ankile/square-01a-ours-mining-beta05-r2-diagnostic-rollouts

该数据集使用LeRobot创建，是一个机器人学习数据集，专门针对panda机器人。数据集包含100个episodes，总计19158个frames，帧率为20fps。数据以parquet文件格式存储，分为训练集（全部数据）。特征包括观察状态（如末端执行器位置、四元数姿态、夹爪位置）、动作（如位置和旋转增量、夹爪动作）、环境状态（如螺母相对于末端执行器的位置和姿态、螺母的绝对位置和姿态）、步骤剩余、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。这些数据适用于机器人控制、强化学习或模仿学习任务，特别是涉及螺母操作或类似场景。This dataset was created using LeRobot and is a robotics learning dataset specifically for the panda robot. It contains 100 episodes with a total of 19158 frames at 20fps. The data is stored in parquet format and split into a training set (all data). Features include observation state (e.g., end-effector position, quaternion orientation, gripper positions), action (e.g., position and rotation deltas, gripper action), environment state (e.g., nut position and orientation relative to the end-effector, absolute nut position and orientation), 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 imitation learning tasks, particularly those involving nut manipulation or similar scenarios.