Document Type : علمی - پژوهشی


1 M.Sc. of Geospatial Information System, K.N. Toosi University of Technology, Tehran, Iran.

2 Associate Prof. of Geospatial Information System, Geoinformation Technology Center of Excellence, Geodesy and Geomatics Engineering Faculty, K.N. Toosi University of Technology, Tehran

3 Associate Prof. of Geospatial Information System, Geodesy and Geomatics Engineering Faculty, K.N. Toosi University of Technology, Tehran

4 . M.Sc. of Artificial Intelligence, Sharif University of Technology, Tehran


Nowadays, heavy traffic is one of the major problems of living in big cities. In recent years, to overcome this problem, various solutions are proposed, many of which have been on the basis of general and comprehensive models. However, because of the essential complexity of urban environment and because of the diversity of parameters affecting urban traffic, those models cannot represent the dynamic space of urban traffic, properly. In contrast to them, agent based approach is a promising approach for modeling of urban traffic. This is mainly because of its ability in modeling the interactions of traffic components, and in the modeling of the dynamic nature of urban environment. Much research has been made in the field of application of agent technology to the modeling of urban traffic. The majority of these researches are focused on a particular area of traffic phenomenon. Some of them are on providing traffic lights with some levels of intelligence. Others try to simulate the behavior and decision making of the drivers. In other cases, agent based modeling is used for simulation of dynamic vehicle routing systems using real-time traffic information. Nonetheless, less attention is paid to the more comprehensive modeling of traffic using intelligent agents. Therefore, in this research, an agent based model is proposed for improving the navigation of vehicles, on the basis of communicating traffic information amongst traffic components. The urban environment is modeled as a vector space. The model components include the two-way streets, intersections, traffic lights, origin and destination of cars. Environment comprises of intersections, streets between intersections, and streets between intersections and the origin/destination points. Active agents are the cars, traffic lights and traffic control center. In this agent based model, the green-red changing of traffic lights is controlled and programmed based on the traffic jam condition (number of cars) of the streets connected to the light. It is assumed that all vehicles are equipped with GPS and necessary communication media. The system is implemented using JADE platform and its class libraries. The data of a simulated traffic network is entered to the model. The main result of this study is a simple model of the basic part of the urban traffic, in which mobile vehicles and traffic lights have access to online traffic information. In this model, all three types of agents, i.e. cars, traffic lights and traffic control center, can communicate with each other. By defining some criteria, the impact of such communications and access to online information can are assessed. In other words, the results of different scenarios are evaluated using criteria such as traffic jam and average of traveling time. An important aspect of the model is that, although communicating with each other, all agents including drivers and traffic lights act and decide independently, i.e. without any centralized decision-making system. In this study, no GIS software is directly used. However, the behavior of vehicles and traffic lights are modeled on the basis of metric spatial relationships (distance calculations) and topological relations (connections of the street edges with each other and with traffic lights). In other words, in this study, a simple spatial environment and simple spatial behaviors are modeled. Spatial environment of two-way street and moving in them is represented by movements in a set of simple lines in the direction of X and Y axes. This model is the first step towards a more complete modeling of urban traffic. In this model, the spatial movements of vehicles are modeled as vectors. The lengths of these vectors are calculated using the assumed vehicle speeds, the distance between points, and simple estimations of traffic jams.


