Adversarial Reinforcement Learning Based Robustification of Highlighted Map for Mobile Robot Localization

被引:0
作者
Yoshimura, Ryota [1 ,2 ]
Maruta, Ichiro [2 ]
Fujimoto, Kenji [2 ]
Sato, Ken [3 ]
Kobayashi, Yusuke [3 ]
机构
[1] Tokyo Metropolitan Ind Technol Res Inst, Reg Technol Support Div, Tokyo, Japan
[2] Kyoto Univ, Dept Aeronaut & Astronaut, Kyoto, Japan
[3] Tokyo Metropolitan Ind Technol Res Inst, Digitalizat Promot Sect, Tokyo, Japan
来源
2021 60TH ANNUAL CONFERENCE OF THE SOCIETY OF INSTRUMENT AND CONTROL ENGINEERS OF JAPAN (SICE) | 2021年
关键词
Adversarial reinforcement learning; highlighted map; mobile robots; Monte Carlo localization; particle filters;
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
A highlighted map, where objects with unique shapes are highlighted, has been studied for mobile robot localization. This map improves the localization accuracy without adding any sensors or online computations for localization. In addition, it can be used in various particle-filter-based localization algorithms. For generating a highlighted map, reinforcement learning has been used. Since this method generates the highlighted map by utilizing a limited number of the actual sensor measurement data, the generated map is vulnerable to unexpected sensor measurement noise. In this paper, the robustification method of a highlighted map is proposed. Our proposed method introduces a virtual obstacle that causes measurement noise, and learns both the worst-case obstacle behavior and the optimal highlighted map simultaneously based on adversarial reinforcement learning. We perform a numerical simulation to verify the robustness of the map.
引用
收藏
页码:599 / 605
页数:7
相关论文
共 50 条
[1]   Highlighted Map for Mobile Robot Localization and Its Generation Based on Reinforcement Learning [J].
Yoshimura, Ryota ;
Maruta, Ichiro ;
Fujimoto, Kenji ;
Sato, Ken ;
Kobayashi, Yusuke .
IEEE ACCESS, 2020, 8 :201527-201544
[2]   Mobile Robot Localization with Reinforcement Learning Map Update Decision aided by an Absolute Indoor Positioning System [J].
Garrote, Luis ;
Torres, Miguel ;
Barros, Tiago ;
Perdiz, Joao ;
Premebida, Cristiano ;
Nunes, Urbano J. .
2019 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2019, :1620-1626
[3]   Mobile robot simultaneous localization and map building based on improved particle filter [J].
Department of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, China .
High Technol Letters, 2006, 4 (385-391)
[4]   Mobile Robot Localization Using Map Based on Cadastral Data for Autonomous Navigation [J].
Hoshino, Satoshi ;
Yagi, Hideaki .
JOURNAL OF ROBOTICS AND MECHATRONICS, 2022, 34 (01) :111-120
[5]   Evolutionary Computation for Simultaneous Localization and Mapping Based on Topological Map of a Mobile Robot [J].
Sasaki, Hironobu ;
Kubota, Naoyuki ;
Taniguchi, Kazuhiko .
INTELLIGENT ROBOTICS AND APPLICATIONS, PT I, PROCEEDINGS, 2008, 5314 :883-+
[6]   Simultaneous localization and map building for mobile robot navigation [J].
Anousaki, GC ;
Kyriakopoulos, KJ .
IEEE ROBOTICS & AUTOMATION MAGAZINE, 1999, 6 (03) :42-53
[7]   Experiments in multisensor mobile robot localization and map building [J].
Castellanos, JA ;
Martínez, JM ;
Neira, J ;
Tardós, JD .
INTELLIGENT AUTONOMOUS VECHICLES 1998 (IAV'98), 1998, :369-374
[8]   Mobile Robot Monte Carlo Localization in Incomplete Map [J].
Zhang, Heng ;
Liu, Yan-Li ;
Sun, Jin .
PROCEEDING OF THE 10TH INTERNATIONAL CONFERENCE ON INTELLIGENT TECHNOLOGIES, 2009, :202-205
[9]   Path planning for mobile robot based on improved reinforcement learning algorithm [J].
Xu X. ;
Yuan J. .
Zhongguo Guanxing Jishu Xuebao/Journal of Chinese Inertial Technology, 2019, 27 (03) :314-320
[10]   Bayesian Landmark Learning for Mobile Robot Localization [J].
Sebastian Thrun .
Machine Learning, 1998, 33 :41-76