 55], [198, 43], [190, 38], [176, 41], [162, 71], [157, 47], [161, 52]]}" + } + ], + "images": "24957_exterior_image_1_left#0", + "gt": "[[182, 0], [233, 43], [221, 100], [207, 55], [198, 43], [190, 38], [176, 41], [162, 71], [157, 47], [161, 52]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "25857_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the second drawer from the right then put the left straw in the drawer', and now you are performing subtask 'pick up the straw from the tabletop.'\nBegin at [123.5, 85.5] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[123.5, 85.5], [117.5, 77.5], [111.5, 86.5], [122.5, 113.5], [146.5, 111.5], [122.5, 133.5], [107.5, 125.5], [104.5, 111.5], [120.5, 76.5], [138.5, 62.5]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/25857_exterior_image_1_left#0.jpg", + "gt": "[[123.5, 85.5], [117.5, 77.5], [111.5, 86.5], [122.5, 113.5], [146.5, 111.5], [122.5, 133.5], [107.5, 125.5], [104.5, 111.5], [120.5, 76.5], [138.5, 62.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "951_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the drawer, then put the pineapple and banana plush toys in the drawer, then close the drawer', and now you are performing subtask 'pick up the banana plush toy from the countertop.'\nWith start location [132.0, 47.5], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[132.0, 47.5], [134.0, 55.5], [118.0, 59.5], [117.0, 66.5], [122.0, 54.5], [137.0, 50.5], [170.0, 74.5], [155.0, 57.5], [139.0, 48.5], [128.0, 55.5]]}" + } + ], + "images": "951_exterior_image_1_left#220", + "gt": "[[132.0, 47.5], [134.0, 55.5], [118.0, 59.5], [117.0, 66.5], [122.0, 54.5], [137.0, 50.5], [170.0, 74.5], [155.0, 57.5], [139.0, 48.5], [128.0, 55.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "11026_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the purple plushy in the box', and now you are performing subtask 'put the purple plushy in the box.'\nYour starting position is [173, 88]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[173, 88], [173, 91], [177, 92], [173, 90], [175, 104], [183, 85], [207, 60], [220, 60], [223, 64], [212, 58]]}" + } + ], + "images": "11026_exterior_image_2_left#0", + "gt": "[[173, 88], [173, 91], [177, 92], [173, 90], [175, 104], [183, 85], [207, 60], [220, 60], [223, 64], [212, 58]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "9567_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the marker out of the pot and put it on the table', and now you are performing subtask 'take the marker out of the pot and put it on the table.'\nWith start location [98.0, 35.0], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[98.0, 35.0], [97.0, 46.0], [119.0, 37.0], [147.0, 47.0], [162.0, 65.0], [164.0, 83.0], [165.0, 51.0], [151.0, 63.0], [151.0, 83.0], [147.0, 75.0]]}" + } + ], + "images": "9567_exterior_image_1_left#0", + "gt": "[[98.0, 35.0], [97.0, 46.0], [119.0, 37.0], [147.0, 47.0], [162.0, 65.0], [164.0, 83.0], [165.0, 51.0], [151.0, 63.0], [151.0, 83.0], [147.0, 75.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "40628_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'use the wooden spatula to mix the contents in the right silver dish', and now you are performing subtask 'use the wooden spatula to mix the contents in the right silver dish.'\nStarting at [114.5, 56.5], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[114.5, 56.5], [113.5, 82.5], [119.5, 87.5], [148.5, 32.5], [148.5, 63.5], [165.5, 71.5], [154.5, 75.5], [130.5, 50.5], [131.5, 72.5], [121.5, 62.5]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/40628_exterior_image_1_left#0.jpg", + "gt": "[[114.5, 56.5], [113.5, 82.5], [119.5, 87.5], [148.5, 32.5], [148.5, 63.5], [165.5, 71.5], [154.5, 75.5], [130.5, 50.5], [131.5, 72.5], [121.5, 62.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "49479_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the lid off the pot', and now you are performing subtask 'take the lid off the pot.'\nStarting at [46, 3], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[46, 3], [132, 70], [159, 100], [131, 49], [124, 48], [130, 55], [131, 70], [137, 80], [127, 65], [127, 65]]}" + } + ], + "images": "49479_exterior_image_1_left#0", + "gt": "[[46, 3], [132, 70], [159, 100], [131, 49], [124, 48], [130, 55], [131, 70], [137, 80], [127, 65], [127, 65]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg3_task_0035_user_0010_scene_0001_cfg_0003_104422070011#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up a small block', and now you are performing subtask 'pick up a small block.'\nYour initial coordinate is [328, 107]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[328, 107], [334, 112], [307, 125], [309, 106], [304, 137], [250, 167], [259, 188], [247, 229], [225, 220], [220, 184]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg3_task_0035_user_0010_scene_0001_cfg_0003_104422070011#0.jpg", + "gt": "[[328, 107], [334, 112], [307, 125], [309, 106], [304, 137], [250, 167], [259, 188], [247, 229], [225, 220], [220, 184]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "86720_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take out a straw from the open drawer and put it on the countertop, then close the open drawer', and now you are performing subtask 'throw the straw on the countertop.'\nStart at [146, 90]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[146, 90], [144, 102], [167, 107], [187, 128], [169, 116], [173, 97], [185, 74], [198, 77], [167, 90], [167, 90]]}" + } + ], + "images": "86720_exterior_image_1_left#0", + "gt": "[[146, 90], [144, 102], [167, 107], [187, 128], [169, 116], [173, 97], [185, 74], [198, 77], [167, 90], [167, 90]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "23301_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the checkered shirt to the left side of the bed', and now you are performing subtask 'move the checkered shirt to the left side of the bed.'\nBegin at [156, 50] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[156, 50], [193, 40], [200, 88], [220, 111], [216, 120], [157, 63], [194, 94], [170, 105], [150, 86], [183, 100]]}" + } + ], + "images": "23301_exterior_image_2_left#0", + "gt": "[[156, 50], [193, 40], [200, 88], [220, 111], [216, 120], [157, 63], [194, 94], [170, 105], [150, 86], [183, 100]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg3_task_0006_user_0016_scene_0004_cfg_0003_104122062823#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'push the small block to the left', and now you are performing subtask 'push the small block to the left.'\nYou start from [242, 0]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[242, 0], [325, 0], [341, 13], [354, 58], [329, 84], [363, 101], [261, 86], [278, 85], [293, 63], [314, 74]]}" + } + ], + "images": "RH20T_cfg3_task_0006_user_0016_scene_0004_cfg_0003_104122062823#0", + "gt": "[[242, 0], [325, 0], [341, 13], [354, 58], [329, 84], [363, 101], [261, 86], [278, 85], [293, 63], [314, 74]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0085_user_0015_scene_0002_cfg_0001_039422060546#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the bubble ring from the assembled bubble ring and ball', and now you are performing subtask 'remove the bubble ring from the assembled bubble ring and ball.'\nThe trajectory starts at [265, 123]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[265, 123], [311, 126], [345, 152], [364, 149], [321, 189], [310, 216], [318, 238], [304, 200], [315, 235], [299, 264]]}" + } + ], + "images": "RH20T_cfg1_task_0085_user_0015_scene_0002_cfg_0001_039422060546#0", + "gt": "[[265, 123], [311, 126], [345, 152], [364, 149], [321, 189], [310, 216], [318, 238], [304, 200], [315, 235], [299, 264]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "20196_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'arrange the cushions in front of the armrest', and now you are performing subtask 'place the second cushion in front of the first cushion, against the armrest.'\nStart at [166, 103]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[166, 103], [179, 113], [167, 125], [166, 107], [192, 93], [215, 105], [208, 95], [175, 99], [167, 123], [237, 109]]}" + } + ], + "images": "20196_exterior_image_1_left#172", + "gt": "[[166, 103], [179, 113], [167, 125], [166, 107], [192, 93], [215, 105], [208, 95], [175, 99], [167, 123], [237, 109]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "79812_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the bottle lying on the stove and place it upright on the countertop', and now you are performing subtask 'pick up the bottle lying on the stove and place it upright on the countertop.'\nYour initial coordinate is [279, 70]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[279, 70], [262, 86], [266, 87], [244, 102], [238, 126], [240, 112], [220, 101], [210, 113], [216, 113], [215, 103]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/79812_exterior_image_1_left#0.jpg", + "gt": "[[279, 70], [262, 86], [266, 87], [244, 102], [238, 126], [240, 112], [220, 101], [210, 113], [216, 113], [215, 103]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "81736_exterior_image_1_left#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close the middle drawer doors', and now you are performing subtask 'push the handle of the left-side middle cabinet door to close the cabinet door.'\nStarting at [145, 56], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[145, 56], [114, 41], [85, 49], [92, 54], [90, 51], [100, 50], [114, 62], [128, 62], [133, 56], [127, 56]]}" + } + ], + "images": "81736_exterior_image_1_left#193", + "gt": "[[145, 56], [114, 41], [85, 49], [92, 54], [90, 51], [100, 50], [114, 62], [128, 62], [133, 56], [127, 56]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg3_task_0058_user_0010_scene_0006_cfg_0003_104122062823#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn off the power strips', and now you are performing subtask 'press the third button of the power strip.'\nBegin at [136, 46] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[136, 46], [134, 44], [134, 43], [136, 46], [136, 53], [135, 48], [135, 45], [136, 45], [132, 46], [129, 50]]}" + } + ], + "images": "RH20T_cfg3_task_0058_user_0010_scene_0006_cfg_0003_104122062823#193", + "gt": "[[136, 46], [134, 44], [134, 43], [136, 46], [136, 53], [135, 48], [135, 45], [136, 45], [132, 46], [129, 50]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "3391_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the left bottom cabinet door', and now you are performing subtask 'open the left bottom cabinet door.'\nYou start from [121.5, 3.5]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[121.5, 3.5], [130.5, 19.5], [127.5, 90.5], [137.5, 87.5], [142.5, 91.5], [136.5, 84.5], [126.5, 85.5], [80.5, 69.5], [73.5, 64.5], [71.5, 67.5]]}" + } + ], + "images": "3391_exterior_image_1_left#0", + "gt": "[[121.5, 3.5], [130.5, 19.5], [127.5, 90.5], [137.5, 87.5], [142.5, 91.5], [136.5, 84.5], [126.5, 85.5], [80.5, 69.5], [73.5, 64.5], [71.5, 67.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0132_user_0020_scene_0004_cfg_0006_104122064161#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks into a cross shape', and now you are performing subtask 'place the first block and the second block on top of the third block, pick up the fourth block from the table, twist the block counterclockwise, transfer the fourth block from the table to on top of the first block and the second block, place the fourth block on top of the first block and the second block.'