utkarshsheel/so101_pick_sharpenr_v3_20260530_095754
收藏资源简介:
该数据集由LeRobot创建,专注于机器人技术任务,具体涉及拾取和锐化操作。数据集包含35个episodes,总计20964帧,以30fps的帧率采集。数据特征包括机器人的动作(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)、观测状态(关节位置)、来自顶部和腕部摄像头的图像观测(分辨率为480x640,3通道),以及时间戳、帧索引、episode索引、任务索引等元数据。机器人类型为so_follower,数据以parquet格式存储,总数据文件大小为100MB,视频文件大小为200MB。数据集适用于机器人控制、视觉导航和强化学习等应用。
This dataset was developed by LeRobot, focusing on robotics tasks, specifically pickup and sharpening operations. It contains 35 episodes, totaling 20964 frames collected at 30 fps. The dataset includes robot action data (e.g., shoulder translation, shoulder elevation, elbow flexion, wrist flexion, wrist rotation, and gripper position), observation states (joint positions), image observations from the top-view and wrist-mounted cameras (resolution: 480×640, 3-channel), as well as metadata such as timestamps, frame indices, episode indices, and task indices. The robot platform used is so_follower. The data is stored in Parquet format, with a total data file size of 100 MB and video file size of 200 MB. This dataset is suitable for applications including robot control, visual navigation, and reinforcement learning.




