eval_so100_herding_1_act

该数据集是使用LeRobot创建的机器人数据集，主要用于机器人技术应用。数据集包含3个episodes，7462帧，1个任务和6个视频。数据特征包括机器人动作（如主肩部旋转、主肩部提升、主肘部弯曲等）、观察状态（与动作相同的特征）、来自笔记本电脑和手机的图像观察（480x640分辨率，3通道，30fps视频）、时间戳、帧索引、episode索引等。数据集结构详细，适用于机器人技术的研究和开发。

This robot dataset was created using LeRobot, and is primarily intended for robotics applications. It consists of 3 episodes, 7462 frames, 1 task, and 6 videos. The data features include robot actions (e.g., primary shoulder rotation, primary shoulder lift, primary elbow flexion, etc.), observation states which share the same set of features as the robot actions, image observations captured from laptops and mobile phones (with a resolution of 480×640, 3-channel, 30fps videos), timestamps, frame indices, episode indices, and more. The dataset has a detailed structure and is suitable for robotics research and development.