期刊
IEEE ROBOTICS AND AUTOMATION LETTERS
卷 4, 期 4, 页码 4555-4562出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LRA.2019.2931179
关键词
Navigation; Reinforcement learning; Task analysis; Cloud computing; Training; Robot kinematics; Deep learning in robotics and automation; autonomous vehicle navigation; AI-based methods
类别
资金
- Shenzhen Science and Technology Innovation Commission [JCYJ2017081853518789]
- Guangdong Science and Technology Plan Guangdong-Hong Kong Cooperation Innovation Platform [2018B050502009]
- National Natural Science Foundation of China [61603376, U1713211]
- Shenzhen Science, Technology and Innovation Commission [JCYJ20160428154842603]
- Basic Research Project of Shanghai Science and Technology Commission [16JC1401200]
This letter was motivated by the problem of how to make robots fuse and transfer their experience so that they can effectively use prior knowledge and quickly adapt to new environments. To address the problem, we present a learning architecture for navigation in cloud robotic systems: Lifelong Federated Reinforcement Learning (LFRL). In the letter, we propose a knowledge fusion algorithm for upgrading a shared model deployed on the cloud. Then, effective transfer learning methods in LFRL are introduced. LFRL is consistent with human cognitive science and fits well in cloud robotic systems. Experiments show that LFRL greatly improves the efficiency of reinforcement learning for robot navigation. The cloud robotic system deployment also shows that LFRL is capable of fusing prior knowledge. In addition, we release a cloud robotic navigation-learning website to provide the service based on LFRL: www.shared-robotics.com.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据