Lisette1231/eval_20260426_act_flipbreadtopot

该数据集是使用LeRobot创建的机器人学数据集，专为机器人控制和学习任务设计。数据集包含一个完整的episode，总计1436帧，帧率为30fps，使用seeed_b601_dm_follower机器人类型。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。数据集特征包括动作（7个浮点值，对应机器人关节位置）、观测状态（7个浮点值，表示机器人状态）、前视和腕部摄像头图像（分辨率480x640，3通道RGB视频），以及补充信息如策略动作、干预标志和状态。数据集适用于训练和评估机器人策略，支持强化学习和模仿学习应用。

This dataset is a robotics dataset created using LeRobot, designed for robot control and learning tasks. It contains one complete episode with a total of 1436 frames at 30fps, using the seeed_b601_dm_follower robot type. The data is stored in Parquet format, with a total data file size of 100MB and video file size of 200MB. The dataset features include actions (7 float values corresponding to robot joint positions), observation states (7 float values representing robot states), front and wrist camera images (480x640 resolution, 3-channel RGB videos), and complementary information such as policy actions, intervention flags, and states. The dataset is suitable for training and evaluating robot policies, supporting applications in reinforcement learning and imitation learning.