跳到主要內容

臺灣博碩士論文加值系統

(35.172.223.251) 您好!臺灣時間:2022/08/16 23:58
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:廖浩凱
研究生(外文):Hao-Kai Liao
論文名稱:多代理人階層式合作策略之研究與比較分析─以RoboCupRescue為例
論文名稱(外文):Hierarchical Cooperation Strategies for Multiagent System in RoboCupRescue
指導教授:吳秀陽吳秀陽引用關係
指導教授(外文):Shiow-Yang Wu
學位類別:碩士
校院名稱:國立東華大學
系所名稱:資訊工程學系
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2002
畢業學年度:90
語文別:中文
論文頁數:147
中文關鍵詞:機器人救難多代理人合作策略多代理人系統人工智慧
外文關鍵詞:multiagent cooperation strategymultiagent systemartificial intelligenceRoboCupRescue
相關次數:
  • 被引用被引用:1
  • 點閱點閱:382
  • 評分評分:
  • 下載下載:74
  • 收藏至我的研究室書目清單書目收藏:0
多代理人系統是人工智慧研究領域的應用之一,而這個多代理人系統顧名思義就是由許多代理人所組成的,其目的就是要讓許多代理人合作去執行無法由單一代理人完成的工作。其中多代理人系統必須透過互相合作來完成這樣子的工作,因此要有一個好的合作策略來讓多代理人系統有效率的合作。這篇論文當中所做的研究,就是去發展一個多代理人的階層式合作策略,並且使用在 RoboCupRescue 的災難模擬環境之中。當我們在設計階層式合作策略時,我們將系統分為系統模型與策略模型。系統模型的目的是為了要描述環境之中的物件,以及物件之間的互動情形。而策略模型則是利用設計完成之後的系統模型來加以設計,設計出來的策略模型具有五個層次的策略,這五個層次分別是反應式策略、優先權策略、溝通策略、群組式策略、中央控制策略。最後我們另外再透過災難環境的模擬,得到各個不同階層策略的模擬結果與效能分析,使得我們可以比較與分析這些策略的優缺點。
Multiagent system is one of the research domains in artificial intelligence. As implied by the name, a multiagent system is composed of multiple agents to perform jobs that a single agent can not accomplish. In such situation, agents in a multiagent system achieve those jobs by mutual collaboration. Therefore, efficient cooperation strategies are essential for multiagent systems. In this thesis, we developed hierarchical cooperation strategies for multiagent systems in disaster simulation environments such as the RoboCupRescue. When designing hierarchical strategies, we separated the system model from strategy model. The purpose of the system model is to describe objects in disaster environments and the interactions between them. The strategy model was designed based on the system model and consisting of five levels. They are reaction, priority, communication, group and central control strategies, respectively. We characterized each strategy by clearly specifying the decision rules used by the agents in different situations. Preliminary implementation and RoboCupRescue system simulation allowed us to compare and analyze the strength and shortcomings of each strategy. Simulation results demonstrated that communication strategy is the strategy of choice in general cases while group and central control strategies are good for situations where fires and civilians waiting to be rescued are gathered around one or two places.
第一章 簡介 1
1.1研究動機與目的 1
1.2研究方法 3
1.3研究成果 4
1.4論文架構 6
第二章 相關研究 7
2.1多代理人 7
2.1.1代理人簡介 7
2.1.2多代理人介紹 8
2.1.3多代理人的技術 11
2.2多代理人合作策略 15
2.3 RoboCupRescue 18
2.3.1 RoboCup 簡介 18
2.3.2 RoboCupRescue 介紹 21
2.3.3 RoboCupRescue 研究領域 25
2.3.4 RoboCupRescue 軟體環境 31
第三章 在 RoboCupRescue 環境中之多代理人系統架構 36
3.1 RoboCupRescue 多代理人系統發展環境 36
3.2多代理人系統參考架構簡介 41
3.3系統分析與模型化 43
3.4多代理人系統模型 45
3.4.1模型元素 45
3.4.2元素間的互動 48
3.4.2.1重要的屬性 48
3.4.2.2具備的能力 50
3.4.2.3可產生的行動 54
3.4.2.4元素間的溝通 55
3.5多代理人階層式策略模型 57
3.5.1情況定義 58
3.5.2階層式策略 62
3.5.2.1反應式策略 65
3.5.2.2優先權策略 67
3.5.2.3溝通策略 69
3.5.2.4群組式策略 76
3.5.2.5中央控制策略 83
3.6多代理人階層式策略應用與轉換 95
第四章 系統實作 99
4.1實作環境 99
4.2程式結構 100
4.3實作之問題與解決方法 103
第五章 效能分析 106
5.1測試環境 106
5.2階層式策略之效能 108
5.2.1採用反應式策略 110
5.2.2採用優先權策略 112
5.2.3採用溝通策略 114
5.2.4採用群組式策略 116
5.2.5採用中央控制策略 120
5.3其他系統之效能 124
5.4火災與平民平均分散案例之比較分析 126
5.5火災與平民非平均分散案例之比較分析 134
5.6實驗總結 138
第六章 結論與未來研究 141
6.1結論 141
6.2未來研究 142
參考資料 144
[1]Chen H., Chung Y.M., Ramsey M., Yang C.C., Ma P.C. and Yen J. Intelligent Spider for Internet Searching. Proceedings of HICSS, pages 178 – 188, 1997.
