saipuneethgottam/pickplace_135cam_newdemos_20260526_161032_remapped
收藏资源简介:
该数据集是一个用于机器人技术的数据集,专门针对抓取放置任务(pickplace),由LeRobot创建。数据集包含100个episodes,总帧数为53178,帧率为30fps。数据特征包括机器人的动作(如肩部、肘部、腕部和抓手的位姿)、观察图像(来自三个摄像头,分辨率分别为1280x720、1280x720和640x480,均为RGB视频)、观察状态(机器人的关节位姿),以及episode索引、帧索引、任务索引和时间戳。机器人类型为so_follower,数据以parquet格式存储,视频以mp4格式存储。数据集适用于机器人学习任务,如模仿学习或强化学习。
This dataset is a robotics dataset specifically designed for pick-and-place tasks, created using LeRobot. It contains 100 episodes with a total of 53,178 frames at a frame rate of 30fps. The features include robot actions (such as positions for shoulder, elbow, wrist, and gripper), observation images (from three cameras with resolutions of 1280x720, 1280x720, and 640x480, all in RGB video format), observation states (robot joint positions), along with episode index, frame index, task index, and timestamp. The robot type is so_follower, and the data is stored in parquet format with videos in mp4 format. The dataset is suitable for robotics learning tasks, such as imitation learning or reinforcement learning.




