多Agent联合灭火救援作战系统应用基础研究
|
摘要
多Agent技术作为一种人工智能新技术已经迅速渗透到信息社会的各个环节中。本文将多Agent理论和技术应用于联合灭火救援作战的研究,重点研究体系结构,智能体模型,协作和战术处理等难点问题,以跨地区联合灭火救援作战为背景,探讨联合灭火救援组织指挥的关键问题。本文的研究对于提高消防部队的作战能力,实现快速、高效、科学决策,保护人民群众的生命和财产安全有着重要的现实意义。本论文以“十一五”、“十二五”国家科技支撑项目为支撑,深入探索了联合灭火救援作战的总体结构、内部模块及相关的处理算法,并进行了仿真分析。
论文的主要工作包括：
1)对Agent和系统建模技术的基础理论进行了综述。提出了利用多Agent系统理论来建立联合灭火救援组织指挥体系结构。该体系结构充分考虑了联合灭火救援指挥行为的特点,包含了各种功能组件,兼顾了联合灭火救援模型对运行效率和高级智能决策的需求。
2)提出了多Agent联合灭火救援作战系统框架。其中,提出了一种多Agent联合灭火救援作战框架,在该框架下,系统由指挥Agent,作战Agent和环境Agent组成,并分析了各Agent之间的交互作用关系。
3)作战Agent的结构及实现。研究了作战Agent的思想与目标、运行机制、及实现方法,使得作战Agent模型能够以一种便于从概念模型向仿真模型转化的方式进行表达。
4)在体系结构研究的基础上,借鉴多Agent理论中的合同网协议,提出了联合灭火救援的任务优化分配和协作算法。
5)联合灭火救援战术处理研究,提出了三级战术处理流程,结合实例研究了各级战术决策的方法。
6)采用多Agent软件工具集和通用软件平台(SWARM),用JAVA语言编程,进行了模拟仿真,并开发了一个原型系统,对本文构造的模型及相应机制进行了功能验证。
As one of the new technologies in the artificial intelligence area, the multi-Agent technology has already filtered into many sectors of the information society. In this paper technology and its application in joint firefighting and rescue are studied. System structure, Agent model, collaboration and tactical operation are the focus of this paper. The key technologies of joint firefighting and rescue organizing and commanding are researched to solve problems in Trans-regional joint firefighting and rescue. It will have a significant meaning to improve the operational quality of fire forces, make rapid and efficient decision on emergency and protect human beings safety and property. Sustained by the national research project, we explore the whole structure, inner module, disposal arithmetic of joint firefighting and rescue and their simulations.
The main efforts are outlined as follows:
1) The theory foundations of Agent and system modeling are summarized and the architecture of joint firefighting and rescue organizing and commanding based multi-Agent is proposed. This architecture contains capability modules which can support the characteristics of joint firefighting and rescue commanding behavior mode. The module deals with the behaviors rapidly, while the advanced cognitive behaviors are processed in joint operation.
2) A kind of multi-Agent based joint firefighting and rescue system is proposed. A kind of framework of the multi-Agent based joint firefighting and rescue is proposed, which is composed of the command Agent, operation Agent and environment Agent and the influence of those Agents on the action of each other is described.
3) The study of the structure and implement of operation Agent. The thoughts, goals, circulate mechanism are explored, which makes it more convenient to translate the operation Agent from the concept model to the simulation model.
4) On basis of the research of architecture, the arithmetic on task optimal allocation and collaboration are put forward combing with the protocol by multi-Agent theory.
5) Tactical disposal research. Three levels of tactical disposal are introduced and give the tactical decision method with examples.
6) The paper made an analog emulation based on Swarm and a prototype is also designed and developed to validate the collaboration model proposed in the paper.
