banana_green_bowl_eval2_RedGreenBlue_v2

该数据集是一个机器人技术数据集，使用LeRobot框架创建。数据集包含20个训练集，总帧数为5937，帧率为30fps。数据格式为parquet文件，视频文件为mp4格式。特征包括动作（如肩部平移、肩部提升、肘部弯曲、腕部弯曲、腕部滚动和夹爪位置）、观察状态（与动作相同的关节位置）、前视图像（480x640分辨率，RGB通道）、时间戳、帧索引、集索引、索引和任务索引。机器人类型为so_follower，适用于机器人控制和模仿学习任务。

This is a robotics dataset developed using the LeRobot framework. It contains 20 training splits, with a total of 5937 frames at a frame rate of 30 fps. The dataset is stored in Parquet files, and the video files are in MP4 format. The features include actions (such as shoulder translation, shoulder elevation, elbow flexion, wrist flexion, wrist roll, and gripper position), observation states (same joint positions as the actions), front-view RGB images with a resolution of 480×640, timestamps, frame indices, split indices, global indices, and task indices. The robot type for this dataset is so_follower, and it is suitable for robot control and imitation learning tasks.