usvz_cube_20260618_191023

该数据集是一个机器人控制数据集，使用LeRobot框架创建，包含15个episodes和15720帧数据。数据特征包括动作信息（如肩部平移、肩部提升、肘部弯曲、腕部弯曲、腕部旋转和夹爪位置）和观察状态（包括关节位置和前端图像，图像分辨率为480x640，3通道，帧率为30fps），以及时间戳、帧索引和episode索引等元数据。数据集专为机器人学习任务设计，涉及so_follower机器人类型，数据以parquet格式和mp4视频格式存储，总数据大小约100MB，视频文件大小约200MB。

This dataset is a robot control dataset created using the LeRobot framework, containing 15 episodes and 15720 frames of data. The data features include action information (such as shoulder translation, shoulder elevation, elbow flexion, wrist flexion, wrist rotation, and gripper position) and observation states (including joint positions and front-end images with a resolution of 480x640, 3 channels, and a frame rate of 30fps), along with metadata like timestamps, frame indices, and episode indices. The dataset is designed for robot learning tasks, involving the so_follower robot type, and is stored in parquet and mp4 video formats, with a total data size of approximately 100MB and a video file size of about 200MB.