基于蚁群系统的仿真机器人足球攻防转换策略

系统仿真学报 ›› 2015, Vol. 27 ›› Issue (3): 534-541.

基于蚁群系统的仿真机器人足球攻防转换策略

唐贤伦, 周家林, 李腊梅, 张毅

重庆邮电大学工业物联网与网络化控制教育部重点实验室, 重庆 400065

收稿日期:2014-03-03 修回日期:2014-09-13 出版日期:2015-03-08 发布日期:2020-08-20
作者简介:唐贤伦(1977-),男,四川安岳人,博士,教授,研究方向为群体智能、智能系统及机器人;周家林(1990-),男,重庆长寿人,硕士生,研究方向为智能系统及及机器人。
基金资助:
国家自然科学基金项目(60905066);重庆市自然科学基金项目(cstc2011jjA1313);重庆市自然科学基金项目(cstc2012jjA1642)

Dynamic Offense and Defense Conversion Strategy of Robot Soccer Based on Ant Colony System

Tang Xianlun, Zhou Jialin, Li Lamei, Zhang Yi

Key Laboratory of Industrial Internet of Things & Networked Control, Ministry of Education, Chongqing University of Posts and Telecommunications, Chongqing 400065, China

Received:2014-03-03 Revised:2014-09-13 Online:2015-03-08 Published:2020-08-20

摘要/Abstract

摘要： 为了提高机器人足球的整体攻防能力,在动态攻防转换策略中建立了基于蚁群系统的混合通信机制,既增强了足球机器人的协作能力,又避免了足球机器人陷入冲突或任务死锁状态,增加了攻防转换的灵活性。在该通信机制的基础上采用攻防区域划分的方法,以球的位置为驱动信息,通过信息素来确定变换队形。在FIRA仿真平台中实验表明,基于蚁群混合通信机制的动态攻防转换策略使得仿真足球机器人在比赛过程中表现出更优异的性能,改善了球队的整体攻防能力,可有效应用于机器人足球比赛中。

关键词: 仿真机器人足球, 攻防转换, 蚁群系统, 混合通信机制

Abstract: In order to improve the offense and defense capability of robot soccer, a dynamic offense and defense conversion strategy of robot soccer based on hybrid communication mechanism of ant colony system was proposed. The mechanism enhanced robots' collaboration capabilities and avoided the conflict or task deadlock. The strategy divided the region and established the formation according to the sub-regional pheromone, and the position of the ball was regarded as the drive information. Experimental results in FIRA simulation platform show that the dynamic offense and defense conversion strategy have better performance and improve the global offense and defense capability, so it can be applied to robot soccer effectively.

Key words: robot soccer, offense and defense conversion, ant system, hybrid communication mechanism

中图分类号:

TP242

唐贤伦, 周家林, 李腊梅, 张毅. 基于蚁群系统的仿真机器人足球攻防转换策略[J]. 系统仿真学报, 2015, 27(3): 534-541.

Tang Xianlun, Zhou Jialin, Li Lamei, Zhang Yi. Dynamic Offense and Defense Conversion Strategy of Robot Soccer Based on Ant Colony System[J]. Journal of System Simulation, 2015, 27(3): 534-541.

