openarm_tablewares_sort10

该数据集由LeRobot创建，专注于机器人技术领域，具体用于openarm_follower机器人。数据集包含10个任务片段（episodes），总计7299帧数据，以parquet格式存储。数据特征包括动作（24维浮点数组，表示7个关节和1个夹爪的位置、速度和扭矩）、观测状态（24维浮点数组，与动作结构相同）、图像观测（前置摄像头和腕部摄像头的视频数据，分辨率为720x1280，30fps，AV1编码），以及时间戳、帧索引、episode索引等元数据。数据集适用于机器人控制和模仿学习任务。This dataset was created by LeRobot, focusing on the robotics domain and specifically tailored for the openarm_follower robot. It contains 10 task episodes, totaling 7299 frames, and is stored in Parquet format. The data features include actions (a 24-dimensional floating-point array representing the position, velocity, and torque of 7 joints plus 1 gripper), observation states (a 24-dimensional floating-point array with the same structure as the actions), image observations (video data from the front-facing camera and wrist camera, with a resolution of 720x1280, 30fps, encoded with AV1), as well as metadata such as timestamps, frame indices, and episode indices. This dataset is suitable for robotics control and imitation learning tasks.