\nStarting at [363, 240], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[363, 240], [369, 191], [377, 208], [378, 164], [369, 165], [357, 219], [365, 230], [363, 177], [355, 154], [336, 145]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg6_task_0132_user_0020_scene_0004_cfg_0006_104122064161#715.jpg", + "gt": "[[363, 240], [369, 191], [377, 208], [378, 164], [369, 165], [357, 219], [365, 230], [363, 177], [355, 154], [336, 145]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "16560_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'wipe the left side of the table with the green towel', and now you are performing subtask 'wipe the left side of the table with the green towel.'\nBegin at [33.0, 5.5] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[33.0, 5.5], [94.0, 57.5], [98.0, 70.5], [92.0, 69.5], [110.0, 91.5], [95.0, 122.5], [100.0, 126.5], [111.0, 105.5], [105.0, 139.5], [106.0, 110.5]]}" + } + ], + "images": "16560_exterior_image_1_left#0", + "gt": "[[33.0, 5.5], [94.0, 57.5], [98.0, 70.5], [92.0, 69.5], [110.0, 91.5], [95.0, 122.5], [100.0, 126.5], [111.0, 105.5], [105.0, 139.5], [106.0, 110.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0028_user_0020_scene_0003_cfg_0007_037522061512#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'grasp the handle and close the drawer', and now you are performing subtask 'grasp the handle and close the drawer.'\nThe trajectory starts at [261, 86]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[261, 86], [243, 127], [188, 164], [175, 222], [176, 194], [186, 173], [182, 168], [190, 142], [209, 112], [229, 101]]}" + } + ], + "images": "RH20T_cfg7_task_0028_user_0020_scene_0003_cfg_0007_037522061512#0", + "gt": "[[261, 86], [243, 127], [188, 164], [175, 222], [176, 194], [186, 173], [182, 168], [190, 142], [209, 112], [229, 101]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "47997_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'use the brush to sweep the candy on the table to the right', and now you are performing subtask 'use the brush to sweep the candy on the table to the right.'\nYour initial coordinate is [103, 91]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[103, 91], [122, 70], [171, 65], [207, 89], [199, 94], [311, 137], [233, 91], [216, 88], [218, 94], [209, 96]]}" + } + ], + "images": "47997_exterior_image_1_left#0", + "gt": "[[103, 91], [122, 70], [171, 65], [207, 89], [199, 94], [311, 137], [233, 91], [216, 88], [218, 94], [209, 96]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0034_user_0014_scene_0004_cfg_0001_039422060546#TrajectoryPrediction_Task#10", + "task": "TrajectoryPrediction_Task", + "p_index": 10, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the squares into a pyramid shape', and now you are performing subtask 'place the fifth square on top of the second square, pick up the sixth square on the table, move the sixth square from the table to the square, place the sixth square onto the square.'\nYou begin at [262, 162]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[262, 162], [333, 171], [362, 163], [369, 174], [366, 190], [278, 167], [259, 175], [240, 145], [284, 124], [344, 120]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0034_user_0014_scene_0004_cfg_0001_039422060546#821.jpg", + "gt": "[[262, 162], [333, 171], [362, 163], [369, 174], [366, 190], [278, 167], [259, 175], [240, 145], [284, 124], [344, 120]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0070_user_0020_scene_0008_cfg_0006_104122061602#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open a sliding window', and now you are performing subtask 'slide the sliding window to the left to open.'\nYour initial coordinate is [416, 165]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[416, 165], [436, 175], [428, 162], [412, 159], [409, 163], [422, 167], [424, 144], [417, 113], [421, 101], [432, 102]]}" + } + ], + "images": "RH20T_cfg6_task_0070_user_0020_scene_0008_cfg_0006_104122061602#278", + "gt": "[[416, 165], [436, 175], [428, 162], [412, 159], [409, 163], [422, 167], [424, 144], [417, 113], [421, 101], [432, 102]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "3613_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the brown object from the pot', and now you are performing subtask 'remove the brown object from the pot.'\nWith start location [282, 2], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[282, 2], [211, 36], [198, 62], [184, 72], [188, 75], [206, 57], [220, 55], [230, 61], [222, 82], [242, 73]]}" + } + ], + "images": "3613_exterior_image_2_left#0", + "gt": "[[282, 2], [211, 36], [198, 62], [184, 72], [188, 75], [206, 57], [220, 55], [230, 61], [222, 82], [242, 73]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "7719_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the green bag of snacks in the sink', and now you are performing subtask 'put the green bag of snacks in the sink.'\nStarting at [104, 87], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[104, 87], [97, 115], [100, 140], [110, 145], [132, 128], [152, 137], [158, 148], [156, 158], [143, 146], [113, 141]]}" + } + ], + "images": "7719_exterior_image_1_left#0", + "gt": "[[104, 87], [97, 115], [100, 140], [110, 145], [132, 128], [152, 137], [158, 148], [156, 158], [143, 146], [113, 141]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "42963_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'cover the pot, turn the faucet clockwise', and now you are performing subtask 'pick up the lid from the stove.'\nWith start location [101, 0], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[101, 0], [112, 32], [105, 30], [110, 41], [109, 68], [119, 84], [112, 91], [111, 94], [116, 92], [112, 91]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/42963_exterior_image_1_left#0.jpg", + "gt": "[[101, 0], [112, 32], [105, 30], [110, 41], [109, 68], [119, 84], [112, 91], [111, 94], [116, 92], [112, 91]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0066_user_0014_scene_0005_cfg_0001_038522062547#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with large Megabloks for the nth time with n blocks', and now you are performing subtask 'pick up the first Megablock from the left side of the table, place the first Megablock on the green base.'\nYou begin at [406, 132]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[406, 132], [432, 220], [473, 272], [460, 270], [468, 260], [451, 234], [423, 219], [436, 220], [400, 216], [442, 223]]}" + } + ], + "images": "RH20T_cfg1_task_0066_user_0014_scene_0005_cfg_0001_038522062547#0", + "gt": "[[406, 132], [432, 220], [473, 272], [460, 270], [468, 260], [451, 234], [423, 219], [436, 220], [400, 216], [442, 223]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0016_user_0014_scene_0001_cfg_0001_819112070044#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'hit the pool ball', and now you are performing subtask 'pick up the pool ball from the surface.'\nBegin at [246, 252] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[246, 252], [249, 246], [247, 242], [245, 244], [246, 237], [248, 247], [239, 259], [245, 264], [285, 256], [284, 251]]}" + } + ], + "images": "RH20T_cfg1_task_0016_user_0014_scene_0001_cfg_0001_819112070044#231", + "gt": "[[246, 252], [249, 246], [247, 242], [245, 244], [246, 237], [248, 247], [239, 259], [245, 264], [285, 256], [284, 251]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0025_user_0020_scene_0008_cfg_0007_037522061512#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold a piece of paper that has been folded once (one end is pressed down by a weight)', and now you are performing subtask 'pull the paper on the table, press the paper on the table.'\nFrom start point [223, 189], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[223, 189], [219, 194], [210, 186], [198, 200], [184, 201], [180, 204], [186, 209], [183, 198], [200, 168], [210, 156]]}" + } + ], + "images": "RH20T_cfg7_task_0025_user_0020_scene_0008_cfg_0007_037522061512#224", + "gt": "[[223, 189], [219, 194], [210, 186], [198, 200], [184, 201], [180, 204], [186, 209], [183, 198], [200, 168], [210, 156]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "57515_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove a tissue from the tissue box and put it on the table', and now you are performing subtask 'remove a tissue from the tissue box and put it on the table.'\nStart at [169, 15]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[169, 15], [153, 60], [157, 68], [145, 69], [129, 49], [159, 46], [161, 41], [124, 38], [113, 42], [122, 53]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/57515_exterior_image_2_left#0.jpg", + "gt": "[[169, 15], [153, 60], [157, 68], [145, 69], [129, 49], [159, 46], [161, 41], [124, 38], [113, 42], [122, 53]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0118_user_0007_scene_0010_cfg_0005_036422060215#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn on the water tap', and now you are performing subtask 'turn on the water tap.'\nStart at [286, 106]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[286, 106], [280, 94], [269, 90], [250, 118], [226, 124], [229, 116], [249, 105], [258, 125], [268, 121], [266, 128]]}" + } + ], + "images": "RH20T_cfg5_task_0118_user_0007_scene_0010_cfg_0005_036422060215#0", + "gt": "[[286, 106], [280, 94], [269, 90], [250, 118], [226, 124], [229, 116], [249, 105], [258, 125], [268, 121], [266, 128]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "68303_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the carrot plush toy backwards, move the blue towel backwards', and now you are performing subtask 'place the blue object on the back side of the table.'\nWith start location [110.5, 100.5], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[110.5, 100.5], [109.5, 101.5], [112.5, 105.5], [120.5, 107.5], [115.5, 100.5], [115.5, 87.5], [117.5, 84.5], [119.5, 84.5], [121.5, 85.5], [122.5, 89.5]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/68303_exterior_image_1_left#78.jpg", + "gt": "[[110.5, 100.5], [109.5, 101.5], [112.5, 105.5], [120.5, 107.5], [115.5, 100.5], [115.5, 87.5], [117.5, 84.5], [119.5, 84.5], [121.5, 85.5], [122.5, 89.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "32537_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the black dish from the sink onto the rack', and now you are performing subtask 'put the black dish from the sink onto the rack.'\nYour initial coordinate is [93, 60]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[93, 60], [111, 65], [93, 60], [116, 73], [164, 150], [119, 56], [135, 44], [124, 65], [152, 87], [129, 111]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/32537_exterior_image_2_left#0.jpg", + "gt": "[[93, 60], [111, 65], [93, 60], [116, 73], [164, 150], [119, 56], [135, 44], [124, 65], [152, 87], [129, 111]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg2_task_0034_user_0003_scene_0006_cfg_0002_104122061850#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the squares into a pyramid shape', and now you are performing subtask 'place the second square to the left of the first square, pick up the third square from the large square, transfer the third square from the large square to the right side of the first square, place the third square to the right of the first square.'\nYour starting position is [329, 222]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[329, 222], [348, 224], [358, 200], [358, 135], [338, 126], [318, 139], [327, 146], [320, 204], [301, 253], [314, 256]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg2_task_0034_user_0003_scene_0006_cfg_0002_104122061850#398.jpg", + "gt": "[[329, 222], [348, 224], [358, 200], [358, 135], [338, 126], [318, 139], [327, 146], [320, 204], [301, 253], [314, 256]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg4_task_0005_user_0010_scene_0004_cfg_0004_038522062288#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'approach and touch the side of the small block', and now you are performing subtask 'approach and touch the side of the small block.'