论文的主要工作包括：
1)对Agent和系统建模技术的基础理论进行了综述。提出了利用多Agent系统理论来建立联合灭火救援组织指挥体系结构。该体系结构充分考虑了联合灭火救援指挥行为的特点,包含了各种功能组件,兼顾了联合灭火救援模型对运行效率和高级智能决策的需求。
2)提出了多Agent联合灭火救援作战系统框架。其中,提出了一种多Agent联合灭火救援作战框架,在该框架下,系统由指挥Agent,作战Agent和环境Agent组成,并分析了各Agent之间的交互作用关系。
3)作战Agent的结构及实现。研究了作战Agent的思想与目标、运行机制、及实现方法,使得作战Agent模型能够以一种便于从概念模型向仿真模型转化的方式进行表达。
4)在体系结构研究的基础上,借鉴多Agent理论中的合同网协议,提出了联合灭火救援的任务优化分配和协作算法。
5)联合灭火救援战术处理研究,提出了三级战术处理流程,结合实例研究了各级战术决策的方法。
6)采用多Agent软件工具集和通用软件平台(SWARM),用JAVA语言编程,进行了模拟仿真,并开发了一个原型系统,对本文构造的模型及相应机制进行了功能验证。
As one of the new technologies in the artificial intelligence area, the multi-Agent technology has already filtered into many sectors of the information society. In this paper technology and its application in joint firefighting and rescue are studied. System structure, Agent model, collaboration and tactical operation are the focus of this paper. The key technologies of joint firefighting and rescue organizing and commanding are researched to solve problems in Trans-regional joint firefighting and rescue. It will have a significant meaning to improve the operational quality of fire forces, make rapid and efficient decision on emergency and protect human beings safety and property. Sustained by the national research project, we explore the whole structure, inner module, disposal arithmetic of joint firefighting and rescue and their simulations.
The main efforts are outlined as follows:
1) The theory foundations of Agent and system modeling are summarized and the architecture of joint firefighting and rescue organizing and commanding based multi-Agent is proposed. This architecture contains capability modules which can support the characteristics of joint firefighting and rescue commanding behavior mode. The module deals with the behaviors rapidly, while the advanced cognitive behaviors are processed in joint operation.
2) A kind of multi-Agent based joint firefighting and rescue system is proposed. A kind of framework of the multi-Agent based joint firefighting and rescue is proposed, which is composed of the command Agent, operation Agent and environment Agent and the influence of those Agents on the action of each other is described.
3) The study of the structure and implement of operation Agent. The thoughts, goals, circulate mechanism are explored, which makes it more convenient to translate the operation Agent from the concept model to the simulation model.
4) On basis of the research of architecture, the arithmetic on task optimal allocation and collaboration are put forward combing with the protocol by multi-Agent theory.
5) Tactical disposal research. Three levels of tactical disposal are introduced and give the tactical decision method with examples.
6) The paper made an analog emulation based on Swarm and a prototype is also designed and developed to validate the collaboration model proposed in the paper.
引文
[1]李建华,康青春,商靠定等.灭火战术[M].北京：群众出版社,2004.
[2]公安部政治部编.灭火应用战术[M].北京：警官教育出版社,1998：215-218.
[3]公安部消防局.中国消防手册第九卷：灭火救援基础[M].上海：上海科学技术出版社,2006：371.
[4]莫于川.中华人民共和国突发事件应对法释义[M].北京：中国法制出版社,2007.
[5]Anthony L. Avillo. Fireground Strategies [M]. United States:PennWell Corporation, 2002.
[6]NFPA. NFPA1620 Recommended Practice for Pre-Incident Planning,2003 edition[S].USA:National Fire Protection Associa,2003:871.
[7]WKChow, GigiCHLui. Fire safety facilities assessment for karakas, Facilities. Bradford: 2002.Vol.20.Iss.13/14.
[8]季慎强.法国灭火救援的组织指挥[J].浙江消防,2000(2)：36-38.
[9]Ifsta Cmmittee. Essentials of Fire Fighting[M]. USA:Fire Protection Publication,1998: 351-431.
[10]L T Wong, H W Chong, W K Chow, sprinklers systems:Code review in high-rise buildings use,Facilitiese,Bradford:2002.Vol.20,Iss.11/12.
[11]Wing Thye Woo. The Asian financial crisis:Hindsight, insight, foresight, ASEAN Economic Bulletin. Singapore:Aug 2000.Vol.17,Iss2:13.
[12]Xia Dengyou, Kang Qingchun, Xin Jing, etc. Early-warning Method of Vehicle Fires Based on Artificial Neural Network [A]. In:Li Shengcai, Wang Yajun. Progress in Safety Science and Technology:Vol. V [C]. Beijing:Science Press.2005.321-326.
[13]Karen A.Harper, StePhenS.Ho, GregL.Zacharias, MareRaibert. Intelligent Hostile Urban Threat Agent for MOUT operations[C]. Proceeding of the 9th conference on Computer Generated Forces and Behavioral Representation. Orlando, Florida. May 2000.
[14]Cohen, P., H.Levesque. Confirmations and Joint action. IJCAII, (1991),951-957.
[15]M. Wooldridge, N. R. Jennings. Intelligent Agents:Theory and Practice [J]. In Knowledge Engineering Review 10(2),1995
[16]张羽.论联合战斗[M],北京：国防大学出版社,2003
[17]金伟新.大型仿真系统[M],北京：电子工业出版社,2004
[18]董明楷.面向智能主体的动态描述逻辑研究[D],中国科学院研究生院,2003.
