cell1_20260520_laundry_folding_20260520_123412

该数据集是一个机器人操作数据集，使用LeRobot工具创建，专门用于机器人学习任务。数据集包含两个训练片段，总帧数为1880，涉及一个具体任务（可能为洗衣折叠任务，从数据集名称推断）。机器人类型为starpilot_yam_gripper，具有双机械臂配置。数据特征包括：动作数据（14维浮点数组，控制两个机械臂的x、y、z位置、rx、ry、rz旋转和夹爪宽度）、观测状态数据（32维浮点数组，包含两个机械臂的编码器角度、IMU加速度和角速度、姿态四元数、夹爪开合状态和距离），以及多个摄像头图像数据（来自左腕、右腕和基座摄像头的RGB和深度视频，分辨率分别为480x640和768x1024，帧率为30fps）。数据集还包含时间戳、帧索引、片段索引等元数据，适用于机器人控制、视觉感知和强化学习研究。This dataset is a robotic manipulation dataset created using the LeRobot tool, specifically designed for robotic learning tasks. It contains two training episodes with a total of 1880 frames, and the corresponding task is inferred to be a laundry cloth folding task based on the dataset's name. The robotic system adopts the starpilot_yam_gripper with a dual-arm configuration. The dataset's data features are as follows: 1. Action data: a 14-dimensional floating-point array that controls the x, y, z positions, rx, ry, rz rotations and gripper width of the two robotic arms; 2. Observation state data: a 32-dimensional floating-point array that includes the encoder angles of the two robotic arms, IMU acceleration and angular velocity, attitude quaternions, gripper opening/closing state and distance; 3. Multiple camera image data: RGB and depth videos captured by left wrist, right wrist and base-mounted cameras, with resolutions of 480x640 and 768x1024 respectively, and a frame rate of 30 fps. In addition, the dataset also includes metadata such as timestamps, frame indices and episode indices, which is applicable to research in robotic control, visual perception and reinforcement learning.