kunhsiang/eval_exp9_sc1var_grasp_the_green_box_20260528-172354
收藏资源简介:
该数据集由LeRobot创建,用于机器人学任务,具体涉及机器人抓取绿色盒子的评估实验。数据集包含一个训练片段,总帧数为2379,数据以Parquet格式存储。数据集结构包括动作特征(如肩部、肘部、腕部和夹爪的6个关节位置)、状态观测(与动作相同的关节位置)、三个视角的图像观测(前视、顶视和夹爪视角,均为480x640分辨率的RGB视频,帧率30fps),以及时间戳、帧索引、片段索引等元数据。数据总大小为100MB,视频总大小为200MB,适用于机器人控制、视觉感知和强化学习等研究。
This dataset was created by LeRobot for robotics tasks, specifically for evaluation experiments on robotic grasping of green boxes. The dataset contains one training segment with a total of 2379 frames, and all data is stored in Parquet format. The dataset structure includes action features (six joint positions covering shoulder, elbow, wrist, and gripper joints), state observations (matching the same joint positions as the action features), three-view image observations: front-view, top-view, and gripper-view, all of which are RGB videos with a resolution of 480×640 and a frame rate of 30 fps, as well as metadata such as timestamps, frame indices, and segment indices. The total size of the non-video data is 100 MB, while the total size of the video data is 200 MB. This dataset is suitable for research in fields including robotic control, visual perception, and reinforcement learning.