[2]Lee J.K.W., Cheung D.W., Kao B. Law J. and Lee T. Intelligent Agents for Matching Information Providers and Consumers on the World-Wide-Web. Proceedings of HICSS, pages 189 – 199, 1997.
[3]Wu S. and Liao C-C. Virtual Proxy Servers for WWW and Intelligent Agents on the Internet. Proceedings of HICSS, pages 200 – 209, 1997.
[4]Lee J-S., Hsian J. and Tsang P-H. A Generic Virus Detection Agent on the Internet. Proceedings of HICSS, pages 210 – 219, 1997.
[5]Lee J.K. and Lee, W. Intelligent Agent Based Contract Process in Electronic Commerce: UNIK-AGENT Approach. Proceedings of HICSS, pages 230 – 241, 1997.
[6]Barrett R., Maglio P.P. and Kellem, D.C. Autonomous Interface Agents. Proceedings of Human Factors in Computer Systems, Georgia, USA, 1997. http://www.acm.org/sigchi/chi97/proceedings/paper/hl.htm.
[7]Lieberman H. and Maulsby D. Instructible agents: Software that just keeps getting better. IBM Systems Journal, 35(3 & 4): 539 – 556, 1996.
[8]Rucker J. and Polanco M.J. Siteseer: Personalized navigation for the Web. Communications of the ACM, 40(3): 73 – 75, 1997.
[9]Bradshaw J.M. An Introduction to Software Agents, In: Software Agents. J.M. Bradshaw (Ed.), Menlo Park, Calif., AAAI Press, pages 3 – 46, 1997.
[10]Huhns M.N. and Singh M.P. Agents and Multi-agent Systems: Themes, Approaches, and Challenges. Readings in Agents. Huhns, M.N. and Singh, M.P. (Eds.), San Francisco, Calif., Morgan Kaufmann Publishers, pages 1 – 23, 1998.
[11]ObjectSpace Voyager. http://www.objectspace.com/developers/voyager/.
[12]IBM Aglets. http://www.trl.ibm.co.jp/aglets/.
[13]General Magic Odyssey. http://www.genmagic.com/technology/odyssey.html.
[14]Durfee E.H., Lesser V.R. and Corkill D.D. Trends in Cooperative Distributed Problem Solving. IEEE Transactions on Knowledge and Data Engineering, 1(1): 63 – 83, March 1989.
[15]Jennings N.R., Sycara K. and Wooldridge M. A Roadmap of Agent Research and Development. Autonomous Agents and Multi-Agent Systems Journal, N.R. Jennings, K. Sycara and M. Georgeff (Eds.), Kluwer Academic Publishers, 1(1): 7 – 38, Boston, 1998.
[16]Decker K., Sycara K. and Williamson M. Middle-Agents for the Internet. Proceedings of the International Joint Conferences on Artificial Intelligence (IJCAI-97), January 1997.
[17]Bradshaw J.M. An Introduction to Software Agents. Software Agents, J.M. Bradshaw (Ed.), Menlo Park, Calif., AAAI Press, pages 3 – 46, 1997.
[18]Wiederhold G. Mediators in the Architecture of Future Information Systems. IEEE Computer, pages 38 – 49, March 1992.
[19]Decker K., Williamson M. and Sycara K. Matchmaking and Brokering. Proceedings of the Second International Conference on Multi-Agent Systems (ICMAS-96), December 1996.
