YOLO2431/put_plate_to_rack_v4_final

该数据集是一个机器人学数据集，由LeRobot创建，专门用于双手机器人（yam_bimanual）的演示数据收集。数据集包含301个情节，总计286,658帧，帧率为30 fps，所有数据均用于训练分割。数据以Parquet格式存储，并包含视频文件。数据集的结构包括观察状态（如左右机械臂的3D位置、6D旋转表示、夹爪状态和关节角度）、动作数据（与观察状态结构相同）、以及来自头部摄像头和左右手腕摄像头的视觉观察（RGB视频，分辨率为360x640）。此外，还包含时间戳、帧索引、情节索引等元数据。该数据集适用于机器人学习任务，如模仿学习或强化学习，用于训练机器人执行多任务操作。This dataset is a robotics dataset created by LeRobot, specifically designed for collecting demonstration data from a bimanual robot (yam_bimanual). It contains 301 episodes, totaling 286,658 frames at 30 fps, with all data allocated to the training split. The data is stored in Parquet format and includes video files. The dataset structure comprises observation states (such as 3D positions, 6D rotation representations, gripper states, and joint angles for both left and right arms), action data (with the same structure as observation states), and visual observations from a head camera and left/right wrist cameras (RGB videos with a resolution of 360x640). Additionally, it includes metadata such as timestamps, frame indices, and episode indices. This dataset is suitable for robotics learning tasks, such as imitation learning or reinforcement learning, to train robots for multi-task manipulation.