KS325/open-lower-drawer-r2-emp-val
收藏资源简介:
该数据集是一个机器人学数据集,使用LeRobot工具创建,专门用于机器人控制任务。数据集包含4个总集、2999个总帧和1个总任务,数据以parquet格式存储。机器人类型为so_follower,特征包括动作(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)、观察状态(关节位置)、两个摄像头(camera1和camera2)的视频图像(分辨率为480x640,30fps,编码为av1),以及时间戳、帧索引、集索引、索引和任务索引等元数据。数据集适用于机器人学习和控制研究,例如模仿学习或强化学习。
This is a robotics dataset developed with the LeRobot toolkit, tailored specifically for robotic control tasks. It contains 4 total datasets, 2999 total frames, and 1 overall task, and is stored in Parquet format. The robotic platform type is so_follower. The dataset's features include actions (such as shoulder translation, shoulder elevation, elbow flexion, wrist flexion, wrist rotation, and gripper position), observation states (joint positions), video images from two cameras (camera1 and camera2) with a resolution of 480×640, 30 frames per second, encoded using AV1, as well as metadata including timestamps, frame indices, dataset indices, individual sample indices, and task indices. This dataset is applicable to robotics learning and control research, such as imitation learning or reinforcement learning.




