RobotLearningProject/fullmerge_allDataDagger2_blank

该数据集是使用LeRobot创建的机器人学习数据集，专门针对so_follower机器人类型。数据集包含311个episodes，总计115570帧，覆盖2个不同的任务。数据以parquet文件格式存储，视频数据以mp4格式存储，帧率为30fps。数据集的特征包括动作（6个关节位置：shoulder_pan.pos、shoulder_lift.pos、elbow_flex.pos、wrist_flex.pos、wrist_roll.pos、gripper.pos）、观测状态（与动作相同的关节位置）、前端图像观测（分辨率720x1280，3通道彩色视频）、时间戳、帧索引、episode索引和任务索引。所有数据仅用于训练分割，适用于机器人控制和视觉任务的研究。

This dataset is a robotics learning dataset created using LeRobot, specifically for the so_follower robot type. It contains 311 episodes, totaling 115,570 frames, and covers 2 distinct tasks. The data is stored in parquet file format, with video data in mp4 format at a frame rate of 30fps. The dataset features include actions (6 joint positions: shoulder_pan.pos, shoulder_lift.pos, elbow_flex.pos, wrist_flex.pos, wrist_roll.pos, gripper.pos), observation states (same joint positions as actions), front image observations (resolution 720x1280, 3-channel color video), timestamp, frame index, episode index, and task index. All data is allocated for the training split, making it suitable for research in robotics control and vision tasks.