omnaathg/so101_card_memory_trial_20260525_214610

该数据集由LeRobot创建，专注于机器人学领域。它包含一个episode的机器人演示数据，总共有750帧，涉及1个任务。数据集的特征包括机器人的动作（如肩部、肘部、手腕和夹爪的位置）、状态观测（与动作相同的关节位置）、来自三脚架摄像头（分辨率480x640，30fps）和夹爪摄像头（分辨率720x1280，30fps）的视频观测，以及时间戳、帧索引、episode索引、任务索引等元数据。数据以Parquet格式存储，视频以MP4格式编码为AV1。机器人类型为so_follower，数据文件总大小为100MB，视频文件总大小为200MB。数据集适用于机器人控制、模仿学习或强化学习任务。This dataset was created using LeRobot and is focused on robotics tasks. It contains demonstration data from a single episode with a total of 750 frames and one task. The dataset features include robot actions (e.g., positions of shoulder, elbow, wrist, and gripper), state observations (joint positions identical to actions), video observations from a tripod camera (resolution 480x640, 30fps) and a gripper camera (resolution 720x1280, 30fps), as well as metadata such as timestamps, frame indices, episode indices, and task indices. Data is stored in Parquet format, with videos encoded in MP4 using AV1 codec. The robot type is so_follower, with a total data file size of 100MB and video file size of 200MB. The dataset is suitable for robotics control, imitation learning, or reinforcement learning applications.