NotAyushXD/so101-arm-pickupbowl-50episodes

该数据集使用LeRobot创建，是一个机器人学数据集，专注于机器人控制任务。数据集包含61个episodes，总计36359帧，涉及1个任务。数据以parquet文件格式存储，视频文件为mp4格式。特征包括：动作（6维浮点数组，表示机器人关节位置，如肩部平移、肩部提升、肘部弯曲、手腕弯曲、手腕滚动和夹爪位置）、观察状态（6维浮点数组，表示关节位置）、图像观察（来自手腕和前端摄像头的视频，分辨率480x640，3通道，30fps，视频编码为av1），以及时间戳、帧索引、episode索引、索引和任务索引等元数据。机器人类型为so_follower，适用于机器人学习和控制研究。This dataset, constructed using LeRobot, is a robotics dataset dedicated to robot control tasks. It comprises 61 episodes, totaling 36,359 frames, and covers one single task. The data is stored in Parquet file format, with video files in MP4 format. Its features include actions (a 6-dimensional floating-point array representing robot joint positions, such as shoulder translation, shoulder elevation, elbow flexion, wrist flexion, wrist rotation, and gripper position), observation states (a 6-dimensional floating-point array representing joint positions), image observations (videos captured by the wrist and front-facing cameras with a resolution of 480×640, 3 channels, 30 fps, and encoded in AV1), as well as metadata such as timestamps, frame indices, episode indices, indices, and task indices. The robot platform is so_follower, which is suitable for robotics learning and control research.