cieclr/bxcube_brg
收藏资源简介:
该数据集是一个用于机器人技术领域的数据集,专门针对so101_follower机器人类型。它包含20个总片段和17737个总帧,所有数据均用于训练。数据以parquet文件格式存储,视频文件以mp4格式存储,帧率为30fps。数据集的特征包括:机器人的动作(包含6个关节位置:肩部平移、肩部升降、肘部弯曲、腕部弯曲、腕部旋转和夹爪位置)、观察状态(同样包含6个关节位置)、两个摄像头(前置和腕部)的图像观察(分辨率为480x640,3通道RGB),以及时间戳、帧索引、片段索引、索引和任务索引等元数据。该数据集适用于机器人控制、模仿学习或强化学习等任务。
This dataset is designed for robotics applications, specifically for the so101_follower robot type. It contains a total of 20 episodes and 17737 frames, all allocated for training. The data is stored in parquet file format, with video files in mp4 format at a frame rate of 30fps. The dataset features include: robot actions (with 6 joint positions: shoulder pan, shoulder lift, elbow flex, wrist flex, wrist roll, and gripper positions), observation states (similarly with 6 joint positions), image observations from two cameras (front and wrist, with a resolution of 480x640 and 3 channels), as well as metadata such as timestamp, frame index, episode index, index, and task index. This dataset is suitable for tasks like robot control, imitation learning, or reinforcement learning.




