act-skill-1-take2-clean

该数据集由LeRobot创建，包含47个episode，共20238帧。数据特征包括：动作（6维，包含肩部、肘部、腕部等关节位置）、状态（6维，与动作相同的关节位置）、两个摄像头图像（腕部摄像头480x640，场景摄像头1080x1920），以及时间戳、帧索引、episode索引等。机器人类型为so_follower。适用于机器人模仿学习等任务。This dataset was created by LeRobot, containing 47 episodes with a total of 20238 frames. The data features include: actions (6-dimensional, including joint positions of shoulder, elbow, wrist, etc.), states (6-dimensional, same joint positions as actions), images from two cameras (wrist camera: 480x640, scene camera: 1080x1920), as well as timestamps, frame indices, episode indices, etc. The robot type is so_follower. It is suitable for tasks such as robot imitation learning.