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
[31]   Real Time Map Building by Means of an Ellipse Spatial Criterion and Sensor-Based Localization for Mobile Robot [J].
G. I. Antonaros ;
L. P. Petrou .
Journal of Intelligent and Robotic Systems, 2001, 30 :331-358
[32]   Real time map building by means of an ellipse spatial criterion and sensor-based localization for mobile robot [J].
Antonaros, GI ;
Petrou, LP .
JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS, 2001, 30 (04) :331-358
[33]   Clustering-based attack detection for adversarial reinforcement learning [J].
Rubén Majadas ;
Javier García ;
Fernando Fernández .
Applied Intelligence, 2024, 54 :2631-2647
[34]   Clustering-based attack detection for adversarial reinforcement learning [J].
Majadas, Ruben ;
Garcia, Javier ;
Fernandez, Fernando .
APPLIED INTELLIGENCE, 2024, 54 (03) :2631-2647
[35]   DIGITAL TWIN SIMULATIONS BASED REINFORCEMENT LEARNING FOR NAVIGATION AND CONTROL OF A WHEEL-ON-LEG MOBILE ROBOT [J].
Alsaleh, Saleh ;
Tepljakov, Aleksei ;
Tamre, Mart ;
Kuts, Vladimir ;
Petlenkov, Eduard .
PROCEEDINGS OF ASME 2022 INTERNATIONAL MECHANICAL ENGINEERING CONGRESS AND EXPOSITION, IMECE2022, VOL 2B, 2022,
[36]   Map-based Robust Localization for Indoor Mobile Robots [J].
Song Jianchao ;
Zhang Xuebo ;
Sun Lei ;
Liu Jingtai .
PROCEEDINGS OF THE 36TH CHINESE CONTROL CONFERENCE (CCC 2017), 2017, :6945-6950
[37]   Reinforcement Learning Control of a Real Mobile Robot Using Approximate Policy Iteration [J].
Zhang, Pengchen ;
Xu, Xin ;
Liu, Chunming ;
Yuan, Qiping .
ADVANCES IN NEURAL NETWORKS - ISNN 2009, PT 3, PROCEEDINGS, 2009, 5553 :278-288
[38]   Metric State Space Reinforcement Learning for a Vision-Capable Mobile Robot [J].
Zhumatiy, Viktor ;
Gomez, Faustino ;
Hutter, Marcus ;
Schmidhuber, Juergen .
INTELLIGENT AUTONOMOUS SYSTEMS 9, 2006, :272-+
[39]   Mobile robot localization based on topological model with tiered features [J].
Fang, Fang ;
Ma, Xudong ;
Dai, Xianzhong .
IEEE ICMA 2006: PROCEEDING OF THE 2006 IEEE INTERNATIONAL CONFERENCE ON MECHATRONICS AND AUTOMATION, VOLS 1-3, PROCEEDINGS, 2006, :520-+
[40]   Extended Kalman Filter Based Localization for a Mobile Robot Team [J].
Lu, Jieying ;
Li, Chuxi ;
Su, Weizhou .
PROCEEDINGS OF THE 28TH CHINESE CONTROL AND DECISION CONFERENCE (2016 CCDC), 2016, :939-944