cell2_20260520_hossam_coffee-shop_setting_cycle_20260520_205716

这是一个使用LeRobot工具创建的机器人学数据集，针对双臂机器人（starpilot_yam_gripper）。数据集包含8个episodes，总计3121帧数据，帧率为30fps。数据以parquet文件格式存储，总数据文件大小为100MB，视频文件大小为200MB。数据集特征包括：14维动作向量，用于控制两个机械臂的末端执行器位置（x, y, z）、旋转（rx, ry, rz）和抓取宽度；32维状态观测，包括机械臂的编码器角度、IMU加速度和角速度、位姿（位置和四元数）以及抓取器开合状态和距离；以及来自多个摄像头的视频数据，包括左腕和右腕的RGB图像和深度图像（分辨率480x640），以及基座的两个RGB摄像头图像（一个480x640，另一个768x1024）。所有视频采用h264编码，无音频。数据集适用于机器人控制、模仿学习或强化学习任务，但具体任务内容未明确说明。This is a robotics dataset created using the LeRobot tool, targeting the dual-arm robot (starpilot_yam_gripper). The dataset contains 8 episodes, totaling 3121 frames with a frame rate of 30 fps. The data is stored in Parquet file format, with a total data file size of 100 MB and a video file size of 200 MB. The dataset features include: a 14-dimensional action vector for controlling the end-effector positions (x, y, z), rotations (rx, ry, rz) and gripper width of the two robotic arms; a 32-dimensional state observation, including the encoder angles of the robotic arms, IMU acceleration and angular velocity, poses (position and quaternion), as well as the gripper opening/closing state and distance; and video data from multiple cameras, including RGB and depth images of the left and right wrists (resolution 480×640), as well as two RGB camera images from the robot base (one with resolution 480×640 and the other 768×1024). All videos are encoded in h264 format with no audio. This dataset is applicable to robotics control, imitation learning or reinforcement learning tasks, while the specific task content is not specified.