ankile/real01c-insert-marker-d1-ours-iql-r2-freecf
收藏资源简介:
该数据集是使用LeRobot创建的机器人学数据集,专门针对Franka机器人。它包含50个训练片段,总计15515帧数据,数据以Parquet格式存储,视频以MP4格式存储,帧率为15fps。数据集涵盖了多种观测特征,包括机器人的状态(如笛卡尔位置、关节位置、速度、夹爪位置)和动作特征(如笛卡尔速度、关节速度、夹爪动作)。此外,还包含来自两个不同视角的图像观测(分辨率480x640),以及任务相关指标如成功标志、奖励、干预标志等。该数据集适用于机器人控制、强化学习等研究任务。
This dataset is a robotics dataset created using LeRobot, specifically for the Franka robot. It contains 50 training episodes with a total of 15,515 frames, stored in Parquet format for data and MP4 format for videos at a frame rate of 15fps. The dataset includes various observation features such as robot state (e.g., Cartesian position, joint position, velocity, gripper position) and action features (e.g., Cartesian velocity, joint velocity, gripper action). Additionally, it provides image observations from two different perspectives (resolution 480x640) and task-related metrics like success flags, rewards, and intervention flags. This dataset is suitable for research in robotics control, reinforcement learning, and related areas.




