車聯網是物聯網中交通領域的具體實現，除了先進駕駛輔助系統，各大汽車廠商及非汽車廠商，也積極發展自動駕駛車技術，雖然自動駕駛車技術發展快速，但是現階段仍然是以裝設在車體的感測器，協助判斷車輛與周圍物體的位置和距離，使得自動駕駛車在避免產生碰撞的狀況下行進，車輛彼此之間無法通訊，當自動駕駛車與人工駕駛車同時行駛在道路上，人工駕駛車無法迅速反應自動駕駛車的動作，會提高交通事故發生率。因此本文提出一套多代理人之間的互動協作機制，包括定義代理人的生命週期、各種互動機制演算法，運用在智能交通系統中車與車之間的溝通。如果能夠實現車與車之間通訊，分享自己的駕駛訊息給其他車輛，許多交通狀況將有效改善，例如降低交通事故發生率、解決交通壅塞問題及縮短行車時間。同時本文也運用JADE提出一種系統架構設計，包括代理人組件、路邊單元設備、消息傳輸組件及安全防護組件，目的是建立多代理人互動協作系統，提供車與車之間通訊上的應用。

The Internet of Things is a network through which two objects exchange information, while the Internet of Vehicles is a concrete realization of transportation systems in the Internet of Things. In addition to advanced driver assistance systems, autonomous vehicle technologies are also the primary target of development among large automobile and non-automobile manufacturers. Despite the rapid development of such technologies, autonomous cars remain reliant on automotive body sensors to help determine the position as well as the distance between a vehicle and its surrounding object. Thus, autonomous cars move forward under the premise that collision with other vehicles is prevented. However, vehicles cannot communicate with each other. When an autonomous car and driver-controlled car are simultaneously traveling on the road, the driver-controlled car cannot quickly respond to the actions of the autonomous car, thereby elevating the incidence of traffic accidents. Therefore, this study proposes a multi-agent coordination mechanism, in addition to defining agent life cycles and various coordination algorithms. Subsequently, the proposed mechanism is applied to an intelligent transportation system for vehicle communication. If vehicle communication can be realized, then driving information can be shared with others, which in turn can effectively improve traffic conditions, lower incidence of traffic accidents, mitigate traffic congestion, and shorten driving time. Furthermore, this study applies the Java Agent Development Framework to develop a system design comprising agent components, roadside equipment, information transmission modules, and safety protection components. This approach is aimed at establishing a multi-agent interaction and coordination system for vehicle communication.

第一章	緒論	1
1.1	研究背景與動機	1
1.2	研究目的	3
1.3	論文架構	3
第二章	文獻探討	4
2.1	物聯網	4
2.2	車聯網	6
2.2.1 V2V	8
2.2.2 V2I 	9
2.3	自動駕駛車	10
2.4	多代理人系統	13
2.5	JADE	14
2.5.1平台架構	14
2.5.2通訊能力	16
2.5.3任務行為	18
第三章	車與車協作機制	22
3.1 建立多代理人協作機制	22
3.1.1 行動代理人行為之生命週期	22
3.1.2 多代理人行為服務	25
3.1.2.1 Cooperation服務	26
3.1.2.2 Altruism服務	28
3.1.2.3 Selfish服務	30
3.1.2.4 Competition服務	32
3.2 多代理人協作系統架構	35
3.3 車與車行為架構	37
3.3.1 Cooperation行為	38
3.3.2 Altruism行為	38
3.3.3 Selfish行為	39
3.3.4 Competition行為	40
第四章	實作	42
4.1 多代理人互動模擬系統	42
4.2 模擬結果	48
第五章	結論與未來方向	51
參考文獻		52
附錄-英文論文	57