[19]司光亚.战略决策综合集成研讨与模拟环境研究与实现[D],国防科技大学研究生院,2000
[20]薛宏涛.基于协进化机制的多智能体系统体系结构及多智能体协作方法研究[D],国防科技大学研究生院,2002
[21]胡晓峰.战争模拟引论[M],北京：国防大学出版社,2004
[22]张维明.智能协作信息技术[M1,北京：电子工业出版社,2002
[23]史越东.指挥决策学[M],北京：解放军出版社,2005
[24]L.Braubach, W. Lamersdorf, A. Pokal. Jadex Implementing a BDI-Infrastructure for JADE Agents [EB/OL]. http://exp.telecomitallalab.com
[25]张全海,施鹏飞.基于本体的多智能体知识共享和协作[J],上海交通大学学报,2003,9：1426-1429.
[26]Alexander OsherenkO. Plane Representation and Plan Execution in Multi-Agent Systems[C]. Proceedings of the KI-2001 Workshop AI in Planning, Scheduling. Configuration and Design,2001
[27]杨瑞平,郭齐胜,赵宏绪,张志荣.C3I系统建模与仿真[M],北京：国防工业出版社,2006
[28]Costanza Charles D. Self-Synchronizing, the Future Joint Force and the United States Army's objective Force [R]. ADA415852,2003
[29]Jason B Scholz. Darren J Sutton. Synchronization and the Networked Force [EB/OL]. http://www.dodccrp.org
[30]李常洪.多Agent合作机制与合作结构研究[D],天津大学,2002
[31]瘫国峰,郝爱民,梁晓辉.一种计算机生成兵力系统自治实体行为描述原语[J],系统仿真学报,Vo1.12 No.7,2000年7月.
[32]曹虎.多主体环境MAGE及其协作与规划研究[D],中国科学院计算技术研究所,2000.
[33]张毅,胡勤友,施朝健.HLA与MAS在分布式仿真应用领域的应用比较[J],计算机技术与发展,2006,1：150-153
[34]侯锋,陈洪辉,罗雪山.基于多Agent的C4ISR系统建模与仿真方法研究[J],光电技术应用,2004,19(3)：25-30
[35]James Allen, Nate Blaylock, George Ferguson. A Problem Solving Model for Collaborative Agents[C]. In First International Joint Conference on Autonomous Agents and Multi-Agent Systems, Bologna, Italy, July 15-19 2002
[36]何炎祥,陈萃萌.Agent和多Agent系统的设计与应用[M],武汉：武汉大学出版社,2001
[37]王红卫.建模与仿真[M],北京：科学出版社,2002
[38]马亚平.作战行动模型的描述对象与建模方法[J].军事运筹与系统工程,20(3)：14-16
[39]徐学文,王寿云.现代作战模拟[M].北京：科学出版社,2001
[40]刘金琨,王树青.多智能体系统联合行动的形式化研究及其应用[J],控制与决策,2000,15(1)：6-10
[41]高波,费奇,陈学广.思考型Agent的基本结构[J],华中科技大学学报,2001,29(2)：25-27
[42]N Minar, K Krmaer, P Macs. Cooperating Mobile Agents for Urnamic Network Routing[Z], MIT Media Lab,2000
[43]郑庆华,李人厚.基于Agent的多层次多群体协同工作的建模[J],西安交通大学学报,2001,35(2)：128-132
[44]Lloyd P Brown. Agent Based Simulation as an Exploratory, Tool in the Study of the Human Dimension of Combat[D], Naval Post-graduate School, Monterey, California,2000
[45]汪江淮,卢利华.联合战役作战指挥[M].北京：国防大学出版社,2001
[46]C Y Miao, A Goh. Y Miao, ZH Yang. Agent that models reasons and makes decisions[Z], Knowledge-Based systems,2002,15:3-211
[47]成思危.复杂性科学探索[M],北京：民主与建设出版社,1999
[48]黄小兵,唐文胜.基于Agent系统的概念、方法和应用[M],计算机与现代化,2000,68(4)：6-11
[49]李建民,王建华,李毅.多智能体系统的一种合作机制[J],计算机研究与发展,1998(2)：35-39
[50]N Minar, K Krmaer, P Macs. Cooperating Mobile Agents for Urnamic Network Routing[Z], MIT Media Lab.,2000
[51]张甫仁.燃气火灾爆炸事故危险源辨识及危险性模拟分析,天然气工业,2005,25(1)：151-154
[52]郑庆华,李人厚.CSCW的一种建模与实现方法.计算机学报,1998,VoLZI(增刊)196～202
[53]李成揩,詹永照,茅兵,谢立.基于角色的CSCW系统访问控制模型,软件学报,2000,11(7)：931-937
