CarlosMunoz0/vla-mujoco-so101-cube_on_tray-joystick-v2.1

该数据集是一个机器人数据集，使用LeRobot工具创建，专门用于机器人学习任务。数据集基于Mujoco模拟环境，机器人类型为so101_mujoco，包含60个训练episodes，总计44995帧，覆盖1个任务。数据以parquet格式存储，视频以mp4格式存储，帧率为30fps。数据集特征丰富，包括动作数据（6维关节位置，如肩部平移、肩部提升、肘部弯曲、腕部弯曲、腕部旋转和夹爪位置）、观测状态（13维，包括关节位置和末端执行器的位置及四元数表示）、多个图像观测（如realsense彩色图像、realsense深度图像、realsense深度可视化图像和腕部摄像头图像，所有图像分辨率为480x640，3通道），以及时间戳、帧索引、episode索引等元数据。数据集适用于机器人控制、视觉导航和强化学习等研究。

This dataset is a robotics dataset created using the LeRobot tool, specifically designed for robot learning tasks. It is based on the Mujoco simulation environment, with robot type so101_mujoco, containing 60 training episodes, totaling 44995 frames, and covering 1 task. The data is stored in parquet format, videos in mp4 format, with a frame rate of 30fps. The dataset features rich information, including action data (6-dimensional joint positions such as shoulder pan, shoulder lift, elbow flex, wrist flex, wrist roll, and gripper positions), observation state (13-dimensional, including joint positions and end-effector position and quaternion representation), multiple image observations (e.g., realsense color images, realsense depth images, realsense depth visualization images, and wrist camera images, all with a resolution of 480x640 and 3 channels), as well as metadata such as timestamps, frame indices, and episode indices. The dataset is suitable for research in robot control, visual navigation, and reinforcement learning.