[20]Bradshaw J.M., Dutfield S., Benoit P. and Woolley J.D. KAoS: Toward An Industrial-Strength Open Agent Architecture. Software Agents, J.M. Bradshaw (Ed.), Menlo Park, Calif., AAAI Press, pages 375 – 418, 1997.
[21]Nii H.P. Blackboard Systems. The Handbook of Artificial Intelligence, A. Barr P.R. Cohen and E.A. Feingenbaum (Eds.), Addison-Wesley, New York, 4(16): 1 – 82, 1989.
[22]Cohen P.R., Cheyer A., Wang M. and Baeg S.C. An open agent architecture. Proceedings of the AAAI Spring Symposium, 1994.
[23]Nwana H.S. Software Agents: An Overview. The Knowledge Engineering Review, 11(3): 205 – 244, October/November 1996.
[24]Finin T., Labrou Y., and Mayfield J. KQML as an Agent Communication Language. Software Agents, J.M. Bradshaw (Ed.), Menlo Park, Calif., AAAI Press, pages 291 – 316, 1997.
[25]Peng Y., Finin T., Labrou Y., Chu B., Long J., Tolone W.J. and Boughannam A. A Multi-Agent System for Enterprise Integration. Proceedings of the Third International Conference and Exhibition on the Practical Application of Intelligent Agents and Multi-Agent Technology, H.S. Nwana and D.T. Ndumu (Eds.) , pages 155 – 169, London UK, March 1998.
[26]Genesereth M. An Agent-based Framework for Interoperability. Software Agents, J.M. Bradshaw (Ed.), Menlo Park, Calif., AAAI Press, pages 317 – 345, 1997.
[27]Arnold K. and Gosling J. The Java Programming Language, Addison-Wesley Publishing Co., 1998.
[28]Ousterhout J.K. Tcl: An Embedded Command Language. Proceedings of the USENIX Conference, pages 133 – 146, 1990.
[29]Labrou Y. and Finin T. A Proposal for a new KQML Specification. TR CS-97-03, Computer Science and Electrical Engineering Department, University of Maryland Baltimore County, Baltimore, February 1997.
[30]Gruber T.R. A Translation Approach to Portable Ontology Specifications. Proceedings of the Knowledge Acquisition for Knowledge-Based Systems (KAW'93), Gaines B.R., Musen M. (Eds.), Banff, Canada, pages 199-220, 1993.
[31]Ginsberg M. The Knowledge Interchange Format: The KIF of Death. AAAI Magazine, 12(3): 57 - 63, 1991.
[32]Nick R. Jennings. Controlling Cooperative Problem Solving in Industrial Multiagent Systems Using Joint Intentions. Artificial Intelligence Journal, 75(2): 1 – 46, 1995.
[33]T. Balch and R. C. Arkin. Motor Schema-Based Formation Control for Multiagent Rrobot Teams. Proceedings of the First International Conference on Multiagent Systems, California USA, pages 10 – 16, 1995.
[34]C. Petrie, M. Cutlosky and H. Park. Design Space Navigation as a Collaborative Aid. Proceedings of the Third International Conference on Artificial Intelligence in Design, Lausanne, 1994.
[35]M. Pollack, T. Znati, E. Ephrati, D. Joslin, S. Lauzac, A. Nunes, N. Onder, Y. Ronen and S. Ur. The Dipart Project. Proceedings of ARPI Annual Meeting, Tucson AZ, 1994.
[36]L. Glicoe, R. Staats and M. Huhns. A Multiagent Environment for Department of Defense Distribution. In IJCAI95 Workshop on Intelligent Systems, 1995.
[37]Sandip Sen and Edmund H. Durfee. A Formal Study of Distributed Meeting Scheduling. Group Decision and Negotiation Support Systems, 1996.
[38]RoboCup. http://www.robocup.org.
[39]Hiroaki Kitano. RoboCup Rescue: A Grand Challenge for Multi-Agent System. Proceedings of MultiAgent Systems, pages 5 – 12, 2000.
[40]The Source for Java Technolodgy. http://java.sun.com/.
[41]Borland. http://www.borland.com.
[42]Sun Microsystems. http://www.sun.com.
[43]RedHat. http://www.redhat.com.
[44]YabAI. http://ne.cs.uec.ac.jp/~morimoto/rescue/yabai/index.html.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top