[54]Atul Prakash, Hyong SoP Shim, DistView. Support for Building Efficient Collaborative Applications using RePlicated Objects.In:Proeeedings of the ACM Conference on CSCW,1994, ChapelHill, NC, USA,153-163
[55]Espejo R, Harnden R. The Viable Systems Model-Interpretations and Applications of Stafford Beer's VSM, Great Britain:John Wiley&Sons Ltd.,1989
[56]Shaplet L.,Grofman B. Optimizing Group Judgmental Accuracy in the Presence of Interdependencies.Public Choice,43,1984:329-343
[57]Remy P.A., Levis A.H. On the Design of Distributed Organizational Structures.Proc.10th IFAC World Congress.Munich,FRG1987
[58]Wasserman S., Faust K. Social Network Analysis:Methods and Applications. Cambridge:Cambridge University Press,1994
[59]PaulF.Reynolds, Natrajan, A., Srinivasan.S. ConsisteneyMaintenanceinmulti-resolution Simulations, ACM Transaetions on Modeling and Computer Simulations, Vol.7, No.3 July 1997
[60]邱晓刚.复杂大系统面向对象仿真的理论与方法研究,博十学位论文,国防科技大研究生院,1998.4.
[61]冯珊,黄景平等.用于复杂系统建模与仿真的面向智能体技术,系统仿真学报,vo1.1l,No.3,1999
[62]Crag.S.Unrath. Dynamic Exploration of Helicopter Recotmaissance Throught Agent-Based Modeling, Master thesis, NavalPostgraduateSehool, Monierey, California, September, 2000.
[63]郑援,李思昆,胡成军.虚拟实体对象的建模方法研究,国防科学技术大学学报,Vol 20,No.1,1998
[64]庞国峰,郝爱民,梁晓辉.一种计算机生成兵力系统自治实体行为描述原语.系统仿真学报,Vol 12,No.4,2000
[65]刘大有,杨鲤,陈建中.Agent的研究现状与发展趋势.软件学报,2000,11(3)
[66]PeterClark, HelenPongracic, Arvind Chandran. Researching the Use of Agent-Based CGF in Human-in-the-Loop simulation.Proeeedingof the 9th conference on computer Generated Forces and Behavioral Representation, Orlando, Florida, May,2000
[67]杨立功,郭齐胜.计算机生成兵力的研究进展.计算机仿真,vol 17,No.3,2000
[68]林尧瑞,马少平.人工智能导论,北京：清华大学出版社,1996
[69]董红斌,王建华.多Agent技术研究,计算机应用研究,1999
[70]Brander G Decision Making Behavior Observed during High Level Wargames, DERA, Famborough, UK,1994
[71]王永寿等译.武器-目标分配问题的一种算法,现代防御技术,1993
[72]刘秀罗,黄柯棣.数据融合技术在CGF建模中的应用,国防科技大学学报,2001
[73]史忠植.智能主体及其应用,北京：科学出版社,2000
[74]姚莉,张维明.智能协作信息技术,北京：电子工业出版社,2002
[75]G. Weiss. Multi-Agent Systems:A Modern Approach to Distributed Artificial Intelligence, 1999
[76]G. Weiss. Adaptation and learning in multi-Agent systems:Some remarks, Lecture Note on Artifieial Intelligence 1042, London, Springer,1996:1-39
[77]张汝波,顾国昌,刘照德,王醒策.强化学习理论、算法及应用,控制理论与应用,2000,17(5)
[78]陈文伟,智能决策技术,北京：电子工业出版社,1998
[79]蔡庆生,陈小平,刘贵全.多Agent系统中的策略协作学习,清华大学学报(自然科学版),1998,38(52)：157-160
[80]王玉善,蓝少华,吴慧中.基于Agent的分布式专家系统的协作过程中的学习问题的研究,小型微型计算机系统,2000(9)
[81]M.V. Nagendra Prasad, Leaming Orgnazational roles in a Heterogeneous Multi-Agent system, In Proe, of the 2nd Internationalconference Multi-Agent systems, Monlo Park, CA, AAAIPress,1996:291-298
[82]Suryadi, Leaming Models of Other Agents Using Influence Diagrams, In the Proeeedings of ICMAS'00,2000
[83]李宁,高阳,陆鑫,陈世福.一种基于强化学习的学习Agent,计算机研究与发展,2001(9)
