kunhsiang/eval_exp9_a2_grasp_the_blue_box_20260526-171849

该数据集是一个机器人学数据集，使用LeRobot框架创建，专注于机器人操作任务，具体为抓取蓝色盒子的评估实验。数据集包含1个完整episode，总计2444帧，帧率为30fps。数据特征包括机器人动作（6个关节位置：肩部平移、肩部升降、肘部弯曲、腕部弯曲、腕部旋转、夹爪位置）、观测状态（与动作相同的6个关节位置）、多视角图像观测（前视、顶部和夹爪摄像头，均为480x640分辨率RGB视频），以及时间戳、帧索引、episode索引等元数据。数据集以Apache 2.0许可证发布，适用于机器人控制、模仿学习或强化学习研究。This is a robotics dataset developed using the LeRobot framework, focused on robotic manipulation tasks, specifically evaluation experiments for blue box grasping. The dataset contains 1 complete episode, totaling 2444 frames at a frame rate of 30 fps. The data features include robot actions (6 joint positions: shoulder translation, shoulder lift, elbow flexion, wrist flexion, wrist rotation, and gripper position), observation states (the same 6 joint positions as the actions), multi-view RGB video observations from three cameras (front-view, top-view, and gripper-mounted camera, all with a resolution of 480x640), as well as metadata such as timestamps, frame indices, and episode indices. The dataset is released under the Apache 2.0 license, and is applicable to research in robot control, imitation learning, or reinforcement learning.