ankile/square-01a-baseline-uniform-r1-policy-rollouts

该数据集是使用LeRobot创建的机器人数据集，专为机器人学习任务设计。数据集包含100个episodes，总计25027帧，针对单一任务。机器人类型为panda，数据以20fps的帧率采集，存储为parquet格式文件，总数据文件大小为100MB，视频文件大小为200MB。数据集的特征包括观察状态（如末端执行器位置和四元数、夹爪位置）、动作（如末端执行器位置和旋转增量、夹爪动作）、环境状态（如螺母相对于末端执行器的位置和四元数、螺母的绝对位置和四元数）、剩余步数、来源标识、成功标志、有效性标志、奖励、完成标志、初始模拟关节位置和速度、时间戳、帧索引、episode索引、索引和任务索引等。这些数据适用于机器人控制、强化学习或仿真任务，特别是涉及螺母操作场景。This dataset is a robotics dataset created using LeRobot, designed for robot learning tasks. It contains 100 episodes with a total of 25027 frames, focusing on a single task. The robot type is panda, and data is collected at 20fps, stored in parquet format files, with a total data file size of 100MB and video file size of 200MB. The dataset features include observation state (such as end-effector position and quaternion, gripper positions), action (such as delta end-effector position and rotation, gripper action), environment state (such as nut position relative to end-effector and quaternion, absolute nut position and quaternion), steps to go, source identifier, success flag, validity flag, reward, done flag, initial simulation joint positions and velocities, timestamp, frame index, episode index, index, and task index. This data is suitable for robot control, reinforcement learning, or simulation tasks, particularly in scenarios involving nut manipulation.