snack_20260725_124653

该数据集使用LeRobot创建，专注于机器人学任务，包含动作（action）、观察状态（observation.state）、来自follower和realsense摄像头的图像观察（observation.images.follower和observation.images.realsense）、时间戳（timestamp）、帧索引（frame_index）、episode索引（episode_index）、索引（index）和任务索引（task_index）等特征。动作和观察状态具体包含6个关节位置，如shoulder_pan.pos、shoulder_lift.pos等。图像数据为视频格式，分辨率为480x640，3通道，帧率为30fps。数据集总共有20个episodes，11839帧，1个任务，数据文件大小为100MB，视频文件大小为200MB。机器人类型为so_follower，使用Apache 2.0许可证。This dataset was developed using LeRobot and focuses on robotics tasks. It includes features such as actions, observation states (observation.state), image observations from the follower and RealSense cameras (observation.images.follower and observation.images.realsense), timestamps, frame indices (frame_index), episode indices (episode_index), indices (index), and task indices (task_index). Specifically, actions and observation states encompass six joint positions, such as shoulder_pan.pos, shoulder_lift.pos, and others. The image data is in video format, with a resolution of 480×640, 3 color channels, and a frame rate of 30 fps. The dataset has a total of 20 episodes, 11839 frames, one single task, with a data file size of 100 MB and a video file size of 200 MB. The robot type is so_follower, and it is licensed under the Apache 2.0 License.