cell1_20260520_laundry_folding_20260520_130052

该数据集使用LeRobot创建，专注于机器人技术领域，特别是双机械臂（starpilot_yam_gripper类型）执行衣物折叠任务的演示数据。数据集包含2个完整episodes，总计953帧，覆盖1个任务。数据以30fps的帧率采集，包括动作特征（如机械臂的3D位置、旋转和抓取宽度）、观察状态特征（如编码器角度、IMU加速度和陀螺仪数据、机械臂姿态、抓取器开合状态）以及多视角视觉数据：左腕和右腕摄像头的RGB图像和深度图像（分辨率480x640），基座摄像头的两个RGB图像（分辨率分别为480x640和768x1024）。数据集结构以Parquet文件格式存储，适用于机器人学习、模仿学习或强化学习任务。This dataset is created using LeRobot and focuses on the robotics domain, specifically demonstration data for dual-arm robots (starpilot_yam_gripper type) performing clothing folding tasks. It contains 2 complete episodes, totaling 953 frames, covering 1 task. Data is collected at a frame rate of 30fps, including action features (such as robot arm 3D position, rotation, and gripper width), observation state features (such as encoder angles, IMU acceleration and gyroscope data, robot arm pose, gripper open/close status), and multi-view visual data: RGB and depth images from left and right wrist cameras (resolution 480x640), and two RGB images from the base camera (resolutions 480x640 and 768x1024). The dataset structure is stored in Parquet file format and is suitable for robot learning, imitation learning, or reinforcement learning tasks.