圖目錄
圖 1 物聯網三層架構	5
圖 2 車聯網概念圖	6
圖 3 車聯網架構圖	7
圖 4 JADE平台架構	15
圖 5 JADE代理人生命週期	16
圖 6 JADE代理人非同步消息傳遞模式	17
圖 7 JADE Behaviour類別圖	18
圖 8 SequentialBehaviour模型圖	20
圖 9 ParalleBehaviour模型圖	20
圖 10 FSMBehaviour模型圖	21
圖 11 行動代理人的生命週期	23
圖 12 Cooperation行為服務模型	27
圖 13 Altruism行為服務模型	29
圖 14 Selfish行為服務模型	31
圖 15 Competition行為服務模型	33
圖 16多代理人協作系統示意圖	35
圖 17 系統架構圖	36
圖 18 車與車透過多代理人協作系統溝通示意圖	37
圖 19 Cooperation行為服務之三層架構	38
圖 20 Altruism行為服務之三層架構	39
圖 21 Selfish行為服務之三層架構	40
圖 22 Competition 行為服務之三層架構	41
圖 23模擬系統車輛行駛畫面	42
圖 24 模擬系統車輛資訊畫面	43
圖 25 Cooperation behaviour service模擬畫面	44
圖 26 Altruism behaviour service模擬畫面	45
圖 27 Selfish behaviour service模擬畫面	46
圖 28 Competition behaviour service模擬畫面	47
圖 29 Cooperation behaviour service自動駕駛車行駛速度 48
圖 30 Altruism behaviour service自動駕駛車行駛速度	49
圖 31 Selfish behaviour service自動駕駛車行駛速度	49
圖 32 Competition behaviour service自動駕駛車行駛速度 50

