arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2109.05940cs.ROcs.LG
收藏

具有不变表示的跨域机器人仿真

Cross Domain Robot Imitation with Invariant Representation

The Hong Kong University of Science and Technology(香港科技大学);University of California, Berkeley(加州大学伯克利分校);Nanjing University(南京大学)

Zhao-Heng Yin, Lingfeng Sun, Hengbo Ma, Masayoshi Tomizuka, Wu-Jun Li

摘要:

动物能够模仿彼此的行为,尽管它们在生物力学上存在差异。相比之下,模仿其他类似的机器人是机器人学中更具挑战性的任务。这个问题被称为跨域模仿学习(CDIL)。在本文中,我们考虑CDIL的一类相似的机器人。我们通过引入一个基于不变表示的模仿学习算法来解决这个问题。我们建议学习不变的状态和动作表示,它对齐多个机器人的行为,使CDIL成为可能。与以前的不变表示学习方法相比,我们的方法不需要人类标记的成对数据进行训练。相反,我们使用循环一致性和域混淆来对齐表示并增加其鲁棒性。我们在模拟器中对多个机器人进行了算法测试,并表明可以成功地用现有的专家演示训练看不见的新机器人实例。定性结果还表明,该方法能够学习类似的表示不同的机器人具有相似的行为,这是成功的CDIL是必不可少的。

英文摘要:

Animals are able to imitate each others' behavior, despite their difference in biomechanics. In contrast, imitating the other similar robots is a much more challenging task in robotics. This problem is called cross domain imitation learning~(CDIL). In this paper, we consider CDIL on a class of similar robots. We tackle this problem by introducing an imitation learning algorithm based on invariant representation. We propose to learn invariant state and action representations, which aligns the behavior of multiple robots so that CDIL becomes possible. Compared with previous invariant representation learning methods for similar purpose, our method does not require human-labeled pairwise data for training. Instead, we use cycle-consistency and domain confusion to align the representation and increase its robustness. We test the algorithm on multiple robots in simulator and show that unseen new robot instances can be trained with existing expert demonstrations successfully. Qualitative results also demonstrate that the proposed method is able to learn similar representations for different robots with similar behaviors, which is essential for successful CDIL.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