robotwin_policy_20rollouts_H25

该数据集是一个机器人控制数据集，使用LeRobot工具创建，专门用于aloha机器人平台。它包含200个训练episodes，总计63965帧数据，覆盖10个不同的任务，帧率为50fps。数据以parquet格式存储，分为一个chunk，每个chunk大小为1000。数据集的特征包括：观察状态（14维浮点数组，表示左右机械臂的关节位置，如腰部、肩部、肘部、前臂滚动、手腕角度、手腕旋转和夹爪状态）、动作（14维浮点数组，结构与观察状态相同）、三个摄像头图像（高分辨率摄像头、左腕摄像头和右腕摄像头，均为RGB图像，分辨率480x640），以及时间戳、帧索引、episode索引、索引和任务索引等元数据。该数据集适用于机器人学习、模仿学习和强化学习任务，支持训练模型的输入输出对齐。This dataset is a robot control dataset created using the LeRobot tool, specifically designed for the aloha robot platform. It contains 200 training episodes, totaling 63965 frames of data, covering 10 different tasks with a frame rate of 50fps. The data is stored in parquet format, divided into one chunk, with each chunk size of 1000. The dataset features include: observation states (a 14-dimensional floating-point array representing the joint positions of the left and right robotic arms, such as waist, shoulder, elbow, forearm roll, wrist angle, wrist rotation, and gripper status), actions (a 14-dimensional floating-point array with the same structure as observation states), three camera images (a high-resolution camera, left wrist camera, and right wrist camera, all RGB images with a resolution of 480x640), and metadata such as timestamps, frame index, episode index, index, and task index. This dataset is suitable for robot learning, imitation learning, and reinforcement learning tasks, supporting input-output alignment for training models.