MGRL: Graph neural network based inference in a Markov network with Reinforcement Learning for visual navigation

doi:https://doi.org/10.1016/j.neucom.2020.07.091

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 深度强化学习

	MGRL: Graph neural network based inference in a Markov network with Reinforcement Learning for visual navigation
	Lu, Yi; Chen, Yaran; Zhao, Dongbin; Li, Dong
发表期刊	Neurocomputing
	2021
卷号	0 期号:0 页码:0
摘要	Visual navigation is an essential task for indoor robots and usually uses the map as assistance to providing global information for the agent. Because the traditional maps match the environments, the map-based and map-building- based navigation methods are limited in the new environments for obtaining maps. Although the deep reinforcement learning navigation method, utilizing the non-map-based navigation technique, achieves satisfactory performance, it lacks the interpretability and the global view of the environment. Therefore, we propose a novel abstract map for the deep reinforcement learning navigation method with better global relative position information and more reasonable interpretability. The abstract map is modeled as a Markov network which is used for explicitly representing the regularity of objects arrangement, inuenced by people activities in different environments. Besides, a knowledge graph is utilized to initialize the structure of the Markov network, as providing the prior structure for the model and reducing the dificulty of model learning. Then, a graph neural network is adopted for probability inference in the Markov network. Furthermore, the update of the abstract map, including the knowledge graph structure and the parameters of the graph neural network, are combined into an end-to-end learning process trained by a reinforcement learning method. Finally, experiments in the AI2THOR framework and the physical environment indicate that our algorithm greatly improves the success rate of navigation in case of new environments, thus confirming the good generalization.
关键词	Visual navigation, graph neural network, Markov network, reinforcement learning, probabilistic graph model
DOI	https://doi.org/10.1016/j.neucom.2020.07.091
收录类别	SCI
WOS记录号	WOS:000593102100012
七大方向——子方向分类	强化与进化学习
引用统计	被引频次：12[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/40610
专题	多模态人工智能系统全国重点实验室_深度强化学习复杂系统管理与控制国家重点实验室
通讯作者	Zhao, Dongbin
作者单位	Institute of Automation, Chinese Academy of Sciences
第一作者单位	中国科学院自动化研究所
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Lu, Yi,Chen, Yaran,Zhao, Dongbin,et al. MGRL: Graph neural network based inference in a Markov network with Reinforcement Learning for visual navigation[J]. Neurocomputing,2021,0(0):0.
APA	Lu, Yi,Chen, Yaran,Zhao, Dongbin,&Li, Dong.(2021).MGRL: Graph neural network based inference in a Markov network with Reinforcement Learning for visual navigation.Neurocomputing,0(0),0.
MLA	Lu, Yi,et al."MGRL: Graph neural network based inference in a Markov network with Reinforcement Learning for visual navigation".Neurocomputing 0.0(2021):0.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
MGRL_Graph neural ne（976KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载