cell1_20260520_laundry_folding_20260520_133920

该数据集是一个用于机器人学习的数据集，专门针对折叠衣物任务。它使用LeRobot框架创建，包含2个完整的情节，总计1774帧，数据以30帧每秒的速率采集。数据集结构包括动作数据（14维浮点数组，表示两个机械臂的末端执行器位置、旋转和抓取宽度）、状态观测数据（32维浮点数组，包括机械臂的编码器角度、惯性测量单元数据和位姿信息）以及多个摄像头图像观测数据（包括左腕、右腕和基座摄像头的RGB和深度图像，其中基座摄像头图像分辨率为768x1024，其他为480x640）。所有数据以Parquet格式存储，视频以MP4格式存储，适用于机器人控制、模仿学习或强化学习任务。数据集采用Apache 2.0许可证。This dataset is for robot learning, specifically for the task of folding clothes. It was created using the LeRobot framework and contains 2 complete episodes, totaling 1774 frames, with data collected at a rate of 30 frames per second. The dataset structure includes action data (14-dimensional float arrays representing the end-effector positions, rotations, and gripper widths of two robotic arms), state observation data (32-dimensional float arrays including encoder angles, IMU data, and pose information of the arms), and multiple camera image observations (including RGB and depth images from left wrist, right wrist, and base cameras, with the base camera resolution at 768x1024 and others at 480x640). All data is stored in Parquet format, videos in MP4 format, and it is suitable for robot control, imitation learning, or reinforcement learning tasks. The dataset is licensed under Apache 2.0.