A Game-Theoretic Reinforcement Learning Approach for Adaptive Interaction at Intersections

被引:8
作者
Jin, Xinze [1 ]
Li, Kuo [1 ]
Jia, Qing-Shan [1 ]
Xia, Huaxia [2 ]
Bai, Yu [2 ]
Ren, Dongchun [2 ]
机构
[1] Tsinghua Univ, BNRist, Dept Automat, Beijing, Peoples R China
[2] Meituan Dianping Grp, Beijing, Peoples R China
来源
2020 CHINESE AUTOMATION CONGRESS (CAC 2020) | 2020年
基金
中国国家自然科学基金;
关键词
MODELS;
D O I
10.1109/CAC51589.2020.9327245
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In this paper, we propose a hi-level algorithm for motion planning at intersections based on a scheme of reasoning game theory and heuristic reinforcement learning. In the upper level, a recurrent neural network is introduced to estimate the type of opponent agent. In the lower level, Q-networks are selectively connected to implement the game with different type. Then the ego agent could update its estimation step-by-step and conclude correspond action from historical joint state. The simulation results show that the hi-level controller improves pass times and collision avoidance performance.
引用
收藏
页码:4451 / 4456
页数:6
相关论文
共 23 条
[1]   Estimation of Multivehicle Dynamics by Considering Contextual Information [J].
Agamennoni, Gabriel ;
Nieto, Juan I. ;
Nebot, Eduardo M. .
IEEE TRANSACTIONS ON ROBOTICS, 2012, 28 (04) :855-870
[2]  
[Anonymous], 2015, ACS SYM SER
[3]  
Camara F., 2018, P MEAS BEH JUN, P238
[4]  
Chen CG, 2019, IEEE INT CONF ROBOT, P6015, DOI [10.1109/ICRA.2019.8794134, 10.1109/icra.2019.8794134]
[5]  
Chen YF, 2017, IEEE INT C INT ROBOT, P1343, DOI 10.1109/IROS.2017.8202312
[6]   Cognition and behavior in two-person guessing games: An experimental study [J].
Costa-Gomes, Miguel A. ;
Crawford, Vincent P. .
AMERICAN ECONOMIC REVIEW, 2006, 96 (05) :1737-1768
[7]   COMPARING MODELS OF STRATEGIC THINKING IN VAN HUYCK, BATTALIO, AND BEIL'S COORDINATION GAMES [J].
Costa-Gomes, Miguel A. ;
Crawford, Vincent P. ;
Iriberri, Nagore .
JOURNAL OF THE EUROPEAN ECONOMIC ASSOCIATION, 2009, 7 (2-3) :365-376
[8]   An Intersection Game-Theory-Based Traffic Control Algorithm in a Connected Vehicle Environment [J].
Elhenawy, Mohammed ;
Elbery, Ahmed A. ;
Hassan, Abdallah A. ;
Rakha, Hesham A. .
2015 IEEE 18TH INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS, 2015, :343-347
[9]   A review of game-theoretic models of road user behaviour [J].
Elvik, Rune .
ACCIDENT ANALYSIS AND PREVENTION, 2014, 62 :388-396
[10]  
He H, 2016, PR MACH LEARN RES, V48