表目錄
表 1自動駕駛車層級劃分表	10
表 2自動駕駛車比較表	12

1. Fortino, G., et al. Integration of agent-based and Cloud Computing for the smart objects-oriented IoT. in Computer Supported Cooperative Work in Design (CSCWD), Proceedings of the 2014 IEEE 18th International Conference on. 2014.
2.	Nastic, S., et al. Provisioning Software-Defined IoT Cloud Systems. in Future Internet of Things and Cloud (FiCloud), 2014 International Conference on. 2014.
3.	Xu, B., et al., Ubiquitous Data Accessing Method in IoT-Based Information System for Emergency Medical Services. IEEE Transactions on Industrial Informatics, 2014. 10(2): p. 1578-1586.
4.	Di, Z., W. Jun, and B. Kerong. Research of information processing for massive sensors in extended IOV applications. in Communication Technology (ICCT), 2013 15th IEEE International Conference on. 2013.
5.	Barberis, C. and G. Malnati, Design and evaluation of a collaborative system for content diffusion and retrieval in vehicular networks. IEEE Transactions on Consumer Electronics, 2011. 57(1): p. 105-112.
6.	Kaplan, S., et al., Driver Behavior Analysis for Safe Driving: A Survey. IEEE Transactions on Intelligent Transportation Systems, 2015. 16(6): p. 3017-3032.
7.	Liu, J.K., et al., Improvements on an authentication scheme for vehicular sensor networks. Expert Systems with Applications, 2014. 41(5): p. 2559-2564.
8.	Tsao, S.L. and C.M. Cheng, Design and evaluation of a two-tier peer-to-peer traffic information system. IEEE Communications Magazine, 2011. 49(5): p. 165-172.
9.	Wahab, O.A., et al., CEAP: SVM-based intelligent detection model for clustered vehicular ad hoc networks. Expert Systems with Applications, 2016. 50: p. 40-54.
10.	Wang, H., et al., VANET Modeling and Clustering Design Under Practical Traffic, Channel and Mobility Conditions. IEEE Transactions on Communications, 2015. 63(3): p. 870-881.
11.	Yang, F. and Y. Tang, Cooperative clustering-based medium access control for broadcasting in vehicular <italic>ad-hoc</italic> networks. IET Communications, 2014. 8(17): p. 3136-3144.
12.	Alexander, P., D. Haley, and A. Grant, Cooperative Intelligent Transport Systems: 5.9-GHz Field Trials. Proceedings of the IEEE, 2011. 99(7): p. 1213-1235.
13.	Al-Sultan, S., A.H. Al-Bayatti, and H. Zedan, Context-Aware Driver Behavior Detection System in Intelligent Transportation Systems. IEEE Transactions on Vehicular Technology, 2013. 62(9): p. 4264-4275.
14.	Conesa, J., F. Cavas-Mart&iacute;nez, and D.G. Fern&aacute;ndez-Pacheco, An agent-based paradigm for detecting and acting on vehicles driving in the opposite direction on highways. Expert Systems with Applications, 2013. 40(13): p. 5113-5124.
15.	Milan&eacute;s, V., et al., A fuzzy aid rear-end collision warning/avoidance system. Expert Systems with Applications, 2012. 39(10): p. 9097-9107.
16.	Wang, M., et al., Real-Time Path Planning Based on Hybrid-VANET-Enhanced Transportation System. IEEE Transactions on Vehicular Technology, 2015. 64(5): p. 1664-1678.
17.	Zelikman, D. and M. Segal, Reducing Interferences in VANETs. IEEE Transactions on Intelligent Transportation Systems, 2015. 16(3): p. 1582-1587.
18.	Fernandes, P. and U. Nunes, Multiplatooning Leaders Positioning and Cooperative Behavior Algorithms of Communicant Automated Vehicles for High Traffic Capacity. IEEE Transactions on Intelligent Transportation Systems, 2015. 16(3): p. 1172-1187.
19.	Liu, L., et al., A real-time personalized route recommendation system for self-drive tourists based on vehicle to vehicle communication. Expert Systems with Applications, 2014. 41(7): p. 3409-3417.
20.	Tian, D., et al., Swarm model for cooperative multi-vehicle mobility with inter-vehicle communications. IET Intelligent Transport Systems, 2015. 9(10): p. 887-896.
21.	Ward, J., et al., The Warrigal Dataset: Multi-Vehicle Trajectories and V2V Communications. IEEE Intelligent Transportation Systems Magazine, 2014. 6(3): p. 109-117.
22.	Coronado Mondragon, A.E., et al., Estimating the performance of intelligent transport systems wireless services for multimodal logistics applications. Expert Systems with Applications, 2012. 39(4): p. 3939-3949.
23.	Ide, C., et al. Channel sensitive transmission scheme for V2I-based Floating Car Data collection via LTE. in 2012 IEEE International Conference on Communications (ICC). 2012.
24.	Neelambike, S. and J. Chandrika. An efficient environmental model considering environmental factor for V2I application services. in 2015 IEEE International Conference on Computational Intelligence and Computing Research (ICCIC). 2015.
25.	WuLing, H., et al. Applicability of short range wireless networks in V2I applications. in 16th International IEEE Conference on Intelligent Transportation Systems (ITSC 2013). 2013.
26.	Du, X. and K.K. Tan, Comprehensive and Practical Vision System for Self-Driving Vehicle Lane-Level Localization. IEEE Transactions on Image Processing, 2016. 25(5): p. 2075-2088.
27.	You, F., et al., Trajectory planning and tracking control for autonomous lane change maneuver based on the cooperative vehicle infrastructure system. Expert Systems with Applications, 2015. 42(14): p. 5932-5946.
28.	Shim, I., et al., An Autonomous Driving System for Unknown Environments Using a Unified Map. IEEE Transactions on Intelligent Transportation Systems, 2015. 16(4): p. 1999-2013.
29.	Hafner, M.R., et al., Cooperative Collision Avoidance at Intersections: Algorithms and Experiments. IEEE Transactions on Intelligent Transportation Systems, 2013. 14(3): p. 1162-1175.
30.	Jang, J.A., K. Choi, and H. Cho, A Fixed Sensor-Based Intersection Collision Warning System in Vulnerable Line-of-Sight and/or Traffic-Violation-Prone Environment. IEEE Transactions on Intelligent Transportation Systems, 2012. 13(4): p. 1880-1890.
31.	P&eacute;rez, J., et al., Cooperative controllers for highways based on human experience. Expert Systems with Applications, 2013. 40(4): p. 1024-1033.
32.	Google Self-Driving Car.
33.	Foo, Y.S.E., H.B. Gooi, and S.X. Chen. Multi agent system for distributed management of microgrids. in 2015 IEEE Power & Energy Society General Meeting. 2015.
34.	Lo, S.K.C., A collaborative multi-agent message transmission mechanism in intelligent transportation system – A smart freeway example. Information Sciences, 2012. 184(1): p. 246-265.
35.	Narayanaswami, S. and N. Rangaraj, A MAS architecture for dynamic, realtime rescheduling and learning applied to railway transportation. Expert Systems with Applications, 2015. 42(5): p. 2638-2656.
36.	Java Agent DEvelopment Framework. Available from: http://jade.tilab.com/.
37.	Carrasco, A., et al., PeMMAS: A Tool for Studying the Performance of Multiagent Systems Developed in JADE. IEEE Transactions on Human-Machine Systems, 2014. 44(2): p. 180-189.
38.	Foundation for Intelligent Physical Agents. Available from: http://www.fipa.org/.