[84]高阳.强化学习及其在多Agent系统中的应用研究,南京大学博士学位论文,2000
[85]Martin Lauer, Martin Riedmiler. Analgorithm for distributed reinforcement learning in cooperative multi-Agent system, In the Proceedings of the 7th International conference on Machine Learning,2000:535-542
[86]L.P.Kaelbling, M.L.Littman., A.W.Moore. Reinforcement leaming:A survey, Joural of Artificial Intelligence Research,1996,14
[87]尹晓虎.多Agent协同的强化学习方法研究,国防科技大学研究生院硕士学位论文,2003
[88]XiaofengWang, Tuomas Sandholm. Reinforcement Learning TO Play An Optimal Nash Equilibrium In Team Markov Games, In Advances in Neural Information Proeessing Systems15(NIPS-2002),Vaneouver,2002
[89]蔡庆生,张波.一种基于Agent团队的强化学习模型与应用研究,计算机研究与发展,2000,37(9)
[90]董红斌,孙羽.多Agent系统的现状与进展,计算机应用研究,2001,Vol 18(1)：54-65
[91]王长缨,姚莉,陈文伟.一种多Agent协作的强化学习方法,中国人工智能进展,(2003),北京邮电大学出版社,北京,2003
[92]姚莉,张维明,王长缨.基于多智能体的复杂信息系统开发方法研究,管理科学学报,2002,5(5)
[93]Miehael Bowling, Manuela Veloso. An Analysis of Stoehastic Game Theory for Multi-Agent Reinforcement Learning, CMU-CS-00-165, Oetober,2000
[94]肖人彬,王雪,费奇等。相关针具合成方法的研究。模式识别和人工智能,1993,9：227-234
[95]N.J.Nilsson著，郑扣根等译,人工智能,北京：机械工业出版社,2000
[96]何建华,高晓光等.网络中心战概念及其空战应用研究,火力与指挥控制,2003,28(4)
[97]刘海龙.基于合同网的多Agent任务分配分布式优化算法,浙江大学学报(工学版),2001,35(5)：550-554
[98]郭锐锋.基于合同网的任务分配方法的研究,小型微型计算机系统,1999,20(10)740-743
[99]熊伟,何友.信息融合系统中的态势预测技术,火力与指挥控制,2001,26(4)：47-50
[100]蓝金辉,马宝华等.D-S证据理论数据融合方法在目标识别中的应用,清华大学报,2001,41(2)：53-55
[101]S.Le Hegarat-Masele, I.Bloeh and D.Vidal-Madjar. Application of Dempster-Shafer Remote Sensing, Evidence Theory to Unsupervised Classification in Multi-source IEEE Trans on Geoseience and Remote Sensing, July 1997,35(4):1018-1031
[102]周彦,戴剑伟.HLA仿真程序设计,北京：电子工业出版社,2002
[103]曹晓东,郭嘉诚.论指挥控制规则建模,军事运筹与系统工程,2006,20(3)：22-26
[104]陈樟洪.IBM Rational Software Architect建模,北京：电子工业出版社,2008
[105]方美其,张树人.复杂系统建模与仿真,北京：中国人民出版社,2005
[106]胡晓峰,司亚光.战争模拟原理与系统,北京：国防大学出版社,2009
[107]张守一.SWARM及其在经济研究中的应用[J],数量经济技术经济研究,2001,(1)：94-97
[108]刘贞,程勇军.Swarm for Java仿真及编程实现,北京：机械工业出版社,2009
[2]公安部政治部编.灭火应用战术[M].北京：警官教育出版社,1998：215-218.
[3]公安部消防局.中国消防手册第九卷：灭火救援基础[M].上海：上海科学技术出版社,2006：371.
[4]莫于川.中华人民共和国突发事件应对法释义[M].北京：中国法制出版社,2007.
[5]Anthony L. Avillo. Fireground Strategies [M]. United States:PennWell Corporation, 2002.
[6]NFPA. NFPA1620 Recommended Practice for Pre-Incident Planning,2003 edition[S].USA:National Fire Protection Associa,2003:871.
[7]WKChow, GigiCHLui. Fire safety facilities assessment for karakas, Facilities. Bradford: 2002.Vol.20.Iss.13/14.
[8]季慎强.法国灭火救援的组织指挥[J].浙江消防,2000(2)：36-38.
[9]Ifsta Cmmittee. Essentials of Fire Fighting[M]. USA:Fire Protection Publication,1998: 351-431.
[10]L T Wong, H W Chong, W K Chow, sprinklers systems:Code review in high-rise buildings use,Facilitiese,Bradford:2002.Vol.20,Iss.11/12.
