xBerry/lerobot_act_rgb

该数据集是一个机器人学数据集，使用LeRobot工具创建，专注于so_follower机器人类型。数据集包含91个episodes，总计40628帧数据，帧率为15fps。数据以parquet文件格式存储，视频文件以mp4格式存储。数据集的结构包括动作数据（如关节位置：肩部平移、肩部提升、肘部弯曲、腕部弯曲、腕部旋转和夹爪位置）、观察状态（与动作相同的关节位置）、多个视频观察（如video0、video8、realsense_d435_color和realsense_d455_color，均为480x640分辨率、3通道彩色视频），以及时间戳、帧索引、episode索引等元数据。数据集适用于机器人控制、视觉感知和强化学习任务。This dataset is a robotics dataset created using the LeRobot tool, focusing on the so_follower robot type. It contains 91 episodes with a total of 40,628 frames at a frame rate of 15fps. The data is stored in parquet file format, and video files are in mp4 format. The dataset structure includes action data (such as joint positions: shoulder pan, shoulder lift, elbow flex, wrist flex, wrist roll, and gripper position), observation states (same joint positions as actions), multiple video observations (e.g., video0, video8, realsense_d435_color, and realsense_d455_color, all with 480x640 resolution and 3-channel color video), and metadata such as timestamps, frame indices, and episode indices. The dataset is suitable for robotics control, visual perception, and reinforcement learning tasks.