\nYour initial coordinate is [231, 120]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[231, 120], [153, 142], [181, 138], [191, 155], [149, 141], [151, 160], [173, 171], [141, 152], [153, 149], [149, 154]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg4_task_0005_user_0010_scene_0004_cfg_0004_038522062288#0.jpg", + "gt": "[[231, 120], [153, 142], [181, 138], [191, 155], [149, 141], [151, 160], [173, 171], [141, 152], [153, 149], [149, 154]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0096_user_0020_scene_0002_cfg_0006_104122064161#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take something out of a drawer', and now you are performing subtask 'pull the drawer handle to open the drawer, pick up the item from the drawer.'\nFrom start point [338, 111], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[338, 111], [334, 83], [337, 95], [344, 89], [368, 143], [375, 120], [361, 85], [351, 86], [342, 101], [351, 79]]}" + } + ], + "images": "RH20T_cfg6_task_0096_user_0020_scene_0002_cfg_0006_104122064161#0", + "gt": "[[338, 111], [334, 83], [337, 95], [344, 89], [368, 143], [375, 120], [361, 85], [351, 86], [342, 101], [351, 79]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0052_user_0007_scene_0010_cfg_0005_105422061350#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'grab a basketball, release it and shoot it into the basket', and now you are performing subtask 'grab a basketball, release it and shoot it into the basket.'\nYou begin at [276, 47]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[276, 47], [231, 33], [213, 100], [195, 114], [196, 143], [214, 64], [249, 5], [371, 0], [320, 6], [301, 90]]}" + } + ], + "images": "RH20T_cfg5_task_0052_user_0007_scene_0010_cfg_0005_105422061350#0", + "gt": "[[276, 47], [231, 33], [213, 100], [195, 114], [196, 143], [214, 64], [249, 5], [371, 0], [320, 6], [301, 90]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "79403_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the cauliflower, red ball, and light blue object into the silver bowl', and now you are performing subtask 'place the blue object in the transparent box.'\nStart at [193, 62]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[193, 62], [199, 83], [198, 63], [178, 52], [166, 54], [161, 63], [167, 81], [181, 67], [207, 80], [168, 23]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/79403_exterior_image_1_left#250.jpg", + "gt": "[[193, 62], [199, 83], [198, 63], [178, 52], [166, 54], [161, 63], [167, 81], [181, 67], [207, 80], [168, 23]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "63647_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the drawer and then put the three plush toys inside', and now you are performing subtask 'transfer a plush toy from the top of the table to the inside of the drawer.'\nThe trajectory starts at [241.5, 155.5]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[241.5, 155.5], [224.5, 150.5], [210.5, 152.5], [202.5, 148.5], [188.5, 153.5], [189.5, 157.5], [194.5, 158.5], [203.5, 153.5], [220.5, 150.5], [231.5, 145.5]]}" + } + ], + "images": "63647_exterior_image_1_left#158", + "gt": "[[241.5, 155.5], [224.5, 150.5], [210.5, 152.5], [202.5, 148.5], [188.5, 153.5], [189.5, 157.5], [194.5, 158.5], [203.5, 153.5], [220.5, 150.5], [231.5, 145.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0105_user_0020_scene_0007_cfg_0006_037522061512#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the object on the shelf', and now you are performing subtask 'pick up the object from the tabletop, transfer the object from the tabletop to the specified location, place the object at the specified location, pick up the object from the tabletop.'\nYou begin at [218, 119]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[218, 119], [235, 117], [247, 94], [257, 126], [234, 115], [208, 130], [199, 165], [203, 191], [189, 149], [210, 124]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg6_task_0105_user_0020_scene_0007_cfg_0006_037522061512#438.jpg", + "gt": "[[218, 119], [235, 117], [247, 94], [257, 126], [234, 115], [208, 130], [199, 165], [203, 191], [189, 149], [210, 124]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0034_user_0020_scene_0001_cfg_0006_104122064161#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the squares into a pyramid shape', and now you are performing subtask 'pick up the third square on the bottom, transfer the third square from the bottom to above the square, place the third square above the square, pick up the fourth square on the top.'\nYour starting position is [340, 246]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[340, 246], [342, 285], [361, 325], [339, 240], [361, 188], [351, 183], [362, 170], [358, 124], [342, 125], [363, 90]]}" + } + ], + "images": "RH20T_cfg6_task_0034_user_0020_scene_0001_cfg_0006_104122064161#489", + "gt": "[[340, 246], [342, 285], [361, 325], [339, 240], [361, 188], [351, 183], [362, 170], [358, 124], [342, 125], [363, 90]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "21213_exterior_image_1_left#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the two paper bags out of the wooden crate', and now you are performing subtask 'place the first paper bag on the table.'\nFrom start point [201, 98], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[201, 98], [223, 110], [226, 119], [224, 119], [223, 113], [225, 98], [219, 117], [203, 125], [202, 109], [211, 102]]}" + } + ], + "images": "21213_exterior_image_1_left#469", + "gt": "[[201, 98], [223, 110], [226, 119], [224, 119], [223, 113], [225, 98], [219, 117], [203, 125], [202, 109], [211, 102]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0091_user_0007_scene_0006_cfg_0004_104122062295#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move an object from one box to another', and now you are performing subtask 'pick up the object in the left box.'\nYour starting position is [280, 50]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[280, 50], [256, 60], [253, 52], [240, 48], [212, 46], [203, 49], [191, 61], [200, 98], [198, 111], [196, 98]]}" + } + ], + "images": "RH20T_cfg4_task_0091_user_0007_scene_0006_cfg_0004_104122062295#0", + "gt": "[[280, 50], [256, 60], [253, 52], [240, 48], [212, 46], [203, 49], [191, 61], [200, 98], [198, 111], [196, 98]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "44324_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unstack the cans and put them beside each other', and now you are performing subtask 'pick up the second can on top of the stack.'\nFrom start point [191, 88], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[191, 88], [190, 73], [191, 76], [182, 83], [186, 91], [187, 86], [180, 91], [171, 89], [164, 97], [164, 97]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/44324_exterior_image_1_left#0.jpg", + "gt": "[[191, 88], [190, 73], [191, 76], [182, 83], [186, 91], [187, 86], [180, 91], [171, 89], [164, 97], [164, 97]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "54175_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the pen from the maroon mug', and now you are performing subtask 'remove the pen from the maroon mug.'\nYour starting position is [245.5, 60.5]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[245.5, 60.5], [218.5, 59.5], [189.5, 69.5], [180.5, 67.5], [179.5, 84.5], [167.5, 73.5], [185.5, 93.5], [206.5, 102.5], [210.5, 96.5], [191.5, 80.5]]}" + } + ], + "images": "54175_exterior_image_1_left#0", + "gt": "[[245.5, 60.5], [218.5, 59.5], [189.5, 69.5], [180.5, 67.5], [179.5, 84.5], [167.5, 73.5], [185.5, 93.5], [206.5, 102.5], [210.5, 96.5], [191.5, 80.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0094_user_0007_scene_0009_cfg_0004_104422070011#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open a box', and now you are performing subtask 'push the box to open the box.'\nFrom start point [332, 101], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[332, 101], [336, 112], [325, 100], [332, 111], [374, 98], [391, 101], [386, 134], [387, 123], [383, 119], [359, 123]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg4_task_0094_user_0007_scene_0009_cfg_0004_104422070011#0.jpg", + "gt": "[[332, 101], [336, 112], [325, 100], [332, 111], [374, 98], [391, 101], [386, 134], [387, 123], [383, 119], [359, 123]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "9102_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pour the contents from the black bin onto the countertop', and now you are performing subtask 'pour the contents from the black bin onto the countertop.'\nThe trajectory starts at [225, 36]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[225, 36], [192, 50], [201, 46], [215, 60], [227, 53], [213, 35], [222, 35], [188, 49], [196, 39], [210, 41]]}" + } + ], + "images": "9102_exterior_image_2_left#0", + "gt": "[[225, 36], [192, 50], [201, 46], [215, 60], [227, 53], [213, 35], [222, 35], [188, 49], [196, 39], [210, 41]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "25975_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the pen from the cup', and now you are performing subtask 'remove the pen from the cup.'\nThe trajectory starts at [198, 66]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[198, 66], [183, 71], [192, 91], [158, 123], [157, 91], [161, 79], [144, 91], [143, 96], [147, 99], [147, 95]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/25975_exterior_image_2_left#0.jpg", + "gt": "[[198, 66], [183, 71], [192, 91], [158, 123], [157, 91], [161, 79], [144, 91], [143, 96], [147, 99], [147, 95]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "52259_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the blue t-shirt once', and now you are performing subtask 'unfold the blue t-shirt once.'\nFrom start point [226, 95], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[226, 95], [140, 130], [136, 138], [145, 161], [165, 151], [173, 160], [237, 142], [229, 142], [220, 128], [222, 94]]}" + } + ], + "images": "52259_exterior_image_1_left#0", + "gt": "[[226, 95], [140, 130], [136, 138], [145, 161], [165, 151], [173, 160], [237, 142], [229, 142], [220, 128], [222, 94]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "5072_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the lid from the counter and put it on the pot', and now you are performing subtask 'pick up the lid from the counter and put it on the pot.'\nYour starting position is [319, 51]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[319, 51], [269, 70], [228, 101], [229, 108], [238, 70], [225, 69], [203, 80], [179, 110], [181, 114], [189, 84]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/5072_exterior_image_2_left#0.jpg", + "gt": "[[319, 51], [269, 70], [228, 101], [229, 108], [238, 70], [225, 69], [203, 80], [179, 110], [181, 114], [189, 84]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0081_user_0015_scene_0002_cfg_0004_104422070011#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the leg of the glasses (with one hand)', and now you are performing subtask 'pick up the glasses on the table, place the glasses with the right leg unfolded on the table.'\nThe trajectory starts at [333, 103]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[333, 103], [336, 120], [317, 144], [315, 164], [322, 163], [282, 187], [293, 185], [310, 147], [334, 136], [337, 150]]}" + } + ], + "images": "RH20T_cfg4_task_0081_user_0015_scene_0002_cfg_0004_104422070011#0", + "gt": "[[333, 103], [336, 120], [317, 144], [315, 164], [322, 163], [282, 187], [293, 185], [310, 147], [334, 136], [337, 150]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0061_user_0020_scene_0001_cfg_0007_104122064161#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the lid of the gift box on the table, then take everything out of the gift box and place it all on the table', and now you are performing subtask 'pick up the lid from the gift box, transfer the lid from the gift box to the tabletop, place the lid on the tabletop.'