[11]Wing Thye Woo. The Asian financial crisis:Hindsight, insight, foresight, ASEAN Economic Bulletin. Singapore:Aug 2000.Vol.17,Iss2:13.
[12]Xia Dengyou, Kang Qingchun, Xin Jing, etc. Early-warning Method of Vehicle Fires Based on Artificial Neural Network [A]. In:Li Shengcai, Wang Yajun. Progress in Safety Science and Technology:Vol. V [C]. Beijing:Science Press.2005.321-326.
[13]Karen A.Harper, StePhenS.Ho, GregL.Zacharias, MareRaibert. Intelligent Hostile Urban Threat Agent for MOUT operations[C]. Proceeding of the 9th conference on Computer Generated Forces and Behavioral Representation. Orlando, Florida. May 2000.
[14]Cohen, P., H.Levesque. Confirmations and Joint action. IJCAII, (1991),951-957.
[15]M. Wooldridge, N. R. Jennings. Intelligent Agents:Theory and Practice [J]. In Knowledge Engineering Review 10(2),1995
[16]张羽.论联合战斗[M],北京：国防大学出版社,2003
[17]金伟新.大型仿真系统[M],北京：电子工业出版社,2004
[18]董明楷.面向智能主体的动态描述逻辑研究[D],中国科学院研究生院,2003.
[19]司光亚.战略决策综合集成研讨与模拟环境研究与实现[D],国防科技大学研究生院,2000
[20]薛宏涛.基于协进化机制的多智能体系统体系结构及多智能体协作方法研究[D],国防科技大学研究生院,2002
[21]胡晓峰.战争模拟引论[M],北京：国防大学出版社,2004
[22]张维明.智能协作信息技术[M1,北京：电子工业出版社,2002
[23]史越东.指挥决策学[M],北京：解放军出版社,2005
[24]L.Braubach, W. Lamersdorf, A. Pokal. Jadex Implementing a BDI-Infrastructure for JADE Agents [EB/OL]. http://exp.telecomitallalab.com
[25]张全海,施鹏飞.基于本体的多智能体知识共享和协作[J],上海交通大学学报,2003,9：1426-1429.
[26]Alexander OsherenkO. Plane Representation and Plan Execution in Multi-Agent Systems[C]. Proceedings of the KI-2001 Workshop AI in Planning, Scheduling. Configuration and Design,2001
[27]杨瑞平,郭齐胜,赵宏绪,张志荣.C3I系统建模与仿真[M],北京：国防工业出版社,2006
[28]Costanza Charles D. Self-Synchronizing, the Future Joint Force and the United States Army's objective Force [R]. ADA415852,2003
[29]Jason B Scholz. Darren J Sutton. Synchronization and the Networked Force [EB/OL]. http://www.dodccrp.org
[30]李常洪.多Agent合作机制与合作结构研究[D],天津大学,2002
[31]瘫国峰,郝爱民,梁晓辉.一种计算机生成兵力系统自治实体行为描述原语[J],系统仿真学报,Vo1.12 No.7,2000年7月.
[32]曹虎.多主体环境MAGE及其协作与规划研究[D],中国科学院计算技术研究所,2000.
[33]张毅,胡勤友,施朝健.HLA与MAS在分布式仿真应用领域的应用比较[J],计算机技术与发展,2006,1：150-153
[34]侯锋,陈洪辉,罗雪山.基于多Agent的C4ISR系统建模与仿真方法研究[J],光电技术应用,2004,19(3)：25-30
[35]James Allen, Nate Blaylock, George Ferguson. A Problem Solving Model for Collaborative Agents[C]. In First International Joint Conference on Autonomous Agents and Multi-Agent Systems, Bologna, Italy, July 15-19 2002
[36]何炎祥,陈萃萌.Agent和多Agent系统的设计与应用[M],武汉：武汉大学出版社,2001
[37]王红卫.建模与仿真[M],北京：科学出版社,2002
[38]马亚平.作战行动模型的描述对象与建模方法[J].军事运筹与系统工程,20(3)：14-16
[39]徐学文,王寿云.现代作战模拟[M].北京：科学出版社,2001
[40]刘金琨,王树青.多智能体系统联合行动的形式化研究及其应用[J],控制与决策,2000,15(1)：6-10
[41]高波,费奇,陈学广.思考型Agent的基本结构[J],华中科技大学学报,2001,29(2)：25-27
[42]N Minar, K Krmaer, P Macs. Cooperating Mobile Agents for Urnamic Network Routing[Z], MIT Media Lab,2000
