kunhsiang/eval_exp9_sc3var_grasp_the_box_on_the_plate_20260527-163847
收藏资源简介:
该数据集是一个用于机器人技术的数据集,专门针对so_follower类型的机器人。它包含一个任务(total_tasks: 1)和一个episode(total_episodes: 1),总共有2501帧数据,以30fps的帧率采集。数据集包括动作(action)和观察(observation)数据:动作数据由6个浮点值组成,代表机器人的关节位置(如肩部平移、肩部提升、肘部弯曲、手腕弯曲、手腕旋转和夹爪位置);观察数据包括状态(state)——同样由6个浮点值表示关节位置,以及来自三个摄像头的图像——前摄像头(front)、顶部摄像头(top)和夹爪摄像头(gripper),每个图像的分辨率为480x640像素,3个通道(RGB),以视频格式存储。数据集以Parquet文件格式组织,并包含对应的视频文件,总数据文件大小为100MB,视频文件大小为200MB。数据集使用Apache 2.0许可证,并旨在用于机器人学习和控制任务。
This dataset is designed for robotics, specifically for the so_follower robot type. It contains one task (total_tasks: 1) and one episode (total_episodes: 1), with a total of 2501 frames captured at 30fps. The dataset includes action and observation data: action data consists of 6 float values representing robot joint positions (e.g., shoulder pan, shoulder lift, elbow flex, wrist flex, wrist roll, and gripper position); observation data includes state—also represented by 6 float values for joint positions—and images from three cameras: front, top, and gripper cameras, each with a resolution of 480x640 pixels, 3 channels (RGB), stored in video format. The dataset is organized in Parquet file format and includes corresponding video files, with a total data file size of 100MB and video file size of 200MB. It is licensed under Apache 2.0 and is intended for robot learning and control tasks.




