eval_results_blue_smolvla

该数据集是使用LeRobot平台创建的机器人数据集，专门针对so_follower类型的机器人设计。数据集包含机器人的动作和状态观测数据，其中动作和状态观测均涉及六个关节位置（包括肩部平移、肩部提升、肘部弯曲、腕部弯曲、腕部旋转和夹爪位置）。观测数据还包括来自两个相机（camera1和camera2）的图像数据，每个相机捕获480x640分辨率的RGB视频。此外，数据集提供时间戳、帧索引、剧集索引、索引和任务索引等元数据。数据以Parquet文件格式存储，视频文件为MP4格式，帧率为30fps。数据集结构支持分块处理，总剧集数、总帧数和总任务数在元数据中暂未指定（值为0），但数据文件大小约为100MB，视频文件大小约为200MB。该数据集适用于机器人学习、控制算法开发和计算机视觉研究等任务。

This dataset is a robot dataset created using the LeRobot platform, specifically designed for the so_follower type of robot. It includes the robots actions and state observation data, where both actions and state observations involve six joint positions (including shoulder translation, shoulder elevation, elbow flexion, wrist flexion, wrist rotation, and gripper position). The observation data also includes image data from two cameras (camera1 and camera2), each capturing RGB video at a resolution of 480x640. Additionally, the dataset provides metadata such as timestamps, frame indices, episode indices, indices, and task indices. The data is stored in Parquet file format, with video files in MP4 format at a frame rate of 30fps. The dataset structure supports chunked processing; the total number of episodes, total frames, and total tasks are not specified in the metadata (value 0), but the data file size is approximately 100MB, and the video file size is about 200MB. This dataset is suitable for tasks such as robot learning, control algorithm development, and computer vision research.