\nThe trajectory starts at [337, 115]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[337, 115], [362, 121], [375, 136], [366, 132], [369, 139], [377, 135], [386, 148], [380, 90], [359, 72], [370, 103]]}" + } + ], + "images": "RH20T_cfg7_task_0061_user_0020_scene_0001_cfg_0007_104122064161#0", + "gt": "[[337, 115], [362, 121], [375, 136], [366, 132], [369, 139], [377, 135], [386, 148], [380, 90], [359, 72], [370, 103]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0034_user_0007_scene_0005_cfg_0005_036422060215#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the squares in a row', and now you are performing subtask 'pick up the first square from the table, transfer the first square from the table to the center of the table, place the first square in the center of the table, pick up the second square from the table.'\nThe trajectory starts at [283, 109]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[283, 109], [282, 119], [274, 126], [261, 154], [248, 213], [252, 215], [272, 162], [271, 167], [269, 154], [247, 139]]}" + } + ], + "images": "RH20T_cfg5_task_0034_user_0007_scene_0005_cfg_0005_036422060215#0", + "gt": "[[283, 109], [282, 119], [274, 126], [261, 154], [248, 213], [252, 215], [272, 162], [271, 167], [269, 154], [247, 139]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg2_task_0034_user_0003_scene_0006_cfg_0002_104122063678#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the squares into a pyramid shape', and now you are performing subtask 'transfer the square from the left side to above the center of the stack, place the square on top of the existing square in the center, pick up the second square next to the first square, transfer the second square from the countertop to the left side of the first square, place the second square to the left of the first square.'\nStarting at [360, 304], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[360, 304], [350, 319], [362, 283], [356, 296], [349, 280], [352, 295], [338, 286], [326, 300], [336, 304], [336, 304]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg2_task_0034_user_0003_scene_0006_cfg_0002_104122063678#138.jpg", + "gt": "[[360, 304], [350, 319], [362, 283], [356, 296], [349, 280], [352, 295], [338, 286], [326, 300], [336, 304], [336, 304]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0005_user_0008_scene_0001_cfg_0001_750612070851#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'approach and touch the side of the small block', and now you are performing subtask 'approach and touch the side of the small block.'\nStart at [329, 155]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[329, 155], [317, 202], [278, 212], [247, 232], [231, 235], [216, 233], [258, 214], [275, 200], [273, 196], [275, 200]]}" + } + ], + "images": "RH20T_cfg1_task_0005_user_0008_scene_0001_cfg_0001_750612070851#0", + "gt": "[[329, 155], [317, 202], [278, 212], [247, 232], [231, 235], [216, 233], [258, 214], [275, 200], [273, 196], [275, 200]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0085_user_0007_scene_0007_cfg_0005_104122061850#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the bubble ring from the assembled bubble ring and ball', and now you are performing subtask 'remove the bubble ring from the assembled bubble ring and ball.'\nStart at [305, 50]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[305, 50], [337, 58], [359, 94], [367, 119], [361, 135], [356, 138], [356, 169], [352, 143], [363, 134], [335, 104]]}" + } + ], + "images": "RH20T_cfg5_task_0085_user_0007_scene_0007_cfg_0005_104122061850#0", + "gt": "[[305, 50], [337, 58], [359, 94], [367, 119], [361, 135], [356, 138], [356, 169], [352, 143], [363, 134], [335, 104]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0038_user_0016_scene_0009_cfg_0001_039422060546#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the cup', and now you are performing subtask 'pick up the cup.'\nYour initial coordinate is [263, 123]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[263, 123], [259, 123], [262, 120], [267, 120], [289, 128], [288, 151], [298, 162], [297, 172], [284, 145], [276, 109]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0038_user_0016_scene_0009_cfg_0001_039422060546#0.jpg", + "gt": "[[263, 123], [259, 123], [262, 120], [267, 120], [289, 128], [288, 151], [298, 162], [297, 172], [284, 145], [276, 109]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "20007_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the drawer on the right, take out three mugs and place them on the countertop', and now you are performing subtask 'pick up the second cup from the right drawer.'\nYou begin at [214, 142]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[214, 142], [211, 159], [227, 153], [221, 136], [176, 115], [173, 128], [164, 122], [173, 105], [202, 129], [210, 122]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/20007_exterior_image_1_left#309.jpg", + "gt": "[[214, 142], [211, 159], [227, 153], [221, 136], [176, 115], [173, 128], [164, 122], [173, 105], [202, 129], [210, 122]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "58228_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the object on the wooden stand', and now you are performing subtask 'put the object on the wooden stand.'\nFrom start point [147, 121], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[147, 121], [164, 113], [164, 129], [181, 143], [164, 123], [165, 100], [171, 91], [195, 92], [181, 76], [170, 84]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/58228_exterior_image_2_left#0.jpg", + "gt": "[[147, 121], [164, 113], [164, 129], [181, 143], [164, 123], [165, 100], [171, 91], [195, 92], [181, 76], [170, 84]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "39227_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'spread the towel on the countertop', and now you are performing subtask 'throw the towel onto the table.'\nFrom start point [295, 35], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[295, 35], [294, 39], [246, 25], [259, 32], [246, 32], [205, 130], [200, 130], [198, 80], [188, 90], [220, 106]]}" + } + ], + "images": "39227_exterior_image_1_left#0", + "gt": "[[295, 35], [294, 39], [246, 25], [259, 32], [246, 32], [205, 130], [200, 130], [198, 80], [188, 90], [220, 106]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0043_user_0020_scene_0009_cfg_0007_104122064161#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unscrew the lid from the jar', and now you are performing subtask 'twist the lid counterclockwise.'\nWith start location [337, 115], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[337, 115], [338, 112], [338, 118], [350, 132], [361, 129], [371, 139], [380, 137], [377, 153], [380, 160], [375, 159]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg7_task_0043_user_0020_scene_0009_cfg_0007_104122064161#0.jpg", + "gt": "[[337, 115], [338, 112], [338, 118], [350, 132], [361, 129], [371, 139], [380, 137], [377, 153], [380, 160], [375, 159]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "67867_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the pot from the right top plate to the right bottom plate of the stove', and now you are performing subtask 'pick up the pot from the right top plate of the stove.'\nYour starting position is [266, 99]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[266, 99], [237, 95], [242, 95], [233, 99], [220, 117], [219, 131], [209, 137], [192, 130], [191, 119], [195, 121]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/67867_exterior_image_1_left#0.jpg", + "gt": "[[266, 99], [237, 95], [242, 95], [233, 99], [220, 117], [219, 131], [209, 137], [192, 130], [191, 119], [195, 121]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0037_user_0014_scene_0009_cfg_0007_104122064161#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'pick up the first block from the desktop, transfer the block from the desktop to the second block, place the block on the second block, pick up the third block from the desktop.'\nYou start from [337, 115]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[337, 115], [353, 119], [350, 107], [359, 101], [368, 122], [360, 131], [366, 119], [374, 129], [368, 114], [357, 111]]}" + } + ], + "images": "RH20T_cfg7_task_0037_user_0014_scene_0009_cfg_0007_104122064161#0", + "gt": "[[337, 115], [353, 119], [350, 107], [359, 101], [368, 122], [360, 131], [366, 119], [374, 129], [368, 114], [357, 111]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg3_task_0092_user_0010_scene_0007_cfg_0003_104122062823#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn the hands of a clock', and now you are performing subtask 'turn the hands of a clock.'\nBegin at [242, 0] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[242, 0], [239, 10], [202, 30], [216, 31], [187, 44], [165, 79], [205, 64], [251, 71], [234, 52], [243, 33]]}" + } + ], + "images": "RH20T_cfg3_task_0092_user_0010_scene_0007_cfg_0003_104122062823#0", + "gt": "[[242, 0], [239, 10], [202, 30], [216, 31], [187, 44], [165, 79], [205, 64], [251, 71], [234, 52], [243, 33]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "82411_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'use the wooden spoon to mix in the bowl', and now you are performing subtask 'use the wooden spoon to mix in the bowl.'\nBegin at [127, 86] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[127, 86], [144, 122], [139, 146], [148, 128], [141, 137], [135, 125], [150, 124], [131, 108], [131, 89], [131, 89]]}" + } + ], + "images": "82411_exterior_image_2_left#0", + "gt": "[[127, 86], [144, 122], [139, 146], [148, 128], [141, 137], [135, 125], [150, 124], [131, 108], [131, 89], [131, 89]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "4968_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the marker out of the mug and put it on the table', and now you are performing subtask 'take the marker out of the mug and put it on the table.'\nFrom start point [50.5, 0.0], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[50.5, 0.0], [153.5, 44.0], [169.5, 66.0], [163.5, 40.0], [142.5, 12.0], [130.5, 8.0], [126.5, 20.0], [130.5, 91.0], [141.5, 103.0], [141.5, 75.0]]}" + } + ], + "images": "4968_exterior_image_1_left#0", + "gt": "[[50.5, 0.0], [153.5, 44.0], [169.5, 66.0], [163.5, 40.0], [142.5, 12.0], [130.5, 8.0], [126.5, 20.0], [130.5, 91.0], [141.5, 103.0], [141.5, 75.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "13477_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the rectangular object from the middle of the table and put it in the cabinet', and now you are performing subtask 'pick up the rectangular object from the middle of the table and put it in the cabinet.'\nYou begin at [69, 89]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[69, 89], [99, 92], [133, 113], [148, 148], [114, 117], [105, 77], [111, 6], [135, 23], [107, 16], [88, 72]]}" + } + ], + "images": "13477_exterior_image_1_left#0", + "gt": "[[69, 89], [99, 92], [133, 113], [148, 148], [114, 117], [105, 77], [111, 6], [135, 23], [107, 16], [88, 72]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "51525_exterior_image_2_left#TrajectoryPrediction_Task#14", + "task": "TrajectoryPrediction_Task", + "p_index": 14, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close the microwave door, move the pink jar on the counter', and now you are performing subtask 'transfer the pink jar from the microwave to the countertop.'