robot-learning-community/rebot-test-dataset
收藏资源简介:
该数据集使用LeRobot创建,包含机器人动作和状态观测数据,用于机器人学习任务。数据集特征包括7个关节位置(肩部平移、肩部提升、肘部弯曲、腕部弯曲、腕部偏航、腕部滚动和夹爪位置),以及时间戳、帧索引、episode索引、任务索引等元数据。数据以Parquet格式存储,总共有1个episode、600帧、1个任务,帧率为30fps,机器人类型为rebot_b601_follower。数据集适用于机器人控制、强化学习等应用场景。
This dataset was created using LeRobot and contains robot action and state observation data for robot learning tasks. The features include 7 joint positions (shoulder_pan.pos, shoulder_lift.pos, elbow_flex.pos, wrist_flex.pos, wrist_yaw.pos, wrist_roll.pos, gripper.pos), along with metadata such as timestamp, frame index, episode index, and task index. The data is stored in Parquet format, with a total of 1 episode, 600 frames, 1 task, a frame rate of 30fps, and robot type rebot_b601_follower. The dataset is suitable for applications such as robot control and reinforcement learning.




