YOLO2431/put_plate_to_rack_v4_lite

该数据集是一个用于机器人学习的数据集，基于LeRobot平台创建。数据集包含200个训练片段，总计168,948帧，600个视频，使用Yamaha双手机器人（yam_bimanual）采集。数据以30帧/秒的速率记录，包含观察状态（如左右机械臂的位置、旋转、夹持器状态和关节角度）、动作数据（与观察状态结构相同）、以及来自头部、左腕和右腕摄像头的视频观察（分辨率为360x640，3通道RGB视频，H.264编码）。数据集结构还包括时间戳、帧索引、片段索引等元数据，所有数据以Parquet格式存储，并按照片段分块组织。This dataset is a robotics learning dataset created using the LeRobot platform. It contains 200 training episodes, totaling 168,948 frames and 600 videos, collected with a Yamaha bimanual robot (yam_bimanual). Data is recorded at 30 frames per second and includes observation states (such as left and right arm positions, rotations, gripper states, and joint angles), action data (with the same structure as observations), and video observations from head, left wrist, and right wrist cameras (resolution 360x640, 3-channel RGB video, H.264 encoding). The dataset structure also includes metadata like timestamps, frame indices, and episode indices, with all data stored in Parquet format and organized into chunks by episode.