YOLO2431/stack_cup_full

该数据集使用LeRobot工具创建，是一个机器人控制数据集，专门针对雅马哈双手机器人（yam_bimanual）。数据集包含156个完整 episodes，总计231,698帧数据，涵盖2个不同任务，并包含468个视频片段。数据特征包括：观察状态（32维浮点向量，编码左右机械手末端执行器的位置（x, y, z）、旋转（6D表示）、夹爪开合状态以及各6个关节角度）；动作空间（同样为32维浮点向量，结构与观察状态一致）；来自三个摄像头的视频观察：头部摄像头、左手腕摄像头和右手腕摄像头，所有视频均为RGB格式，分辨率720x1280，帧率30fps。此外，数据集还包含时间戳、帧索引、episode索引、全局索引和任务索引等元数据。所有数据均划分到训练集，用于机器人学习任务，如模仿学习或强化学习。This dataset was created using the LeRobot tool and is a robotics control dataset specifically for a Yamaha bimanual robot (yam_bimanual). It contains 156 complete episodes, totaling 231,698 frames, covering 2 distinct tasks, and includes 468 video clips. The data features include: observation state (a 32-dimensional float vector encoding the position (x, y, z), rotation (6D representation), gripper state, and 6 joint angles for both the left and right end-effectors); action space (also a 32-dimensional float vector with the same structure as the observation state); video observations from three cameras: head camera, left wrist camera, and right wrist camera, all in RGB format with a resolution of 720x1280 and a frame rate of 30 fps. Additionally, the dataset includes metadata such as timestamps, frame indices, episode indices, global indices, and task indices. All data is allocated to the training set and is intended for robot learning tasks such as imitation learning or reinforcement learning.