minhducvm1912/pick_red_20260527_133805
收藏资源简介:
该数据集由LeRobot创建,专注于机器人技术领域,用于支持机器人学习和控制任务。数据集包含100个episodes,总计63,101帧数据,以parquet格式存储,并附带相应的mp4视频文件。数据特征包括机器人的动作(如肩部、肘部、腕部和夹爪的位置)、观察状态(机器人关节位置)、观察图像(来自左侧和顶部摄像头的视频,分辨率为480x640,3通道,帧率30fps)、时间戳、帧索引、episode索引、索引和任务索引。机器人类型为so_follower,适用于训练和评估机器人控制算法。数据集结构设计用于机器人的视觉和状态反馈学习,支持实时模拟和数据分析。
This dataset is created by LeRobot and focuses on the robotics domain, designed to support robot learning and control tasks. It contains 100 episodes with a total of 63,101 frames, stored in parquet format along with corresponding mp4 video files. The features include robot actions (such as positions of shoulder, elbow, wrist, and gripper), observation states (robot joint positions), observation images (videos from left and top cameras with a resolution of 480x640, 3 channels, and a frame rate of 30fps), timestamp, frame index, episode index, index, and task index. The robot type is so_follower, making it suitable for training and evaluating robot control algorithms. The dataset structure is tailored for visual and state feedback learning in robotics, enabling real-time simulation and data analysis.




