kunhsiang/eval_exp9_sc1var_grasp_the_box_outside_the_plate_20260529-114749
收藏资源简介:
该数据集是一个机器人任务数据集,使用LeRobot框架创建。数据集针对so_follower类型的机器人,包含一个完整的任务episode,总计2528帧,帧率为30fps。数据以parquet文件格式存储,视频文件为mp4格式。数据集的特征包括:动作空间(6个自由度,包括肩部平移、肩部提升、肘部弯曲、腕部弯曲、腕部旋转和夹爪位置),观测状态(与动作相同的6个自由度),以及三个视角的图像观测(前视、顶视和夹爪视角),每个图像的分辨率为480x640像素,3个颜色通道。此外,还包含时间戳、帧索引、episode索引、任务索引等元数据。数据集用于机器人控制和学习任务,适用于强化学习或模仿学习研究。
This dataset is a robotics task dataset created using the LeRobot framework. It is designed for the so_follower robot type and contains one complete task episode with a total of 2528 frames at 30fps. The data is stored in parquet format, and video files are in mp4 format. The dataset features include: action space (6 degrees of freedom, covering shoulder pan, shoulder lift, elbow flex, wrist flex, wrist roll, and gripper position), observation state (same 6 degrees of freedom as actions), and image observations from three perspectives (front, top, and gripper), each with a resolution of 480x640 pixels and 3 color channels. Additionally, it includes metadata such as timestamp, frame index, episode index, and task index. The dataset is intended for robot control and learning tasks, suitable for reinforcement learning or imitation learning research.




