ankile/real01c-insert-marker-d1-baseline-uniform-r2-nocf
收藏资源简介:
该数据集是使用LeRobot工具创建的机器人学习数据集,专门用于机器人控制和强化学习任务。数据集基于Franka机器人平台,包含50个完整的情节(episodes),总计15631个帧(frames),数据以15帧每秒(fps)的速率采集。数据集结构包括观测数据(如机器人的笛卡尔位置、关节位置、速度、夹爪位置等)、动作数据(如笛卡尔速度、关节速度、夹爪动作等)、以及任务相关指标(如成功标志、干预标志、奖励、完成标志等)。此外,数据集还包含来自两个相机视角(标识为18650758_left和25916956_left)的视频数据,分辨率为480x640像素,编码为h264格式。数据以Parquet文件格式存储,总数据文件大小为100MB,视频文件大小为200MB。该数据集适用于机器人行为克隆、强化学习算法训练等应用。
This dataset is a robotics learning dataset created using the LeRobot tool, specifically designed for robot control and reinforcement learning tasks. It is based on the Franka robot platform and includes 50 complete episodes, totaling 15631 frames, collected at a rate of 15 frames per second (fps). The dataset structure comprises observation data (such as Cartesian position, joint position, velocity, gripper position, etc.), action data (such as Cartesian velocity, joint velocity, gripper action, etc.), and task-related metrics (such as success flag, intervention flag, reward, done flag, etc.). Additionally, the dataset includes video data from two camera perspectives (labeled 18650758_left and 25916956_left) with a resolution of 480x640 pixels, encoded in h264 format. The data is stored in Parquet file format, with a total data file size of 100MB and video file size of 200MB. This dataset is suitable for applications such as robot behavior cloning and reinforcement learning algorithm training.




