cell1_20260520_laundry_folding_20260520_131030

该数据集是一个机器人操作数据集，基于LeRobot框架创建，专注于双机械臂（starpilot_yam_gripper）执行任务，可能涉及衣物折叠（从文件名laundry_folding推断）。数据集包含2个episodes、2321帧和1个任务，数据以parquet格式存储，视频以mp4格式存储，帧率为30fps。特征包括：动作（14维浮点数组，用于控制两个机械臂的位姿和抓取宽度）、观测状态（32维浮点数组，包括编码器角度、IMU加速度和陀螺仪数据、位姿和抓取器状态）、以及来自多个摄像头（左腕、右腕和基座）的RGB和深度视频观测（分辨率分别为480x640和768x1024）。数据集用于机器人学习研究，支持动作-观测对的训练和评估。

This is a robotic manipulation dataset created using the LeRobot framework, focusing on tasks performed by dual robotic arms (starpilot_yam_gripper), which may involve laundry folding as inferred from the filename 'laundry_folding'. The dataset contains 2 episodes, 2321 frames, and 1 task. The structured data is stored in Parquet format, while the video data is stored in MP4 format with a frame rate of 30fps. The features include: actions represented as a 14-dimensional floating-point array that controls the pose and gripper width of the two robotic arms; observation states as a 32-dimensional floating-point array covering encoder angles, IMU acceleration and gyroscope data, as well as pose and gripper states; and RGB and depth video observations from multiple cameras (left wrist, right wrist, and base camera) with resolutions of 480×640 and 768×1024 respectively. This dataset is intended for robotic learning research, supporting the training and evaluation of action-observation pairs.