r_b_g_expt_3_pick_place_pnp

该数据集使用LeRobot工具创建，专注于机器人学领域，包含机器人控制任务的数据。基于so101_follower机器人类型，总共有96个训练集，涵盖7个不同任务，包含18117帧数据，帧率为30fps。数据特征包括机器人的动作（如肩部、肘部、腕部和抓取器的位置）、状态观测（与动作相同的关节位置）、来自前置和腕部摄像头的图像观测（分辨率480x640，RGB格式），以及时间戳、帧索引、集索引等元数据。数据以Parquet文件格式存储，视频文件以MP4格式存储，总数据大小约100MB，视频大小约200MB。数据集采用Apache 2.0许可证，主要用于机器人学习和控制研究。Created using the LeRobot toolkit, this dataset is specialized for robotics research and contains data for robot control tasks. Built on the so101_follower robot platform, it includes 96 training datasets covering 7 distinct tasks, with a total of 18117 frames of data at 30fps. The dataset features include robot actions (e.g., positions of the shoulder, elbow, wrist, and gripper), state observations (matching the joint positions of the actions), image observations from the front and wrist cameras (480x640 resolution, RGB format), as well as metadata such as timestamps, frame indices, and dataset indices. The core dataset data is stored in Parquet file format, while the video files are saved in MP4 format. The total size of the tabular dataset is approximately 100 MB, and the video files amount to around 200 MB. This dataset is licensed under Apache 2.0, and is primarily intended for robotics learning and control research.