klcantrell/so101_spam_musubi_slide_spam_for_pick_up_left_task
收藏资源简介:
该数据集使用LeRobot创建,专注于机器人学领域,具体任务为拾取左侧任务中的spam musubi滑动spam。数据集包含6个episodes,总计4983帧,涉及一个任务。数据特征包括动作(如肩部旋转、肩部抬升、肘部弯曲、腕部弯曲、腕部旋转和夹爪位置)、观察状态(关节位置和来自头顶、基座和手腕视角的图像视频,分辨率为1080x1920,30fps),以及时间戳、帧索引、episode索引等元数据。机器人类型为so_follower,数据以Parquet文件(用于结构化数据)和MP4视频文件存储,总数据大小约100MB,视频文件大小约200MB。数据集适用于机器人控制、视觉感知和强化学习研究。
This dataset was created using LeRobot and focuses on the robotics domain, specifically for the task of spam musubi slide spam for pick up left task. It consists of 6 episodes with a total of 4983 frames, involving one task. The features include actions (e.g., shoulder pan position, shoulder lift position, elbow flex position, wrist flex position, wrist roll position, gripper position), observation states (joint positions and image videos from overhead, base, and wrist perspectives, with a resolution of 1080x1920 at 30fps), and metadata such as timestamp, frame index, and episode index. The robot type is so_follower, and the data is stored in Parquet files (for structured data) and MP4 video files, with a total data size of approximately 100MB and video file size of 200MB. The dataset is suitable for research in robot control, visual perception, and reinforcement learning.




