kunhsiang/eval_exp9_sc1var_grasp_the_small_box_20260528-183450
收藏资源简介:
该数据集是一个机器人学习数据集,使用LeRobot框架创建,专门用于机器人抓取小盒子的任务。数据集包含一个完整的情节(episode),总计2569帧,帧率为30fps。数据涵盖了机器人的动作信息(如肩部、肘部、手腕和夹爪的位置),以及观测数据,包括来自前视、顶部和夹爪摄像头的图像/视频(分辨率480x640,RGB三通道)。此外,数据集还包含时间戳、帧索引、情节索引和任务索引等元数据。数据以parquet文件格式存储,适用于机器人控制、强化学习和计算机视觉研究。
This dataset is a robotics learning dataset created using the LeRobot framework, specifically designed for a robot grasping task involving a small box. It contains one complete episode with a total of 2569 frames at 30fps. The data includes robot actions (such as positions of shoulder, elbow, wrist, and gripper joints) and observations, including images/videos from front, top, and gripper cameras (resolution 480x640, RGB three channels). Additionally, the dataset includes metadata such as timestamps, frame indices, episode indices, and task indices. The data is stored in parquet format and is suitable for research in robot control, reinforcement learning, and computer vision.




