Task Allocation Without Communication Based on Incomplete Information Game Theory for Multi-robot Systems

被引:36
作者
Dai, Wei [1 ]
Lu, Huimin [1 ]
Xiao, Junhao [1 ]
Zheng, Zhiqiang [1 ]
机构
[1] Natl Univ Def Technol, Coll Mechatron & Automat, Changsha, Hunan, Peoples R China
基金
中国博士后科学基金; 美国国家科学基金会;
关键词
Task allocation; Without communication; Incomplete information game; Soccer robots; OMNIDIRECTIONAL VISION; ROBUST;
D O I
10.1007/s10846-018-0783-y
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In the task allocation of multi-robot system, the communication is an important condition to ensure global consistency. Unfortunately, with the popularity of WLAN, the congestion and interference among the bands are particularly severe, making traditional task allocation methods which rely on communication can not work. In this paper, the task allocation without communication is considered to be an incomplete information game, where game theory is employed to realize the task allocation and cooperation of soccer robots. Firstly, the joint probability distribution of the robot type is established according to the distance information, which can be employed to solve the incomplete information static game. Then the ball velocity information is added to modify the joint probability distribution and the incomplete information dynamic game can be solved in the same way. The experimental results show that the success rate of task allocation without communication can be improved effectively using the proposed method.
引用
收藏
页码:841 / 856
页数:16
相关论文
共 36 条
[1]  
[Anonymous], 2017, STUDIES COMPUTATIONA
[2]  
Bachran T, 2005, PROCEEDINGS OF THE THIRD IASTED INTERNATIONAL CONFERENCE ON COMMUNICATIONS AND COMPUTER NETWORKS, P120
[3]  
Balch T., 1994, AUTONOMOUS ROBOTS, V1, P1
[4]  
Choset H., 1998, Coverage Path Planning: The Boustrophedon Cellular Decomposition, P203, DOI [DOI 10.1007/978-1-4471-1273-0_32, 10.1007/978-1-4471-1273-0_32]
[5]  
Dai W., 2016, ROBOT WORLD CUP, P356
[6]   Framing prisoners and chickens: Valence effects in the prisoner's dilemma and the chicken game [J].
de Heus, Peter ;
Hoogervorst, Niek ;
van Dijk, Eric .
JOURNAL OF EXPERIMENTAL SOCIAL PSYCHOLOGY, 2010, 46 (05) :736-742
[7]  
Eksin C, 2015, IEEE DECIS CONTR P, P5190, DOI 10.1109/CDC.2015.7403031
[8]   Machine learning module to improve communication between agents in Multi-Agent System [J].
El-Sherif, Shimaa M. ;
Far, Behrouz ;
Eberlein, Armin .
2012 11TH INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS (ICMLA 2012), VOL 2, 2012, :295-300
[9]  
Fujiwara-Greve T, 2015, NONCOOPERATIVE GAME, P133
[10]  
Fukuda T., 1990, Proceedings. IROS '90. IEEE International Workshop on Intelligent Robots and Systems '90. Towards a New Frontier of Applications (Cat. No.90TH0332-7), P827, DOI 10.1109/IROS.1990.262502