\nYour initial coordinate is [116, 70]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[116, 70], [104, 68], [96, 64], [90, 58], [92, 57], [96, 63], [108, 70], [120, 83], [120, 85], [121, 83]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/51525_exterior_image_2_left#378.jpg", + "gt": "[[116, 70], [104, 68], [96, 64], [90, 58], [92, 57], [96, 63], [108, 70], [120, 83], [120, 85], [121, 83]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "59916_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the lid from the tray and put it on the pot', and now you are performing subtask 'pick up the lid from the tray and put it on the pot.'\nYour initial coordinate is [53, 0]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[53, 0], [113, 69], [123, 94], [105, 70], [109, 61], [120, 55], [162, 66], [177, 78], [177, 94], [175, 87]]}" + } + ], + "images": "59916_exterior_image_1_left#0", + "gt": "[[53, 0], [113, 69], [123, 94], [105, 70], [109, 61], [120, 55], [162, 66], [177, 78], [177, 94], [175, 87]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "8448_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the marker and put it in the bowl', and now you are performing subtask 'pick up the marker and put it in the bowl.'\nWith start location [155, 87], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[155, 87], [136, 72], [119, 73], [110, 86], [104, 129], [107, 83], [112, 79], [115, 89], [117, 77], [126, 72]]}" + } + ], + "images": "8448_exterior_image_2_left#0", + "gt": "[[155, 87], [136, 72], [119, 73], [110, 86], [104, 129], [107, 83], [112, 79], [115, 89], [117, 77], [126, 72]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0058_user_0014_scene_0001_cfg_0006_104122063633#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the switches on the power strip in sequence', and now you are performing subtask 'press the fourth button on the power strip.'\nYour initial coordinate is [253, 199]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[253, 199], [253, 200], [250, 202], [250, 196], [249, 193], [250, 180], [252, 177], [257, 176], [258, 178], [255, 185]]}" + } + ], + "images": "RH20T_cfg6_task_0058_user_0014_scene_0001_cfg_0006_104122063633#229", + "gt": "[[253, 199], [253, 200], [250, 202], [250, 196], [249, 193], [250, 180], [252, 177], [257, 176], [258, 178], [255, 185]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg6_task_0017_user_0014_scene_0002_cfg_0006_104122063633#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the pen into the pen holder', and now you are performing subtask 'pick up the pen from the table.'\nThe trajectory starts at [233, 118]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[233, 118], [232, 149], [244, 190], [250, 196], [244, 163], [271, 169], [278, 178], [286, 230], [275, 206], [263, 202]]}" + } + ], + "images": "RH20T_cfg6_task_0017_user_0014_scene_0002_cfg_0006_104122063633#0", + "gt": "[[233, 118], [232, 149], [244, 190], [250, 196], [244, 163], [271, 169], [278, 178], [286, 230], [275, 206], [263, 202]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "52635_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'unfold the towel', and now you are performing subtask 'slide the towel to the left.'\nStart at [204, 61]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[204, 61], [199, 68], [194, 69], [176, 66], [199, 43], [233, 30], [227, 32], [246, 35], [239, 36], [242, 37]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/52635_exterior_image_1_left#252.jpg", + "gt": "[[204, 61], [199, 68], [194, 69], [176, 66], [199, 43], [233, 30], [227, 32], [246, 35], [239, 36], [242, 37]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0037_user_0020_scene_0004_cfg_0006_104122061602#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'pick up the block on the surface, transfer the block from the surface to the other block, place the block on the other block.'\nYour starting position is [446, 106]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[446, 106], [444, 133], [435, 139], [441, 154], [434, 207], [435, 196], [421, 184], [415, 155], [404, 156], [397, 167]]}" + } + ], + "images": "RH20T_cfg6_task_0037_user_0020_scene_0004_cfg_0006_104122061602#0", + "gt": "[[446, 106], [444, 133], [435, 139], [441, 154], [434, 207], [435, 196], [421, 184], [415, 155], [404, 156], [397, 167]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "12658_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'rotate the tap nozzle clockwise', and now you are performing subtask 'rotate the tap nozzle clockwise.'\nWith start location [145, 0], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[145, 0], [174, 23], [188, 66], [175, 67], [165, 25], [171, 15], [146, 34], [120, 40], [133, 43], [124, 42]]}" + } + ], + "images": "12658_exterior_image_1_left#0", + "gt": "[[145, 0], [174, 23], [188, 66], [175, 67], [165, 25], [171, 15], [146, 34], [120, 40], [133, 43], [124, 42]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg2_task_0201_user_0007_scene_0008_cfg_0002_105422061350#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'the medium pipette is moved from the table to the holder for medium pipette tips', and now you are performing subtask 'the medium pipette is moved from the table to the holder for medium pipette tips.'\nYou start from [306, 109]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[306, 109], [286, 168], [266, 180], [257, 180], [228, 207], [235, 215], [230, 214], [247, 217], [243, 215], [283, 169]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg2_task_0201_user_0007_scene_0008_cfg_0002_105422061350#0.jpg", + "gt": "[[306, 109], [286, 168], [266, 180], [257, 180], [228, 207], [235, 215], [230, 214], [247, 217], [243, 215], [283, 169]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "40066_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the white mug to the right, place the marker inside the mug', and now you are performing subtask 'place the marker inside the white mug.'\nThe trajectory starts at [189.0, 91.5]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[189.0, 91.5], [178.0, 63.5], [160.0, 56.5], [166.0, 54.5], [170.0, 65.5], [182.0, 34.5], [201.0, 41.5], [217.0, 65.5], [211.0, 79.5], [218.0, 54.5]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/40066_exterior_image_1_left#184.jpg", + "gt": "[[189.0, 91.5], [178.0, 63.5], [160.0, 56.5], [166.0, 54.5], [170.0, 65.5], [182.0, 34.5], [201.0, 41.5], [217.0, 65.5], [211.0, 79.5], [218.0, 54.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0039_user_0014_scene_0005_cfg_0006_104122060811#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pour the water from a cup into another empty cup', and now you are performing subtask 'pour the water from a cup into another empty cup.'\nStarting at [385, 127], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[385, 127], [369, 152], [367, 142], [394, 92], [418, 91], [399, 93], [380, 108], [371, 145], [359, 155], [365, 138]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg6_task_0039_user_0014_scene_0005_cfg_0006_104122060811#0.jpg", + "gt": "[[385, 127], [369, 152], [367, 142], [394, 92], [418, 91], [399, 93], [380, 108], [371, 145], [359, 155], [365, 138]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "54397_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'fold the top right corner over the bottom left corner, then fold the bottom right corner over the top left corner', and now you are performing subtask 'fold the bottom right corner over the top left corner.'\nFrom start point [199, 85], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[199, 85], [192, 93], [202, 76], [183, 80], [170, 96], [173, 91], [183, 88], [193, 73], [196, 65], [193, 66]]}" + } + ], + "images": "54397_exterior_image_1_left#204", + "gt": "[[199, 85], [192, 93], [202, 76], [183, 80], [170, 96], [173, 91], [183, 88], [193, 73], [196, 65], [193, 66]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg1_task_0016_user_0014_scene_0003_cfg_0001_038522062547#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'hit the pool ball', and now you are performing subtask 'pick up the pool cue from the table, strike the pool ball on the table.'\nWith start location [407, 136], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[407, 136], [422, 108], [400, 87], [398, 63], [360, 57], [357, 66], [356, 60], [367, 52], [377, 68], [377, 68]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0016_user_0014_scene_0003_cfg_0001_038522062547#0.jpg", + "gt": "[[407, 136], [422, 108], [400, 87], [398, 63], [360, 57], [357, 66], [356, 60], [367, 52], [377, 68], [377, 68]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "37064_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the marker and put it above the table', and now you are performing subtask 'pick up the marker and put it above the table.'\nStarting at [318, 52], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[318, 52], [224, 130], [211, 113], [198, 103], [162, 87], [131, 81], [123, 86], [122, 99], [124, 86], [130, 83]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/37064_exterior_image_2_left#0.jpg", + "gt": "[[318, 52], [224, 130], [211, 113], [198, 103], [162, 87], [131, 81], [123, 86], [122, 99], [124, 86], [130, 83]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "62165_exterior_image_2_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the lid off the clear container', and now you are performing subtask 'place the lid on the table.'\nFrom start point [175, 82], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[175, 82], [174, 105], [173, 80], [163, 71], [155, 73], [149, 97], [150, 110], [149, 93], [134, 66], [134, 66]]}" + } + ], + "images": "62165_exterior_image_2_left#115", + "gt": "[[175, 82], [174, 105], [173, 80], [163, 71], [155, 73], [149, 97], [150, 110], [149, 93], [134, 66], [134, 66]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "52193_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'cover the pot', and now you are performing subtask 'cover the pot.'\nYour starting position is [122.5, 56.5]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[122.5, 56.5], [139.5, 55.5], [128.5, 77.5], [120.5, 57.5], [110.5, 59.5], [108.5, 80.5], [88.5, 82.5], [85.5, 75.5], [104.5, 81.5], [103.5, 74.5]]}" + } + ], + "images": "52193_exterior_image_1_left#0", + "gt": "[[122.5, 56.5], [139.5, 55.5], [128.5, 77.5], [120.5, 57.5], [110.5, 59.5], [108.5, 80.5], [88.5, 82.5], [85.5, 75.5], [104.5, 81.5], [103.5, 74.5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0047_user_0020_scene_0004_cfg_0007_104122061602#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the cup off the cup rack', and now you are performing subtask 'take the cup off the cup rack.'\nWith start location [448, 116], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[448, 116], [459, 125], [454, 105], [474, 108], [493, 129], [472, 94], [423, 82], [412, 98], [426, 77], [454, 75]]}" + } + ], + "images": "RH20T_cfg7_task_0047_user_0020_scene_0004_cfg_0007_104122061602#0", + "gt": "[[448, 116], [459, 125], [454, 105], [474, 108], [493, 129], [472, 94], [423, 82], [412, 98], [426, 77], [454, 75]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "86744_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the button of the toaster', and now you are performing subtask 'press the button of the toaster.'\nYour starting position is [275, 14]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[275, 14], [154, 42], [149, 46], [150, 54], [146, 52], [148, 58], [144, 53], [150, 45], [183, 39], [183, 39]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/86744_exterior_image_2_left#0.jpg", + "gt": "[[275, 14], [154, 42], [149, 46], [150, 54], [146, 52], [148, 58], [144, 53], [150, 45], [183, 39], [183, 39]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0062_user_0014_scene_0003_cfg_0006_037522061512#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the toilet paper on its holder', and now you are performing subtask 'put the toilet paper on its holder.'