Self-Supervised Disentangled Representation Learning for Third-Person Imitation Learning
Self-Supervised Disentangled Representation Learning for Third-Person Imitation Learning
复制标题
DOI：
10.1109/iros51168.2021.9636363
复制
发表时间：
2021-08
期刊：
影响因子：
--
通讯作者：
Jinghuan Shang;M. Ryoo
中科院分区：
文献类型：
--
作者：
Jinghuan Shang;M. Ryoo
人类通过观察他人来学习模仿。然而，机器人模仿学习通常需要第一人称视角(FPV)中的专家演示。为每个机器人收集这样的FPV视频可能非常昂贵。第三人称模仿学习(TPIL)是通过在第三人称视图(TPV)中观察其他代理来学习行动策略的概念，类似于人类所做的事情。这最终允许在TPV中利用来自许多不同数据源的人类和机器人演示视频来进行策略学习。在本文中，我们提出了一种解决机器人运动任务的TPIL方法。虽然许多具有地面/空中机动性的机器人任务经常涉及到相机运动的动作，但针对这类任务的TPIL的研究一直是有限的。在这里，FPV和TPV的观察在视觉上是非常不同的；FPV显示出运动，而试剂的外观只在TPV中才能观察到。为了使TPIL能够更好地进行状态学习，我们提出了解缠表示学习方法。我们使用双自动编码器结构，加上表示置换损失和时间对比损失，以确保状态表示和视点表示能够很好地分离。实验结果表明了该方法的有效性。
Humans learn to imitate by observing others. However, robot imitation learning generally requires expert demonstrations in the first-person view (FPV). Collecting such FPV videos for every robot could be very expensive.Third-person imitation learning (TPIL) is the concept of learning action policies by observing other agents in a third-person view (TPV), similar to what humans do. This ultimately allows utilizing human and robot demonstration videos in TPV from many different data sources, for the policy learning. In this paper, we present a TPIL approach for robot tasks with egomotion. Although many robot tasks with ground/aerial mobility often involve actions with camera egomotion, study on TPIL for such tasks has been limited. Here, FPV and TPV observations are visually very different; FPV shows egomotion while the agent appearance is only observable in TPV. To enable better state learning for TPIL, we propose our disentangled representation learning method. We use a dual auto-encoder structure plus representation permutation loss and time-contrastive loss to ensure the state and viewpoint representations are well disentangled. Our experiments show the effectiveness of our approach.