[43]郑庆华,李人厚.基于Agent的多层次多群体协同工作的建模[J],西安交通大学学报,2001,35(2)：128-132
[44]Lloyd P Brown. Agent Based Simulation as an Exploratory, Tool in the Study of the Human Dimension of Combat[D], Naval Post-graduate School, Monterey, California,2000
[45]汪江淮,卢利华.联合战役作战指挥[M].北京：国防大学出版社,2001
[46]C Y Miao, A Goh. Y Miao, ZH Yang. Agent that models reasons and makes decisions[Z], Knowledge-Based systems,2002,15:3-211
[47]成思危.复杂性科学探索[M],北京：民主与建设出版社,1999
[48]黄小兵,唐文胜.基于Agent系统的概念、方法和应用[M],计算机与现代化,2000,68(4)：6-11
[49]李建民,王建华,李毅.多智能体系统的一种合作机制[J],计算机研究与发展,1998(2)：35-39
[50]N Minar, K Krmaer, P Macs. Cooperating Mobile Agents for Urnamic Network Routing[Z], MIT Media Lab.,2000
[51]张甫仁.燃气火灾爆炸事故危险源辨识及危险性模拟分析,天然气工业,2005,25(1)：151-154
[52]郑庆华,李人厚.CSCW的一种建模与实现方法.计算机学报,1998,VoLZI(增刊)196～202
[53]李成揩,詹永照,茅兵,谢立.基于角色的CSCW系统访问控制模型,软件学报,2000,11(7)：931-937
[54]Atul Prakash, Hyong SoP Shim, DistView. Support for Building Efficient Collaborative Applications using RePlicated Objects.In:Proeeedings of the ACM Conference on CSCW,1994, ChapelHill, NC, USA,153-163
[55]Espejo R, Harnden R. The Viable Systems Model-Interpretations and Applications of Stafford Beer's VSM, Great Britain:John Wiley&Sons Ltd.,1989
[56]Shaplet L.,Grofman B. Optimizing Group Judgmental Accuracy in the Presence of Interdependencies.Public Choice,43,1984:329-343
[57]Remy P.A., Levis A.H. On the Design of Distributed Organizational Structures.Proc.10th IFAC World Congress.Munich,FRG1987
[58]Wasserman S., Faust K. Social Network Analysis:Methods and Applications. Cambridge:Cambridge University Press,1994
[59]PaulF.Reynolds, Natrajan, A., Srinivasan.S. ConsisteneyMaintenanceinmulti-resolution Simulations, ACM Transaetions on Modeling and Computer Simulations, Vol.7, No.3 July 1997
[60]邱晓刚.复杂大系统面向对象仿真的理论与方法研究,博十学位论文,国防科技大研究生院,1998.4.
[61]冯珊,黄景平等.用于复杂系统建模与仿真的面向智能体技术,系统仿真学报,vo1.1l,No.3,1999
[62]Crag.S.Unrath. Dynamic Exploration of Helicopter Recotmaissance Throught Agent-Based Modeling, Master thesis, NavalPostgraduateSehool, Monierey, California, September, 2000.
[63]郑援,李思昆,胡成军.虚拟实体对象的建模方法研究,国防科学技术大学学报,Vol 20,No.1,1998
[64]庞国峰,郝爱民,梁晓辉.一种计算机生成兵力系统自治实体行为描述原语.系统仿真学报,Vol 12,No.4,2000
[65]刘大有,杨鲤,陈建中.Agent的研究现状与发展趋势.软件学报,2000,11(3)
[66]PeterClark, HelenPongracic, Arvind Chandran. Researching the Use of Agent-Based CGF in Human-in-the-Loop simulation.Proeeedingof the 9th conference on computer Generated Forces and Behavioral Representation, Orlando, Florida, May,2000
[67]杨立功,郭齐胜.计算机生成兵力的研究进展.计算机仿真,vol 17,No.3,2000
[68]林尧瑞,马少平.人工智能导论,北京：清华大学出版社,1996
[69]董红斌,王建华.多Agent技术研究,计算机应用研究,1999
[70]Brander G Decision Making Behavior Observed during High Level Wargames, DERA, Famborough, UK,1994
[71]王永寿等译.武器-目标分配问题的一种算法,现代防御技术,1993
[72]刘秀罗,黄柯棣.数据融合技术在CGF建模中的应用,国防科技大学学报,2001
[73]史忠植.智能主体及其应用,北京：科学出版社,2000
[74]姚莉,张维明.智能协作信息技术,北京：电子工业出版社,2002