参考文献

[1] Junhua Duan, Yian Zhu, Shujuan Huang.Stigmergy Agent and Swarm-Intelligence-based Multi-agent System[C]// Proc of the 10th IEEE World Congress on Intelligent Control and Automation. USA: IEEE, 2012: 720-724.
[2] Semsar-Kazerooni E, Khorasani K.A game theory approach to multi-Agent team coorperation[C]// Proc. of the American control Conference on Hyatt Regency River front, St. Louis, MO, USA, 2009: 10-12.
[3] Riedmiller M, Gabel T.On experience in a competitive gaming domin: reinforcement learing meets robot cup[C]// Proc. of the 3rd IEEE Symposium on Computational Intelligence and Games. USA: IEEE, 2007: 17-23.
[4] R Serban, L Valentin.An Adaptive Multi-agent Model for Automated Negotiation[C]// Proc. of the 19^th International Conference on Control Systems and Computer. USA: IEEE, 2013: 167-174.
[5] Feldman R, Dagan I.Knowledge discovery in textual database (KDT) [C]// KDD-95. Montreal, Canada: AAAI Press, 1995: 112-117.
[6] H Okada, T Takagi.Evaluation of Multi-objective Genetic Algorithm for RoboCup Soccer Team Evolution[C]// Proc. of the IEEE International Conference on Instrument, Control and Information Technology. USA: IEEE, 2008: 151-154.
[7] H Okada, T Wada, A Yamashita.Evolving RoboCup Soccer Player Formations by Particle Swarm Optimization[C]// Proc. of the IEEE SCIE Annual Conference. USA: IEEE, 2011: 1950-1953.
[8] Mansury E, Nikookar A, Salehi M E.Artificial Bee Colony optimization of ferguson splines for soccer robot path planning[C]// Proc. of the First IEEE RSI/ISM International Conference on Robotics and Mechatronics. USA: IEEE, 2013: 85-89.
[9] Kunli Zhou, Song Ma, Xuliang Zhu, et al. Imroved Ant Colony Algorithm Based on Cellular Automata for Obstacle Avoidance in Robot Soccer[C]// Proc. of the 3rd IEEE International Conference on Computer Science and Information Technology. USA: IEEE, 2010: 298-302.
[10] Bin Chen, Chenxi Xiao, Xiaoshen Song.Intelligent Decision System Based on SOM-LVQ Neural Network for Soccer Robot[C]// Proc. of the IEEE International Conference on Intelligent Human-Machine Systems and Cybernetics. USA: IEEE, 2012: 323-326.
[11] Torabian S, Hosein Alipour S, Mirzargar A, et al. Improving the localization of humanoid soccer robots in specified fields: A neural network approach[C]// Proc. of the IEEE International Conference on Robotics and Mechatronics. USA: IEEE, 2013: 443-448.
[12] Kim J H, Kim Y H, Choi S H, et al. Evolutionary multi-objective optimization in robot soccer system for education[J]. Computational Intelligence Magazine, IEEE (S1556-603x), 2009, 4(1): 31-41.
[13] Kao-Shing Hwang, Yu-Jen Chen, Ching-Huang Lee.Reinforcement Learning in Strategy Selection for a Coordinated Multi-robot System[J]. IEEE Transactions on Systems, Man, and Cybernetics-Part A: Systems and Humans (S1083-4427), 2007, 37(6): 1151-1157.
[14] Dorigo M, Bonabeaub E, Theraulaz G.Ant algorithms and stigmergy[J] Future Generation Computer Systems (S0167-739x), 2000, 16: 851-871.
[15] 段海滨, 马冠军, 王道波, 等.一种求解连续空间优化问题的改进蚁群算法[J]. 系统仿真学报, 2007, 19(5): 974-977.
[16] Valckenaers P, Kollingbaum M, Van Brussel H.Multi-agent coordination and control using stigmergy[J]. Computers in Industry (S0166-3615), 2004, 53(1): 75-96.
[17] Tuan A. Phan, R.Andrew Russell. An Effective Collaboration Algorithm for Swarm Robots Communicating by Sematectonic Stigmergy[C]// Proc. of the 11th IEEE International Conference on Control Automation Robotics & Vision. USA: IEEE, 2010: 390-397.
[18] 覃杨森, 屈四宝, 娄云峰, 等. 基于蚁群算法的SimuroSot中场队形转换技术[J]. 计算机应用研究, 2009, 26(7): 2446-2449.
[19] 唐贤伦, 周维, 张衡, 等. 一种基于多目标混沌PSO的机器人足球防守策略[J]. 系统仿真学报, 2014, 26(1): 51-55.