serving_b5_20260514_202829

该数据集使用LeRobot创建，专注于机器人技术领域。数据集包含机器人执行任务时的动作和观测数据，具体包括6维动作向量（控制肩部、肘部、腕部和夹持器的位置）、6维观测状态向量（反映机器人关节位置）、顶部和手腕摄像头的视频观测（分辨率480x640，30fps，RGB格式），以及时间戳、帧索引、情节索引、任务索引等元数据。数据集总共有2个情节、1159帧、1个任务，使用omx_follower机器人类型。数据以parquet文件格式存储，视频以mp4格式存储，适用于机器人控制、模仿学习等研究。This dataset is developed using LeRobot and focuses on the field of robotics. It contains action and observation data collected during robotic task execution, specifically including a 6-dimensional action vector that controls the positions of the shoulder, elbow, wrist and gripper, a 6-dimensional observation state vector that reflects the positions of robot joints, video observations from the top and wrist cameras (RGB format, 480x640 resolution, 30 FPS), as well as metadata such as timestamps, frame indices, episode indices and task indices. In total, this dataset has 2 episodes, 1159 frames and 1 task, and uses the omx_follower robot type. The data is stored in Parquet file format, while the videos are stored in MP4 format, and it is applicable to research in robot control, imitation learning and other related fields.