kunhsiang/eval_exp9_sc1var_grasp_the_blue_box_20260528-171001
收藏资源简介:
该数据集是一个机器人技术数据集,使用LeRobot框架创建,专门用于评估机器人抓取蓝色盒子的任务(任务标识:eval_exp9_sc1var_grasp_the_blue_box_20260528-171001)。数据集包含1个任务、1个episode和2382帧数据,数据以30fps的帧率采集。数据集结构包括动作数据(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)、状态观测(机器人关节位置)以及多视角图像观测(前视摄像头、顶部摄像头和夹爪摄像头),所有图像分辨率为480x640,视频编码为av1。机器人类型为so_follower,数据以parquet格式存储,总数据文件大小为100MB,视频文件大小为200MB。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 the LeRobot framework, specifically designed for evaluating the task of grasping a blue box (task identifier: eval_exp9_sc1var_grasp_the_blue_box_20260528-171001). It contains 1 task, 1 episode, and 2382 frames of data, collected at a frame rate of 30fps. The dataset structure includes action data (e.g., shoulder pan, shoulder lift, elbow flex, wrist flex, wrist roll, and gripper positions), state observations (robot joint positions), and multi-view image observations (front camera, top camera, and gripper camera), all with a resolution of 480x640 and video encoding in av1. The robot type is so_follower, and the data is stored in parquet format, with a total data file size of 100MB and video file size of 200MB. The dataset is suitable for research in robot control, visual perception, and reinforcement learning.