\nYou begin at [261, 86]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[261, 86], [256, 86], [257, 91], [247, 73], [268, 95], [262, 86], [254, 105], [268, 156], [262, 142], [260, 90]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg6_task_0062_user_0014_scene_0003_cfg_0006_037522061512#0.jpg", + "gt": "[[261, 86], [256, 86], [257, 91], [247, 73], [268, 95], [262, 86], [254, 105], [268, 156], [262, 142], [260, 90]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "47509_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the gray object inside the pot', and now you are performing subtask 'put the gray object inside the pot.'\nYou begin at [278, 2]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[278, 2], [257, 18], [232, 61], [233, 73], [208, 30], [202, 35], [199, 59], [214, 47], [216, 41], [208, 43]]}" + } + ], + "images": "47509_exterior_image_2_left#0", + "gt": "[[278, 2], [257, 18], [232, 61], [233, 73], [208, 30], [202, 35], [199, 59], [214, 47], [216, 41], [208, 43]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "83808_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the pen from the cup and put it on the left side of the table', and now you are performing subtask 'remove the pen from the cup and put it on the left side of the table.'\nYou start from [150.0, 23.0]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[150.0, 23.0], [157.0, 16.0], [174.0, 21.0], [175.0, 41.0], [183.0, 59.0], [190.0, 62.0], [197.0, 37.0], [192.0, 32.0], [175.0, 37.0], [152.0, 69.0]]}" + } + ], + "images": "83808_exterior_image_1_left#0", + "gt": "[[150.0, 23.0], [157.0, 16.0], [174.0, 21.0], [175.0, 41.0], [183.0, 59.0], [190.0, 62.0], [197.0, 37.0], [192.0, 32.0], [175.0, 37.0], [152.0, 69.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "63429_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the marker in the cup', and now you are performing subtask 'the marker falls on the printer.'\nStarting at [168, 18], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[168, 18], [164, 20], [147, 40], [142, 53], [143, 67], [126, 38], [111, 29], [105, 29], [100, 32], [98, 31]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/63429_exterior_image_2_left#0.jpg", + "gt": "[[168, 18], [164, 20], [147, 40], [142, 53], [143, 67], [126, 38], [111, 29], [105, 29], [100, 32], [98, 31]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "26372_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the washing machine lid', and now you are performing subtask 'open the washing machine lid.'\nFrom start point [247, 75], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[247, 75], [188, 112], [178, 146], [173, 151], [168, 148], [168, 155], [201, 170], [192, 156], [188, 122], [217, 55]]}" + } + ], + "images": "26372_exterior_image_2_left#0", + "gt": "[[247, 75], [188, 112], [178, 146], [173, 151], [168, 148], [168, 155], [201, 170], [192, 156], [188, 122], [217, 55]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0024_user_0014_scene_0003_cfg_0004_038522062288#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn off the power strip by pressing the button', and now you are performing subtask 'turn off the power strip by pressing the button.'\nBegin at [234, 117] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[234, 117], [186, 105], [216, 109], [214, 100], [205, 87], [229, 159], [202, 166], [209, 169], [217, 153], [248, 149]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg4_task_0024_user_0014_scene_0003_cfg_0004_038522062288#0.jpg", + "gt": "[[234, 117], [186, 105], [216, 109], [214, 100], [205, 87], [229, 159], [202, 166], [209, 169], [217, 153], [248, 149]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0008_user_0007_scene_0001_cfg_0005_104422070044#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'grab the block and place it at the designated location', and now you are performing subtask 'grab the block and place it at the designated location.'\nWith start location [375, 134], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[375, 134], [441, 174], [449, 196], [487, 233], [479, 262], [481, 248], [445, 189], [417, 163], [422, 155], [422, 155]]}" + } + ], + "images": "RH20T_cfg5_task_0008_user_0007_scene_0001_cfg_0005_104422070044#0", + "gt": "[[375, 134], [441, 174], [449, 196], [487, 233], [479, 262], [481, 248], [445, 189], [417, 163], [422, 155], [422, 155]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg2_task_0071_user_0007_scene_0006_cfg_0002_104122063678#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'close a sliding window', and now you are performing subtask 'close a sliding window.'\nBegin at [400, 196] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[400, 196], [377, 189], [378, 204], [381, 213], [405, 218], [377, 210], [388, 211], [383, 192], [396, 196], [411, 224]]}" + } + ], + "images": "RH20T_cfg2_task_0071_user_0007_scene_0006_cfg_0002_104122063678#0", + "gt": "[[400, 196], [377, 189], [378, 204], [381, 213], [405, 218], [377, 210], [388, 211], [383, 192], [396, 196], [411, 224]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "1909_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'wiping the table with a green towel', and now you are performing subtask 'wiping the table with a green towel.'\nBegin at [167, 6] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[167, 6], [168, 24], [163, 18], [164, 26], [176, 40], [184, 62], [185, 81], [176, 88], [152, 83], [151, 59]]}" + } + ], + "images": "1909_exterior_image_1_left#0", + "gt": "[[167, 6], [168, 24], [163, 18], [164, 26], [176, 40], [184, 62], [185, 81], [176, 88], [152, 83], [151, 59]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "31719_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the cloth off the hook and put it on the table', and now you are performing subtask 'take the cloth off the hook and put it on the table.'\nThe trajectory starts at [60, 20]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[60, 20], [98, 32], [123, 24], [120, 32], [169, 48], [164, 64], [122, 90], [118, 103], [127, 104], [134, 81]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/31719_exterior_image_2_left#0.jpg", + "gt": "[[60, 20], [98, 32], [123, 24], [120, 32], [169, 48], [164, 64], [122, 90], [118, 103], [127, 104], [134, 81]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0020_user_0010_scene_0007_cfg_0005_104122063678#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn on the desk lamp by pressing the button', and now you are performing subtask 'turn on the desk lamp by pressing the button.'\nYour starting position is [323, 132]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[323, 132], [326, 161], [311, 175], [321, 160], [338, 173], [349, 154], [345, 185], [361, 184], [353, 168], [381, 141]]}" + } + ], + "images": "RH20T_cfg5_task_0020_user_0010_scene_0007_cfg_0005_104122063678#0", + "gt": "[[323, 132], [326, 161], [311, 175], [321, 160], [338, 173], [349, 154], [345, 185], [361, 184], [353, 168], [381, 141]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "13360_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the lid on the black pot', and now you are performing subtask 'put the lid on the black pot.'\nYour initial coordinate is [200, 101]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[200, 101], [200, 127], [185, 156], [183, 176], [197, 168], [197, 134], [189, 115], [187, 125], [190, 128], [192, 115]]}" + } + ], + "images": "13360_exterior_image_2_left#0", + "gt": "[[200, 101], [200, 127], [185, 156], [183, 176], [197, 168], [197, 134], [189, 115], [187, 125], [190, 128], [192, 115]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0096_user_0007_scene_0008_cfg_0005_104122063678#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take something out of a drawer', and now you are performing subtask 'pull the drawer handle to the outside of the table, pick up the object from the drawer, transfer the object from the drawer to the top of the table, place the object on the table.'\nYour initial coordinate is [399, 197]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[399, 197], [400, 232], [371, 260], [377, 214], [393, 203], [366, 146], [364, 152], [352, 153], [348, 187], [357, 157]]}" + } + ], + "images": "RH20T_cfg5_task_0096_user_0007_scene_0008_cfg_0005_104122063678#401", + "gt": "[[399, 197], [400, 232], [371, 260], [377, 214], [393, 203], [366, 146], [364, 152], [352, 153], [348, 187], [357, 157]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "65816_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove some tissues from the box', and now you are performing subtask 'remove some tissues from the box.'\nWith start location [36, 103], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[36, 103], [99, 65], [135, 59], [136, 77], [125, 73], [133, 27], [160, 1], [180, 47], [163, 178], [158, 111]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/65816_exterior_image_2_left#0.jpg", + "gt": "[[36, 103], [99, 65], [135, 59], [136, 77], [125, 73], [133, 27], [160, 1], [180, 47], [163, 178], [158, 111]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "73732_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open and close the microwave door and then close the top fridge door', and now you are performing subtask 'push the microwave door to the closed position.'\nYour initial coordinate is [223.5, 43.0]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[223.5, 43.0], [219.5, 36.0], [211.5, 35.0], [196.5, 56.0], [178.5, 61.0], [164.5, 50.0], [156.5, 37.0], [148.5, 35.0], [169.5, 41.0], [189.5, 38.0]]}" + } + ], + "images": "73732_exterior_image_1_left#229", + "gt": "[[223.5, 43.0], [219.5, 36.0], [211.5, 35.0], [196.5, 56.0], [178.5, 61.0], [164.5, 50.0], [156.5, 37.0], [148.5, 35.0], [169.5, 41.0], [189.5, 38.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "2863_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn off the switch on the fourth from the right on the adapter', and now you are performing subtask 'turn off the switch on the fourth from the right on the adapter.'\nStart at [205, 1]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[205, 1], [208, 21], [200, 38], [203, 38], [200, 40], [201, 49], [185, 61], [181, 72], [174, 71], [174, 82]]}" + } + ], + "images": "2863_exterior_image_1_left#0", + "gt": "[[205, 1], [208, 21], [200, 38], [203, 38], [200, 40], [201, 49], [185, 61], [181, 72], [174, 71], [174, 82]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg3_task_0058_user_0010_scene_0010_cfg_0003_036422060909#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the buttons on a row of four power strips to turn off the power strips', and now you are performing subtask 'press the button on the power strip above.'\nYour starting position is [221, 100]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[221, 100], [241, 98], [236, 102], [240, 106], [237, 104], [238, 108], [240, 108], [239, 109], [241, 106], [231, 92]]}" + } + ], + "images": "RH20T_cfg3_task_0058_user_0010_scene_0010_cfg_0003_036422060909#193", + "gt": "[[221, 100], [241, 98], [236, 102], [240, 106], [237, 104], [238, 108], [240, 108], [239, 109], [241, 106], [231, 92]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "1571_exterior_image_1_left#TrajectoryPrediction_Task#10", + "task": "TrajectoryPrediction_Task", + "p_index": 10, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move all the plush toys from the basket to the table one by one', and now you are performing subtask 'place the seventh toy on the table.'