臺灣博碩士論文加值系統

本論文以多重代理人模擬和遊戲引擎Unity實現一套適應式交通號誌系統，但因Unity不是一個公認的多重代理人模擬平台，故以黑板架構模式 (Blackboard Architecture Pattern) 使其成為一套多重代理人模擬平台，同時增強解決代理人的商用現貨問題。系統主要以生活中的地圖進行模擬，透過代理人特質以及代理人模擬觀察車輛代理人與交通號誌代理人兩者間彼此的互動，系統代理人涵蓋車輛代理人、行人代理人以及交通號誌代理人。交通號誌代理人於每次評估新一輪的號誌時間時，會與鄰近的交通號誌代理人共同進行評估時間，而鄰近代理人能透過黑板架構模式給予時間進而改善交通路況。此外，本論文提供一套網路監控系統，使用者能以瀏覽器或是行動裝置進行觀察交通號誌代理人每一回合所評估的時間，同時也能知道路段的當前狀態，包括：路段的紅綠燈分布、路段行駛方的倒數時間及路段停止方的車輛數目。最後，使用者也能參與於系統內，讓使用者依據親身經驗來增加系統模擬結果的多樣性及變化性。

This thesis presents the implementation of a set of adaptive traffic lights with multiagent simulation and game engine “Unity”. Since Unity is not a agent simulation platform, we transform the system to become a agent simulation platform by utilizing the Blackboard Architecture Pattern. This approach is similar to enhancing the COTS (commercial off the shelfs) solution to suite our goal. In this work, we implement different kinds of agent including vehicle agents, pedestrian agents and traffic light agents to simulate a real-life ma. Meanwhile, the system observes the interaction between vehicle agents and traffic light agents by their properties. The traffic light agent is able to interact with neighbor agents when it has predicted a new time of traffic light periodically. In addition, the neighbor agent will contribute the time value and improve the traffic condition with the Blackboard Architecture Pattern. After that, we have proposed a network monitoring system for observing the states of traffic lights, which includes the distribution, countdown time and the amounts of cars stop at traffic lights. Finally, the user could participate in the scene of the simulation by their driving experience and increase the diversity of the simulation result.

目錄
摘要 i
Abstract ii
目錄 iii
圖目錄 v
表目錄 vii
函式目錄 viii
第一章 緒論 1
第二章 相關背景知識 2
2.1 代理人相關研究 2
2.1.1 多重代理人基本特性 2
2.2 代理人模擬應用研究 6
2.2.1 代理人模擬 6
2.2.2 代理人模擬工具 6
2.2.3 代理人模擬於交通系統 7
2.3 交通號誌於交通模擬系統相關之研究 10
2.3.1 交通號誌於交通系統內之影響 10
2.3.2 交通號誌時間於交通系統內之影響 11
2.4 商用現貨 12
第三章 研究方法 13
3.1 系統分析 13
3.1.1系統架構 13
3.1.2 代理人設計 15
3.1.3 使用者參與模擬 16
3.1.4 模擬系統改進 - 適應式交通號誌系統 17
3.2 黑板架構模式 (Blackboard Architecture Pattern) 19
3.2.1 黑板模式架構 19
3.2.2 黑板模式之應用與設計 20
3.3 代理人相關設定 22
3.3.1 車輛、行人代理人 22
3.3.2 交通號誌代理人 24
第四章 系統實作 28
4.1 模擬系統 28
4.1.1 系統架構 28
4.1.2 系統開發環境 29
4.1.3 程式介面 30
4.1.4 固定式交通號誌 32
4.1.5 適應式交通號誌 34
4.1.6 黑板架構模式系統 38
4.1.7 監控系統 40
4.2 地圖建模 43
4.3 交通實體 45
4.3.1 車輛代理人 45
4.3.3 交通號誌代理人 46
4.4 實驗與結果 49
4.4.1 實驗 (一)：固定式交通號誌系統與適應式交通號誌系統差異 49
4.4.2 實驗 (二)：適應式交通號誌系統與黑板模式系統 57
4.4.3 實驗 (三)：使用者參與 61
4.4.4 實驗 (四)：網路監控系統 62
第五章 結論與未來展望 64
5.1 結論 64
5.2 未來展望 64
參考文獻 66
附錄一 黑板架構模式 69
附錄二 車輛代理人設計 72
附錄三 交通號誌代理人設計 75
附錄四 統計區間設計 79
附錄五 交通號誌時間設計 82

[1]A. I. Ahmed and A. G. E. seed, “Intelligent Traffic Light Based on Multi-agent System,” 2013 Int. Conf. Adv. Comput. Sci. Appl. Technol., pp. 89–92, Dec. 2013.
