TrossenRoboticsCommunity/stationary-block-transfer-lerobot-v3

这是一个用于机器人学习的数据集，专门针对块转移任务，使用LeRobot框架创建。数据集采用双WidowX AI Follower机器人，包含60个episodes，总计26940帧，帧率为30fps。数据特征包括动作（14个关节位置）、观测状态（相同关节位置）、以及来自四个摄像头的图像观测：高摄像头、低摄像头、左腕摄像头和右腕摄像头，所有图像分辨率为480x640，3通道彩色视频。数据以parquet格式存储，视频以mp4格式存储，总数据大小约100MB，视频大小约500MB。数据集适用于机器人控制、模仿学习或强化学习研究，标签表明其与RLE-2研究相关。This is a dataset for robotics learning, specifically designed for block transfer tasks, created using the LeRobot framework. It employs a bi WidowX AI Follower robot, comprising 60 episodes with a total of 26,940 frames at 30 fps. The features include actions (14 joint positions), observation states (same joint positions), and image observations from four cameras: high camera, low camera, left wrist camera, and right wrist camera, all with a resolution of 480x640 and 3-channel color video. Data is stored in parquet format, videos in mp4 format, with a total data size of approximately 100 MB and video size of 500 MB. The dataset is suitable for robot control, imitation learning, or reinforcement learning research, with tags indicating its association with RLE-2 study.