[75]G. Weiss. Multi-Agent Systems:A Modern Approach to Distributed Artificial Intelligence, 1999
[76]G. Weiss. Adaptation and learning in multi-Agent systems:Some remarks, Lecture Note on Artifieial Intelligence 1042, London, Springer,1996:1-39
[77]张汝波,顾国昌,刘照德,王醒策.强化学习理论、算法及应用,控制理论与应用,2000,17(5)
[78]陈文伟,智能决策技术,北京：电子工业出版社,1998
[79]蔡庆生,陈小平,刘贵全.多Agent系统中的策略协作学习,清华大学学报(自然科学版),1998,38(52)：157-160
[80]王玉善,蓝少华,吴慧中.基于Agent的分布式专家系统的协作过程中的学习问题的研究,小型微型计算机系统,2000(9)
[81]M.V. Nagendra Prasad, Leaming Orgnazational roles in a Heterogeneous Multi-Agent system, In Proe, of the 2nd Internationalconference Multi-Agent systems, Monlo Park, CA, AAAIPress,1996:291-298
[82]Suryadi, Leaming Models of Other Agents Using Influence Diagrams, In the Proeeedings of ICMAS'00,2000
[83]李宁,高阳,陆鑫,陈世福.一种基于强化学习的学习Agent,计算机研究与发展,2001(9)
[84]高阳.强化学习及其在多Agent系统中的应用研究,南京大学博士学位论文,2000
[85]Martin Lauer, Martin Riedmiler. Analgorithm for distributed reinforcement learning in cooperative multi-Agent system, In the Proceedings of the 7th International conference on Machine Learning,2000:535-542
[86]L.P.Kaelbling, M.L.Littman., A.W.Moore. Reinforcement leaming:A survey, Joural of Artificial Intelligence Research,1996,14
[87]尹晓虎.多Agent协同的强化学习方法研究,国防科技大学研究生院硕士学位论文,2003
[88]XiaofengWang, Tuomas Sandholm. Reinforcement Learning TO Play An Optimal Nash Equilibrium In Team Markov Games, In Advances in Neural Information Proeessing Systems15(NIPS-2002),Vaneouver,2002
[89]蔡庆生,张波.一种基于Agent团队的强化学习模型与应用研究,计算机研究与发展,2000,37(9)
[90]董红斌,孙羽.多Agent系统的现状与进展,计算机应用研究,2001,Vol 18(1)：54-65
[91]王长缨,姚莉,陈文伟.一种多Agent协作的强化学习方法,中国人工智能进展,(2003),北京邮电大学出版社,北京,2003
[92]姚莉,张维明,王长缨.基于多智能体的复杂信息系统开发方法研究,管理科学学报,2002,5(5)
[93]Miehael Bowling, Manuela Veloso. An Analysis of Stoehastic Game Theory for Multi-Agent Reinforcement Learning, CMU-CS-00-165, Oetober,2000
[94]肖人彬,王雪,费奇等。相关针具合成方法的研究。模式识别和人工智能,1993,9：227-234
[95]N.J.Nilsson著，郑扣根等译,人工智能,北京：机械工业出版社,2000
[96]何建华,高晓光等.网络中心战概念及其空战应用研究,火力与指挥控制,2003,28(4)
[97]刘海龙.基于合同网的多Agent任务分配分布式优化算法,浙江大学学报(工学版),2001,35(5)：550-554
[98]郭锐锋.基于合同网的任务分配方法的研究,小型微型计算机系统,1999,20(10)740-743
[99]熊伟,何友.信息融合系统中的态势预测技术,火力与指挥控制,2001,26(4)：47-50
[100]蓝金辉,马宝华等.D-S证据理论数据融合方法在目标识别中的应用,清华大学报,2001,41(2)：53-55
[101]S.Le Hegarat-Masele, I.Bloeh and D.Vidal-Madjar. Application of Dempster-Shafer Remote Sensing, Evidence Theory to Unsupervised Classification in Multi-source IEEE Trans on Geoseience and Remote Sensing, July 1997,35(4):1018-1031
[102]周彦,戴剑伟.HLA仿真程序设计,北京：电子工业出版社,2002
[103]曹晓东,郭嘉诚.论指挥控制规则建模,军事运筹与系统工程,2006,20(3)：22-26
[104]陈樟洪.IBM Rational Software Architect建模,北京：电子工业出版社,2008
[105]方美其,张树人.复杂系统建模与仿真,北京：中国人民出版社,2005
[106]胡晓峰,司亚光.战争模拟原理与系统,北京：国防大学出版社,2009
[107]张守一.SWARM及其在经济研究中的应用[J],数量经济技术经济研究,2001,(1)：94-97
[108]刘贞,程勇军.Swarm for Java仿真及编程实现,北京：机械工业出版社,2009