so100_test

该数据集使用LeRobot创建，主要包含机器人操作的相关数据。数据集结构包括动作、观察状态、图像（工作空间和手腕视角）、时间戳、帧索引、片段索引等特征。具体来说，动作和观察状态都包含6个浮点型数据，分别代表机器人的不同关节位置。图像数据以视频形式存储，分辨率为480x640，帧率为30fps，无音频。数据集总共有2个片段，1725帧，4个视频，1个任务，所有数据都用于训练。

This dataset was developed using LeRobot, and primarily comprises data related to robotic manipulation operations. The dataset structure includes features such as actions, observation states, images (workspace and wrist viewpoints), timestamps, frame indices, and episode indices. Specifically, both actions and observation states each contain 6 floating-point values, which respectively represent the different joint positions of the robot. The image data is stored in video format, with a resolution of 480×640, a frame rate of 30 fps, and no audio. In total, this dataset has 2 episodes, 1725 frames, 4 videos, and 1 task, and all data is used for training.