[2]N. R. Jennings, K. Sycara, and M. Wooldridge, “A Roadmap of Agent Research and Development,” Auton. Agents Multi-Agent Syst., vol. 1, no. 1, pp. 7–38, Mar. 1998.
[3]F. Pieper and S. Mostaghim, “Influence of dynamic environments on agent strategies,” 2016 IEEE Symp. Ser. Comput. Intell. SSCI, pp. 1–8, Dec. 2016.
[4]P. Stone and M. Veloso, “Multiagent Systems: A Survey from a Machine Learning Perspective,” Auton Robots, vol. 8, no. 3, pp. 345–383, Jun. 2000.
[5]吳宗錫, “A Multiagent Approach to Vehicle-Pedestrian Interaction in the Virtual City,” 中正大學電機工程學系學位論文, Jul. 2017.
[6]K. P. Sycara, “Multiagent Systems,” AI Mag., vol. 19, no. 2, p. 79, Jun. 1998.
[7]T. Kristensen and K. Smith, “Intelligent traffic simulation by a multi-agent system,” 2015 Third World Conf. Complex Syst. WCCS, pp. 1–7, Nov. 2015.
[8]T. Finin, R. Fritzson, D. McKay, and R. McEntire, “KQML As an Agent Communication Language,” Proc. Third Int. Conf. Inf. Knowl. Manag., pp. 456–463, 1994.
[9]N. R. Jennings, P. Faratin, A. R. Lomuscio, S. Parsons, M. J. Wooldridge, and C. Sierra, “Automated Negotiation: Prospects, Methods and Challenges,” Group Decis. Negot., vol. 10, no. 2, pp. 199–215, Mar. 2001.
[10]S. Jeff, “Agent-based modeling.” [Online]. Available: http://www.agent-based-models.com/blog/.
[11]C. M. Macal and M. J. North, “Tutorial on agent-based modelling and simulation,” J. Simul., vol. 4, no. 3, pp. 151–162, Sep. 2010.
[12]A. Rob, “Survey of Agent Based Modelling and Simulation Tools.” [Online]. Available: http://193.62.125.70/Complex/ABMS/.
[13]C. Nikolai and G. Madey, “Tools of the Trade: A Survey of Various Agent Based Modeling Platforms,” J. Artif. Soc. Soc. Simul., p. 37, Mar. 2009.
[14]S. Luke, “Multiagent Simulation and the MASON Library,” Jun-2015. [Online]. Available: https://cs.gmu.edu/~eclab/projects/mason/manual.pdf.
[15]“NetLogo.” [Online]. Available: https://ccl.northwestern.edu/netlogo/docs/.
[16]N. Collier, “Repast: An extensible framework for agent simulation,” Natural Resources and Environmental Issues. [Online]. Available: https://digitalcommons.usu.edu/nrei/vol8/iss1/4.
[17]S. Abar, G. K. Theodoropoulos, P. Lemarinier, and G. M. P. O’Hare, “Agent Based Modelling and Simulation tools: A review of the state-of-art software,” Comput. Sci. Rev., vol. 24, pp. 13–33, May 2017.
[18]R. Claes, T. Holvoet, and D. Weyns, “A Decentralized Approach for Anticipatory Vehicle Routing Using Delegate Multiagent Systems,” IEEE Trans. Intell. Transp. Syst., vol. 12, no. 2, pp. 364–373, Jun. 2011.
[19]M. C. Choy, D. Srinivasan, and R. L. Cheu, “Cooperative, hybrid agent architecture for real-time traffic signal control,” IEEE Trans. Syst. Man Cybern. - Part Syst. Hum., vol. 33, no. 5, pp. 597–607, Sep. 2003.
