ankile/real01c-insert-marker-d1-ours-iql-r2-nocf
收藏资源简介:
该数据集是一个使用LeRobot创建的机器人控制数据集,专门用于训练机器人任务。数据集包含50个训练片段,总帧数为16206帧,数据以parquet格式存储,视频文件为mp4格式。数据集的特征丰富,包括机器人状态观测(如笛卡尔位置、关节位置、速度、夹爪位置)、动作(如笛卡尔速度、关节速度、夹爪动作)、任务相关指标(如步骤剩余数、干预标志、成功标志、奖励等),以及来自两个摄像头的图像观测(分辨率480x640,帧率15fps)。机器人类型为franka,仅支持训练任务。
This dataset is a robotics control dataset created using LeRobot, specifically designed for training robot tasks. It contains 50 training episodes with a total of 16,206 frames, stored in parquet format and accompanied by mp4 video files. The dataset features a wide range of attributes, including robot state observations (such as Cartesian position, joint position, velocity, gripper position), actions (such as Cartesian velocity, joint velocity, gripper action), task-related metrics (e.g., steps to go, intervention flag, success flag, reward), and image observations from two cameras (resolution 480x640, 15fps). The robot type is franka, and the dataset is intended for training purposes only.




