The Improved Q-Learning Algorithm based on Pheromone Mechanism for Swarm Robot System

被引:0
作者
Shi, Zhiguo [1 ,2 ]
Tu, Jun [1 ]
Zhang, Qiao [1 ]
Zhang, Xiaomeng [1 ]
Wei, Junming [3 ]
机构
[1] Univ Sci & Technol Beijing, Sch Comp & Commun Engn, Beijing 100083, Peoples R China
[2] Ryerson Univ, Dept Aerosp Engn, Toronto, ON M5B 2K3, Canada
[3] Australian Natl Univ, ANU Coll Engn & Comp Sci, Canberra, ACT 2601, Australia
来源
2013 32ND CHINESE CONTROL CONFERENCE (CCC) | 2013年
基金
北京市自然科学基金;
关键词
Swarm robotics system; Distribute reinforcement learning; Q-Learning; Pheromone mechanism;
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
The reinforcement learning of the robot learning have general applicability in path planning, motion control and other aspects of mobile robot, which not only converges of reinforcement learning but also attributes to the simple implementation of the reinforcement learning, the typical reinforcement learning method is Q-Learning. Some improvements of the shortcomings of the Q-Learning is proposed by using the pheromone mechanism of the ant colony algorithm to solve the information sharing problem in the reinforcement learning system. Finally, the improved Q-Learning algorithm is simulated in the platform of Player/Stage. The results are compared with Q-Learning algorithm and PSO algorithm, which prove that the improved Q-Learning has high efficiency in the path planning of swarm robotics.
引用
收藏
页码:6033 / 6038
页数:6
相关论文
共 50 条
[41]   Fidelity-Based Ant Colony Algorithm with Q-learning of Quantum System [J].
Liao, Qin ;
Guo, Ying ;
Tu, Yifeng ;
Zhang, Hang .
INTERNATIONAL JOURNAL OF THEORETICAL PHYSICS, 2018, 57 (03) :862-876
[42]   Fidelity-Based Ant Colony Algorithm with Q-learning of Quantum System [J].
Qin Liao ;
Ying Guo ;
Yifeng Tu ;
Hang Zhang .
International Journal of Theoretical Physics, 2018, 57 :862-876
[43]   Study on Statistics Based Q-learning Algorithm for Multi-Agent System [J].
Xie Ya ;
Huang Zhonghua .
2013 FOURTH INTERNATIONAL CONFERENCE ON INTELLIGENT SYSTEMS DESIGN AND ENGINEERING APPLICATIONS, 2013, :595-600
[44]   Q-learning based handoff algorithm for satellite system with ancillary terrestrial component [J].
Xiong, Dan-Ni ;
Li, Yi .
Tongxin Xuebao/Journal on Communications, 2015, 36 (09) :252-258
[45]   A Task Scheduling Algorithm Based on Q-Learning for WSNs [J].
Zhang, Benhong ;
Wu, Wensheng ;
Bi, Xiang ;
Wang, Yiming .
COMMUNICATIONS AND NETWORKING, CHINACOM 2018, 2019, 262 :521-530
[46]   Q-Learning Algorithm Based on Incremental RBF Network [J].
Hu Y. ;
Li D. ;
He Y. ;
Han J. .
Jiqiren/Robot, 2019, 41 (05) :562-573
[47]   A new Q-learning algorithm based on the Metropolis criterion [J].
Guo, MZ ;
Liu, Y ;
Malec, J .
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 2004, 34 (05) :2140-2143
[48]   Ramp Metering Control Based on the Q-Learning Algorithm [J].
Ivanjko, Edouard ;
Necoska, Daniela Koltovska ;
Greguric, Martin ;
Vujic, Miroslav ;
Jurkovic, Goran ;
Mandzuka, Sadko .
CYBERNETICS AND INFORMATION TECHNOLOGIES, 2015, 15 (05) :88-97
[49]   NAO robot obstacle avoidance based on fuzzy Q-learning [J].
Wen, Shuhuan ;
Hu, Xueheng ;
Li, Zhen ;
Lam, Hak Keung ;
Sun, Fuchun ;
Fang, Bin .
INDUSTRIAL ROBOT-THE INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH AND APPLICATION, 2020, 47 (06) :801-811
[50]   Solving the optimal path planning of a mobile robot using improved Q-learning [J].
Low, Ee Soong ;
Ong, Pauline ;
Cheah, Kah Chun .
ROBOTICS AND AUTONOMOUS SYSTEMS, 2019, 115 :143-161