eval_pi0-test0-AE1-8LoRA-carrot

该数据集是使用LeRobot创建的机器人数据集，专注于跟随机器人（so_follower）任务。数据集包含10个episodes，总计10920帧，覆盖1个任务，数据以parquet文件格式存储，总数据文件大小为100MB，视频文件大小为200MB，帧率为30fps。数据集结构包括动作特征（6个关节位置：肩部平移、肩部提升、肘部弯曲、手腕弯曲、手腕旋转、夹爪位置）、观测状态特征（相同的6个关节位置）、观测图像特征（顶部和手腕摄像头，均为RGB视频，分辨率480x640，30fps，无音频），以及元数据如时间戳、帧索引、episode索引等。数据集适用于机器人控制、视觉导航等研究，并遵循Apache 2.0许可证。

This dataset is a robotics dataset created using LeRobot, focusing on the so_follower task. It contains 10 episodes, totaling 10920 frames, covering 1 task. The data is stored in parquet format, with a total data file size of 100MB and a video file size of 200MB, at a frame rate of 30fps. The dataset structure includes action features (6 joint positions: shoulder translation, shoulder lift, elbow bend, wrist bend, wrist rotation, gripper position), observation state features (the same 6 joint positions), observation image features (top and wrist cameras, both RGB video with 480x640 resolution, 30fps, no audio), and metadata such as timestamps, frame indices, episode indices. It is suitable for research in robot control, visual navigation, and follows the Apache 2.0 license.