Posted 2024-11-05Updated 2024-11-05Notea minute read (About 131 words) visitsAR2-D2 -- Training a Robot Without a Robot背景机器人执行任务的视频数据集非常重要,特别是对于Visual Imitation Learning来说。想要获得这些训练集视频,传统的方法是人工引导机器人做相关动作,然后再录制,耗费大量人力和时间成本,最关键的是机器人是固定在实验室内的,能接触到的物品和任务比较有限,因此这些训练数据中不包含更日常的场景 AR2-D2 -- Training a Robot Without a Robothttp://chen-yulin.github.io/2024/11/05/[OBS]Deep Learning-Imitation Learnning-AR2-D2 -- Training a Robot Without a Robot/AuthorChen YulinPosted on2024-11-05Updated on2024-11-05Licensed under#ImitationLearningMR/AR
2024-10-28Augmented Reality and Robotics - A Survey and Taxonomy for AR-enhanced Human-Robot Interaction and Robotic InterfacesNote