\nStarting at [108, 103], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[108, 103], [109, 81], [139, 92], [118, 83], [117, 102], [125, 79], [144, 92], [126, 82], [135, 104], [144, 85]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/1571_exterior_image_1_left#416.jpg", + "gt": "[[108, 103], [109, 81], [139, 92], [118, 83], [117, 102], [125, 79], [144, 92], [126, 82], [135, 104], [144, 85]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "47386_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the object from the blue plate and place it on the table, then pick up another object from the plate and place it on the table, and then slide the towel to the left', and now you are performing subtask 'slide the towel on the tabletop to the left.'\nStarting at [184, 50], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[184, 50], [181, 43], [185, 41], [214, 41], [219, 36], [241, 48], [225, 75], [197, 81], [193, 77], [201, 48]]}" + } + ], + "images": "47386_exterior_image_1_left#211", + "gt": "[[184, 50], [181, 43], [185, 41], [214, 41], [219, 36], [241, 48], [225, 75], [197, 81], [193, 77], [201, 48]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "30832_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the fruits from the glass bowl and place them on the countertop', and now you are performing subtask 'place the fruit on the countertop.'\nThe trajectory starts at [242, 91]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[242, 91], [233, 83], [218, 88], [215, 119], [222, 85], [234, 72], [244, 79], [248, 114], [243, 115], [238, 86]]}" + } + ], + "images": "30832_exterior_image_1_left#144", + "gt": "[[242, 91], [233, 83], [218, 88], [215, 119], [222, 85], [234, 72], [244, 79], [248, 114], [243, 115], [238, 86]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "32668_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open the doors of the second shelf of the cabinet', and now you are performing subtask 'pull the handle of the left door of the second shelf to open the door.'\nYou begin at [128, 0]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[128, 0], [107, 33], [109, 48], [124, 54], [118, 59], [103, 55], [95, 38], [99, 18], [116, 13], [109, 5]]}" + } + ], + "images": "32668_exterior_image_1_left#340", + "gt": "[[128, 0], [107, 33], [109, 48], [124, 54], [118, 59], [103, 55], [95, 38], [99, 18], [116, 13], [109, 5]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "3614_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the grey faucet to the right', and now you are performing subtask 'move the grey faucet to the right.'\nYour starting position is [93, 1]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[93, 1], [148, 22], [175, 42], [176, 55], [172, 57], [185, 62], [188, 60], [181, 44], [135, 8], [135, 8]]}" + } + ], + "images": "3614_exterior_image_1_left#0", + "gt": "[[93, 1], [148, 22], [175, 42], [176, 55], [172, 57], [185, 62], [188, 60], [181, 44], [135, 8], [135, 8]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "84954_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the third switch from the right', and now you are performing subtask 'press the third switch from the right.'\nFrom start point [61, 0], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[61, 0], [116, 109], [151, 119], [154, 123], [149, 124], [151, 127], [165, 120], [163, 130], [157, 131], [160, 146]]}" + } + ], + "images": "84954_exterior_image_2_left#0", + "gt": "[[61, 0], [116, 109], [151, 119], [154, 123], [149, 124], [151, 127], [165, 120], [163, 130], [157, 131], [160, 146]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "47675_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'turn off the switch on the extension cord then close the clear container', and now you are performing subtask 'press the switch on the power strip to turn it off.'\nYou begin at [280, 0]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[280, 0], [245, 22], [229, 44], [219, 51], [224, 52], [213, 59], [203, 72], [190, 80], [194, 95], [182, 69]]}" + } + ], + "images": "47675_exterior_image_1_left#0", + "gt": "[[280, 0], [245, 22], [229, 44], [219, 51], [224, 52], [213, 59], [203, 72], [190, 80], [194, 95], [182, 69]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0034_user_0014_scene_0007_cfg_0007_104122064161#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the squares into a pyramid shape', and now you are performing subtask 'pick up the first block from the desktop, transfer the first block from the desktop to the right side of the table, place the first block on the right side of the table.'\nYour initial coordinate is [337, 115]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[337, 115], [399, 169], [399, 196], [391, 202], [415, 212], [387, 253], [352, 255], [348, 278], [334, 293], [372, 263]]}" + } + ], + "images": "RH20T_cfg7_task_0034_user_0014_scene_0007_cfg_0007_104122064161#0", + "gt": "[[337, 115], [399, 169], [399, 196], [391, 202], [415, 212], [387, 253], [352, 255], [348, 278], [334, 293], [372, 263]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "69300_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the glue stick inside the open drawer', and now you are performing subtask 'put the glue stick inside the open drawer.'\nYou begin at [150.5, 63.0]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[150.5, 63.0], [128.5, 56.0], [125.5, 60.0], [129.5, 57.0], [144.5, 68.0], [132.5, 69.0], [127.5, 81.0], [133.5, 80.0], [144.5, 92.0], [126.5, 84.0]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/69300_exterior_image_1_left#0.jpg", + "gt": "[[150.5, 63.0], [128.5, 56.0], [125.5, 60.0], [129.5, 57.0], [144.5, 68.0], [132.5, 69.0], [127.5, 81.0], [133.5, 80.0], [144.5, 92.0], [126.5, 84.0]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg2_task_0073_user_0014_scene_0003_cfg_0002_105422061350#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the block in the drawer, close the drawer', and now you are performing subtask 'pick up the square on the fabric, transfer the square from the fabric to the drawer, place the square in the drawer, push the drawer to close it.'\nYou begin at [306, 100]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[306, 100], [311, 107], [301, 104], [289, 116], [287, 148], [315, 108], [307, 100], [353, 58], [358, 65], [317, 87]]}" + } + ], + "images": "RH20T_cfg2_task_0073_user_0014_scene_0003_cfg_0002_105422061350#0", + "gt": "[[306, 100], [311, 107], [301, 104], [289, 116], [287, 148], [315, 108], [307, 100], [353, 58], [358, 65], [317, 87]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0065_user_0010_scene_0005_cfg_0001_038522063145#TrajectoryPrediction_Task#12", + "task": "TrajectoryPrediction_Task", + "p_index": 12, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with small Lego blocks for the nth time with n blocks', and now you are performing subtask 'place the blue small Lego block on the white small Lego block, press the blue small Lego block, pick up the red small Lego block from the desktop.'\nYou start from [450, 157]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[450, 157], [446, 159], [448, 151], [450, 157], [448, 155], [452, 155], [447, 138], [449, 131], [448, 134], [442, 134]]}" + } + ], + "images": "RH20T_cfg1_task_0065_user_0010_scene_0005_cfg_0001_038522063145#1411", + "gt": "[[450, 157], [446, 159], [448, 151], [450, 157], [448, 155], [452, 155], [447, 138], [449, 131], [448, 134], [442, 134]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "52264_exterior_image_2_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pour the contents of the cup into the pot', and now you are performing subtask 'pour the contents of the cup into the pot.'\nFrom start point [225, 33], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[225, 33], [193, 60], [162, 117], [161, 91], [198, 83], [209, 55], [185, 74], [163, 114], [175, 110], [175, 110]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/52264_exterior_image_2_left#0.jpg", + "gt": "[[225, 33], [193, 60], [162, 117], [161, 91], [198, 83], [209, 55], [185, 74], [163, 114], [175, 110], [175, 110]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "23955_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pour the contents in the cup into the bowl', and now you are performing subtask 'pour the contents in the cup into the bowl.'\nFrom start point [210, 111], estimate 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[210, 111], [173, 98], [157, 96], [145, 104], [148, 114], [165, 101], [170, 102], [170, 109], [176, 105], [178, 99]]}" + } + ], + "images": "23955_exterior_image_1_left#0", + "gt": "[[210, 111], [173, 98], [157, 96], [145, 104], [148, 114], [165, 101], [170, 102], [170, 109], [176, 105], [178, 99]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "10520_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the cloth on the purple mat', and now you are performing subtask 'put the cloth on the purple mat.'\nThe trajectory starts at [225, 56]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[225, 56], [215, 59], [205, 60], [183, 57], [187, 59], [189, 58], [205, 70], [214, 80], [213, 84], [217, 82]]}" + } + ], + "images": "10520_exterior_image_1_left#0", + "gt": "[[225, 56], [215, 59], [205, 60], [183, 57], [187, 59], [189, 58], [205, 70], [214, 80], [213, 84], [217, 82]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg4_task_0047_user_0014_scene_0014_cfg_0004_036422060909#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'take the cup off the cup rack', and now you are performing subtask 'take the cup off the cup rack.'\nYou begin at [339, 80]. Given the scene as observed, supply 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[339, 80], [252, 76], [213, 119], [205, 81], [283, 62], [352, 70], [380, 86], [375, 99], [325, 56], [259, 42]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg4_task_0047_user_0014_scene_0014_cfg_0004_036422060909#0.jpg", + "gt": "[[339, 80], [252, 76], [213, 119], [205, 81], [283, 62], [352, 70], [380, 86], [375, 99], [325, 56], [259, 42]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "22578_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'remove the lid from the glass jar and place it on the table, then put it back on the jar', and now you are performing subtask 'place the lid from the table on the right side of the glass jar onto the glass jar.'\nWith start location [191, 90], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[191, 90], [183, 64], [179, 67], [198, 101], [185, 52], [172, 63], [182, 73], [171, 71], [170, 76], [175, 59]]}" + } + ], + "images": "22578_exterior_image_1_left#163", + "gt": "[[191, 90], [183, 64], [179, 67], [198, 101], [185, 52], [172, 63], [182, 73], [171, 71], [170, 76], [175, 59]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0066_user_0014_scene_0005_cfg_0007_104122063633#TrajectoryPrediction_Task#6", + "task": "TrajectoryPrediction_Task", + "p_index": 6, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'build with large Megabloks for the nth time with n blocks', and now you are performing subtask 'place the block on the block board, pick up the block on the flat surface, transfer the block from the flat surface to the other blocks, place the block on the other blocks, pick up the block on the flat surface.'\nYour initial coordinate is [181, 180]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[181, 180], [139, 194], [178, 149], [212, 136], [227, 149], [224, 156], [227, 147], [231, 153], [221, 148], [188, 160]]}" + } + ], + "images": "RH20T_cfg7_task_0066_user_0014_scene_0005_cfg_0007_104122063633#448", + "gt": "[[181, 180], [139, 194], [178, 149], [212, 136], [227, 149], [224, 156], [227, 147], [231, 153], [221, 148], [188, 160]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "25109_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the orange cube on top of the green cube', and now you are performing subtask 'put the orange cube on top of the green cube.'