KS325/skill-set-r2-wm
收藏资源简介:
该数据集是一个机器人学数据集,使用LeRobot创建,专为机器人技能学习设计。数据集包含320个episodes,总计235207帧,覆盖5个不同任务。数据以parquet文件格式存储,视频文件为mp4格式,帧率为30fps。机器人类型为so_follower。数据集特征包括:动作数据(6个浮点数,表示肩部平移、肩部提升、肘部弯曲、腕部弯曲、腕部旋转和夹爪位置)、观察状态(与动作相同的6个浮点数关节位置)、两个摄像头图像(camera1和camera2,均为480x640分辨率、3通道彩色视频),以及时间戳、帧索引、episode索引、索引和任务索引等元数据。数据集适用于机器人控制、视觉感知和强化学习研究。
This dataset is a robotics dataset created using LeRobot, designed for robot skill learning. It contains 320 episodes, totaling 235207 frames, and covers 5 different tasks. The data is stored in parquet files, with video files in mp4 format at 30fps. The robot type is so_follower. Dataset features include: action data (6 float values representing shoulder pan, shoulder lift, elbow flex, wrist flex, wrist roll, and gripper positions), observation state (same 6 float joint positions as actions), two camera images (camera1 and camera2, both 480x640 resolution, 3-channel color videos), and metadata such as timestamp, frame index, episode index, index, and task index. The dataset is suitable for research in robot control, visual perception, and reinforcement learning.