[20]A. Wibisono, W. Jatmiko, H. A. Wisesa, B. Hardjono, and P. Mursanto, “Traffic big data prediction and visualization using Fast Incremental Model Trees-Drift Detection (FIMT-DD),” Knowl.-Based Syst., vol. 93, pp. 33–46, Feb. 2016.
[21]B. C. da Silva, A. L. C. Bazzan, G. K. Andriotti, F. Lopes, and D. de Oliveira, “ITSUMO: An Intelligent Transportation System for Urban Mobility,” Innov. Internet Community Syst., pp. 224–235, Jun. 2004.
[22]L. S. Passos, R. J. F. Rossetti, and Z. Kokkinogenis, “Towards the next-generation traffic simulation tools: a first appraisal,” 6th Iber. Conf. Inf. Syst. Technol. CISTI 2011, pp. 1–6, Jun. 2011.
[23]B. Haycs-Roth, “BB1: An architecture for blackboard systems that control, explain, and learn about their own behavior,” Stanf. Univ., no. 84–16, Dec. 1984.
[24]D. D. Corkill, “blackboard-systems,” AI Expert, pp. 40–47, 1991.
[25]M. Wiering, J. van Veenen, J. Vreeken, and A. Koopman, “Intelligent Traffic Light Control,” Inst. Inf. Comput. Sci. Utrecht Univ., p. 31, Jul. 2004.
[26]B. Zhou, J. Cao, X. Zeng, and H. Wu, “Adaptive Traffic Light Control in Wireless Sensor Network-Based Intelligent Transportation System,” 2010 IEEE 72nd Veh. Technol. Conf. - Fall, pp. 1–5, Sep. 2010.
[27]L. Figueiredo, I. Jesus, J. A. T. Machado, J. R. Ferreira, and J. L. M. de Carvalho, “Towards the development of intelligent transportation systems,” ITSC 2001 2001 IEEE Intell. Transp. Syst. Proc. Cat No01TH8585, pp. 1206–1211, Aug. 2001.
[28]M. Aslani, M. S. Mesgari, and M. Wiering, “Adaptive traffic signal control with actor-critic methods in a real-world traffic network with different traffic disruption events,” Transp. Res. Part C Emerg. Technol., vol. 85, pp. 732–752, Dec. 2017.
[29]M. S. Tarawneh, “Evaluation of pedestrian speed in Jordan with investigation of some contributing factors,” J. Safety Res., vol. 32, no. 2, pp. 229–236, Jun. 2001.
[30]M. M. Ishaque and R. B. Noland, “Behavioural Issues in Pedestrian Speed Choice and Street Crossing Behaviour: A Review,” Transp. Rev., vol. 28, no. 1, pp. 61–85, Jan. 2008.
[31]T. J. Gates, D. A. Noyce, A. R. Bill, and N. V. Ee, “Recommended Walking Speeds for Pedestrian Clearance Timing Based on Pedestrian Characteristics,” Resubmitted TRB CD-ROM, p. 24, Nov. 2006.
[32]D. Corkill, “Blackboard and Multi-Agent Systems & the Future,” Proc. Int. Lisp Conf., Jan. 2003.
[33]A. S. Rao and M. P. Georgeff, “BDI Agents: From Theory to Practice,” Proc. 1st Int. Conf. Multi-Agent Syst., pp. 312–319, 1995.
[34]A. S. Rao, “AgentSpeak(L): BDI agents speak out in a logical computable language,” Agents Break. Away, pp. 42–55, Jan. 1996.
[35]“BDI Architecture.” [Online]. Available: http://www.inf.ufrgs.br/prosoft/bdi4jade/?page_id=46.
[36]“Unity,” Unity. [Online]. Available: https://unity3d.com.
[37]“Playmaker Manual.” [Online]. Available: https://hutonggames.fogbugz.com/default.asp?W1.
[38]嘉義縣政府, “嘉義縣政府全球資訊網,” 嘉義縣政府, 01-Aug-2016. [Online]. Available: https://www.cyhg.gov.tw/Default.aspx?Create=1.
[39]“Materialize.” [Online]. Available: https://materializecss.com/