\nYou start from [188, 80]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[188, 80], [189, 83], [188, 84], [187, 99], [182, 111], [181, 111], [180, 107], [180, 101], [183, 88], [181, 91]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/25109_exterior_image_1_left#0.jpg", + "gt": "[[188, 80], [189, 83], [188, 84], [187, 99], [182, 111], [181, 111], [180, 107], [180, 101], [183, 88], [181, 91]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg6_task_0034_user_0020_scene_0001_cfg_0006_104122063633#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the squares into a pyramid shape', and now you are performing subtask 'place the first square in the center, pick up the second square on the right, transfer the second square from the right to below the first square, place the second square below the first square.'\nStart at [221, 135]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[221, 135], [173, 103], [177, 117], [200, 119], [195, 132], [209, 126], [228, 138], [226, 157], [218, 151], [228, 125]]}" + } + ], + "images": "RH20T_cfg6_task_0034_user_0020_scene_0001_cfg_0006_104122063633#562", + "gt": "[[221, 135], [173, 103], [177, 117], [200, 119], [195, 132], [209, 126], [228, 138], [226, 157], [218, 151], [228, 125]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "92033_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open and close the cup lid', and now you are performing subtask 'push the cup lid to close it.'\nStart at [247, 57]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[247, 57], [246, 60], [239, 63], [233, 70], [235, 69], [234, 44], [239, 38], [245, 36], [250, 36], [254, 34]]}" + } + ], + "images": "92033_exterior_image_1_left#151", + "gt": "[[247, 57], [246, 60], [239, 63], [233, 70], [235, 69], [234, 44], [239, 38], [245, 36], [250, 36], [254, 34]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg7_task_0037_user_0014_scene_0001_cfg_0007_104122064161#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line', and now you are performing subtask 'place the second block on top of the first block, pick up the third block from the table, transfer the third block from the table to the stacking position.'\nYou start from [362, 203]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[362, 203], [366, 204], [380, 215], [383, 227], [382, 219], [372, 209], [367, 201], [367, 193], [351, 196], [341, 203]]}" + } + ], + "images": "RH20T_cfg7_task_0037_user_0014_scene_0001_cfg_0007_104122064161#237", + "gt": "[[362, 203], [366, 204], [380, 215], [383, 227], [382, 219], [372, 209], [367, 201], [367, 193], [351, 196], [341, 203]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "88987_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the black marker from the table and place it in the pot', and now you are performing subtask 'pick up the black marker from the table and place it in the pot.'\nYou start from [131, 10]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[131, 10], [149, 18], [173, 37], [205, 78], [216, 99], [209, 92], [202, 70], [189, 67], [170, 76], [149, 65]]}" + } + ], + "images": "88987_exterior_image_1_left#0", + "gt": "[[131, 10], [149, 18], [173, 37], [205, 78], [216, 99], [209, 92], [202, 70], [189, 67], [170, 76], [149, 65]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "65467_exterior_image_1_left#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'pick up the bottle from the table and put it inside the clear bowl, turn off the white extension cable, take out one bottle from the clear bowl and place it on the left side of the table', and now you are performing subtask 'press the switch on the white extension cable to turn off the power.'\nWith start location [211, 105], and given the scene, produce 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[211, 105], [213, 100], [225, 93], [256, 87], [281, 96], [286, 113], [267, 123], [268, 132], [253, 110], [253, 110]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/65467_exterior_image_1_left#165.jpg", + "gt": "[[211, 105], [213, 100], [225, 93], [256, 87], [281, 96], [286, 113], [267, 123], [268, 132], [253, 110], [253, 110]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "35690_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'move the black and yellow bottle to the left, move the water bottle to the right, then move the black and yellow bottle closer to the water bottle', and now you are performing subtask 'push the black and yellow bottle to the left on the counter.'\nYou start from [264, 101]. Using the present scene, provide 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[264, 101], [226, 93], [199, 106], [214, 77], [209, 84], [197, 46], [171, 33], [145, 44], [156, 72], [142, 115]]}" + } + ], + "images": "35690_exterior_image_1_left#0", + "gt": "[[264, 101], [226, 93], [199, 106], [214, 77], [209, 84], [197, 46], [171, 33], [145, 44], [156, 72], [142, 115]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg3_task_0003_user_0016_scene_0002_cfg_0003_036422060909#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press the three buttons in sequence', and now you are performing subtask 'press the green button on the right, press the green button in the middle.'\nThe trajectory starts at [413, 89]. Considering the current scene, return 10 trajectory points to achieve the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[413, 89], [401, 94], [389, 108], [380, 114], [371, 113], [355, 122], [352, 125], [347, 136], [342, 140], [345, 132]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg3_task_0003_user_0016_scene_0002_cfg_0003_036422060909#151.jpg", + "gt": "[[413, 89], [401, 94], [389, 108], [380, 114], [371, 113], [355, 122], [352, 125], [347, 136], [342, 140], [345, 132]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "28385_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'push the toaster lever button', and now you are performing subtask 'push the toaster lever button.'\nYour starting position is [8, 26]. Given the current scene, predict 10 trajectory points to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[8, 26], [110, 32], [125, 44], [124, 65], [144, 95], [146, 86], [149, 91], [136, 89], [117, 68], [84, 59]]}" + } + ], + "images": "28385_exterior_image_1_left#0", + "gt": "[[8, 26], [110, 32], [125, 44], [124, 65], [144, 95], [146, 86], [149, 91], [136, 89], [117, 68], [84, 59]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "4584_exterior_image_1_left#TrajectoryPrediction_Task#4", + "task": "TrajectoryPrediction_Task", + "p_index": 4, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'the towel on the folding table', and now you are performing subtask 'fold the towel a third time.'\nYour initial coordinate is [191, 98]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[191, 98], [185, 110], [199, 90], [199, 77], [179, 78], [167, 90], [175, 83], [164, 63], [178, 130], [175, 80]]}" + } + ], + "images": "4584_exterior_image_1_left#266", + "gt": "[[191, 98], [185, 110], [199, 90], [199, 77], [179, 78], [167, 90], [175, 83], [164, 63], [178, 130], [175, 80]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "20992_exterior_image_1_left#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'put the candy bar in the sink', and now you are performing subtask 'put the candy bar in the sink.'\nStarting at [142, 79], infer 10 trajectory points based on the current scene to complete the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[142, 79], [106, 98], [84, 131], [91, 141], [113, 122], [145, 123], [150, 159], [150, 147], [129, 140], [124, 132]]}" + } + ], + "images": "20992_exterior_image_1_left#0", + "gt": "[[142, 79], [106, 98], [84, 131], [91, 141], [113, 122], [145, 123], [150, 159], [150, 147], [129, 140], [124, 132]]", + "h": 180, + "w": 320, + "new_h": 168, + "new_w": 308 + }, + { + "id": "RH20T_cfg5_task_0037_user_0007_scene_0010_cfg_0005_037522062165#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'pick up the first block on the table, transfer the first block from the table to the position above the second block, place the first block on top of the second block.'\nStart at [289, 152]. According to the current scene, compute 10 trajectory points to accomplish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[289, 152], [246, 179], [246, 193], [241, 185], [247, 199], [245, 178], [238, 176], [209, 185], [209, 195], [195, 203]]}" + } + ], + "images": "RH20T_cfg5_task_0037_user_0007_scene_0010_cfg_0005_037522062165#0", + "gt": "[[289, 152], [246, 179], [246, 193], [241, 185], [247, 199], [245, 178], [238, 176], [209, 185], [209, 195], [195, 203]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg1_task_0094_user_0001_scene_0009_cfg_0001_038522062547#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'open a box', and now you are performing subtask 'pull the lid of the box upwards to open the box.'\nBegin at [335, 311] (trajectory start). From the scene, output 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[335, 311], [334, 303], [357, 291], [363, 275], [388, 259], [412, 213], [418, 218], [404, 237], [406, 226], [394, 215]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg1_task_0094_user_0001_scene_0009_cfg_0001_038522062547#212.jpg", + "gt": "[[335, 311], [334, 303], [357, 291], [363, 275], [388, 259], [412, 213], [418, 218], [404, 237], [406, 226], [394, 215]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg7_task_0037_user_0014_scene_0002_cfg_0007_037522061512#TrajectoryPrediction_Task#2", + "task": "TrajectoryPrediction_Task", + "p_index": 2, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'stack the blocks in a vertical line of five', and now you are performing subtask 'pick up the third block from the tabletop, transfer the third block from the tabletop to the first block, place the third block on the first block.'\nYour initial coordinate is [238, 141]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[238, 141], [232, 146], [238, 160], [229, 156], [222, 141], [221, 133], [229, 116], [240, 111], [254, 124], [253, 127]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg7_task_0037_user_0014_scene_0002_cfg_0007_037522061512#147.jpg", + "gt": "[[238, 141], [232, 146], [238, 160], [229, 156], [222, 141], [221, 133], [229, 116], [240, 111], [254, 124], [253, 127]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + }, + { + "id": "RH20T_cfg5_task_0003_user_0010_scene_0005_cfg_0005_037522062165#TrajectoryPrediction_Task#0", + "task": "TrajectoryPrediction_Task", + "p_index": 0, + "conversations": [ + { + "from": "human", + "value": "\nThe robot task is 'press three buttons from left to right in sequence', and now you are performing subtask 'press the green button on the right.'\nYour initial coordinate is [289, 152]. Using the scene context, generate 10 trajectory points to finish the task.\nReturn in JSON format: The trajectory is a list of tuples, i.e. [[x1, y1], [x2, y2], w...], where each tuple contains the x and y coordinates of a 2d point." + }, + { + "from": "gpt", + "value": "{\"future_traj\": [[289, 152], [280, 163], [228, 162], [199, 174], [211, 189], [226, 188], [208, 195], [208, 203], [204, 183], [253, 206]]}" + } + ], + "images": "Generation/image/val/traj_init_point_qa/RH20T_cfg5_task_0003_user_0010_scene_0005_cfg_0005_037522062165#0.jpg", + "gt": "[[289, 152], [280, 163], [228, 162], [199, 174], [211, 189], [226, 188], [208, 195], [208, 203], [204, 183], [253, 206]]", + "h": 360, + "w": 640, + "new_h": 364, + "new_w": 644 + } +] \ No newline at end of file