Pick_up_ClariClear_v3

该数据集是一个机器人学习数据集，使用LeRobot框架创建，专门针对Franka机器人。它包含101个episodes，总计48718帧数据，帧率为30fps。数据集仅用于训练目的，数据以parquet文件格式存储，总大小为100MB，同时包含200MB的视频文件。数据特征包括：动作空间（7维，表示末端执行器位姿的增量变化和夹爪命令），观测空间（15维，包括机器人关节位置、夹爪状态和末端执行器位姿），以及来自两个相机的图像观测（每个相机提供480x640分辨率的RGB视频）。此外，数据集还包含时间戳、帧索引、episode索引等元数据，适用于机器人控制、模仿学习或强化学习任务。

This dataset is a robot learning dataset created using the LeRobot framework, specifically designed for Franka robots. It contains 101 episodes, totaling 48,718 frames of data with a frame rate of 30fps. The dataset is intended solely for training purposes, with data stored in parquet file format, totaling 100MB in size, along with 200MB of video files. The data features include: action space (7-dimensional, representing incremental changes in end-effector pose and gripper commands), observation space (15-dimensional, including robot joint positions, gripper status, and end-effector pose), and image observations from two cameras (each providing RGB video at 480x640 resolution). Additionally, the dataset includes metadata such as timestamps, frame indices, and episode indices, making it suitable for robot control, imitation learning, or reinforcement learning tasks.