eval_act_so101_test48

该数据集使用LeRobot平台创建，专注于机器人学领域，具体针对so101_follower机器人类型。数据集包含1个完整episode、599帧数据和1个任务，以parquet格式存储，总数据大小为100MB，视频文件大小为500MB。数据特征包括：动作数据（6个浮点数表示关节位置，如肩部平移、肩部提升、肘部弯曲、腕部弯曲、腕部旋转和夹爪位置）、观测状态（同样为6个关节位置）、图像观测（顶部和侧面两个视角的视频，分辨率为480x640，3通道彩色，帧率5fps，使用AV1编解码器），以及时间戳、帧索引、episode索引等元数据。该数据集适用于机器人控制、模仿学习或强化学习任务，用于训练和评估机器人模型。

This dataset is created using the LeRobot platform, focusing on the field of robotics, specifically for the so101_follower robot type. It contains 1 complete episode, 599 frames of data, and 1 task, stored in parquet format with a total data size of 100MB and a video file size of 500MB. The data features include: action data (6 floating-point numbers representing joint positions, such as shoulder translation, shoulder elevation, elbow flexion, wrist flexion, wrist rotation, and gripper position), observation state (also 6 joint positions), image observations (video from top and side perspectives with a resolution of 480x640, 3-channel color, 5fps frame rate, using the AV1 codec), as well as metadata such as timestamps, frame indices, and episode indices. This dataset is suitable for robot control, imitation learning, or reinforcement learning tasks, used for training and evaluating robot models.