  1. Abdoos, M., Mozayani, N. & Bazaan, A.L.C., 2013, Holonic Multi-Agent System for Traffic Signals Control, Engineering Applications of Artificial Intelligence, 26(5-6), PP. 1575-1587.
  2. Adler, J.L. & Blue, V.J., 2002, A Cooperative Multi-Agent Transportation Management and Route Guidance System, Transp. Res. Part C: Emerging Technol., 10(5/6), PP. 433-454.
  3. Adler, J.L., Satapathy, G., Manikonda, V., Bowles, B. & Blue, V.J., 2005, A Multi-Agent Approach to Cooperative Traffic Management and Route Guidance, Transp. Res. Part B: Methodological, 39(4), PP. 297- 318.
  4. Aronsson, K.F.M., 2006, Speed Characteristics of Urban Streets Based on Driver Behaviour Studies and Simulation, Doctoral Thesis in Infrastructure, Royal Institute of Technology.
  5. Bellifemine, F.L., Caire, G. & Greenwood, D., 2007, Developing Multi-Agent Systems with JADE, Hoboken, NJ: Wiley, PP. 1-15.
  6. ـــــــــــــــــــــــــــــــــــــــــــــــــــــــــــ
  7. rester
  8. Chen, B., Cheng, H.H. & Palen, J., 2009, Integrating Mobile Agent Technology with Multi-Agent Systems for Distributed Traffic Detection and Management systems, Transportation Research Part C: Emerging Technologies, 17(1), PP. 1-10.
  9. Chen, H. & Rakha, H.A., 2016, Multi-Step Prediction of Experienced Travel Times Using Agent-Based Modeling, Transportation Research Part C: Emerging Technologies, 71, PP. 108-121.
  10. Choy, M.C., Srinivasan, D. & Cheu, R.L., 2003, Cooperative, Hybrid Agent Architecture for Real-Time Traffic Signal Control, IEEE Trans. Syst., Man, Cybern. A, Syst., Humans, 33(5), PP. 597-607.
  11. Dia, H., 2002, An Agent-Based Approach to Modelling Driver Route Choice Behavior under the Influence of Real-Time Information, Transp. Res. Part C:Emerging Technol., 10(5/6), PP. 331-349.
  12. Dresner, K. & Stone, P., 2008, A Multiagent Approach to Autonomous Intersection Management, J. Artif. Intell. Res., 31(1), PP. 591- 656.
  13. Galland, S., Buisson, J., Gaud, A., Goncalves, M., Koukam, A., Guiot, F. & Henry, L., 2014, Agent-Based Simulation of Drivers with the Janus Platform, Procedia Computer Science, 32, PP. 738-743.
  14. Jin, J. & Ma, X., 2015, Adaptive Group-Based Signal Control by Reinforcement Learning, Transportation Research Procedia, 10, PP. 207-216.
  15. Khamis, M.A. & Gomaa, W., 2014, Adaptive Multi-Objective Reinforcement Learning with Hybrid Exploration for Traffic Signal Control Based on Cooperative Multi- Agent Framework, Engineering Applications of Artificial Intelligence, 29, PP. 134- 151.
  16. Kisiel-Dorohinicki, M., 2002, Agent-Oriented Model of Simulated evolution, In W.L. Grosky & F. Plasil (Eds.), Sofsem 2002: Theory and Practice of Informatics, LNCS, Springer-Verlag.
  17. Kosonen, I., 2003, Multi-Agent Fuzzy Signal Control Based on Real-Time Simulation, Transp. Res. Part C: Emerging Technol., 11(5), PP. 389-403.
  18. Kukla, R., Kerridge, J., Willis, A. & Hine, J., 2001, PEDFLOW: Development of an Autonomous Agent Model of Pedestrian Flow, Transp. Res. Rec., 1774, PP. 11-17.
  19. Lopez-Neri, E., Ramirez-Trevino, A. & Lopez-Mellado, E., 2010, A Modeling Framework for Urban Traffic Systems Microscopic Simulation, International Journal of Simulation: Simulation Modelling Practice and Theory (ELSEVIER), PP. 1145-1161.
  20. Lu, C. & Chen, H., 2012, Hierarchical Planning for Agent-Based Traffic Management and Control, IFAC Proceedings Volumes, 45(24), PP. 256-261.
  21. Melnikov, V.R., Krzhizhanovskaya, V.V., Lees, M.H. & Boukhanovsky, A.V., 2016, Data-Driven Travel Demand Modelling and Agent-Based Traffic Simulation in Amsterdam Urban Area, Procedia Computer Science, 80, PP. 2030-2041.
  22. Roozemond, D.A., 1999, Using Autonomous Intelligent Agents for Urban Traffic Control Systems, Proc. 6th World Congr. Intell. Transp. Syst., Toronto, Canada.
  23. Roozemond, D.A., 2001, Using Intelligent Agents for Pro-active, Real-Time Urban Intersection Control, Eur. J. Oper. Res., 131(2), PP. 293-301.
  24. Rosenfeld, A., Kaminka, G., Kraus, S. & Shehory, O., 2008, A Study of Mechanisms for Improving Robotic Group Performance, Artificial Intelligence, 172. PP. 633-655.
  25. Rossetti, R.J.F., Ferreira, P.A.F., Braga, R.A.M. & Oliveira, E.C., 2008, Towards an Artificial Traffic Control System, Proc. 11th Int. IEEE Conf. Intell. Transp. Syst., PP. 14-19.
  26. Salim, F.D., Krishnaswamy, S., Loke, S.W. & Rakotonirainy, A., 2005, Context-Aware Ubiquitous Data Mining Based Agent Model for Intersection Safety, Proc. EUC Workshops, 3823, PP. 61-70.
  27. Sandhu, S.S., Jain, N., Gaurav, A., Sriman, N.C. & Iyengar, N., 2015, Agent Based Intelligent Traffic Management System for Smart Cities, International Journal of Smart Home, 9(12), PP. 307-316.
  28. Srinivasan, D. & Choy, M.C., 2006, Cooperative Multi-Agent System for Coordinated Traffic Signal Control, Proc. Inst. Elect. Eng.—Intell. Transp. Syst., 153(1), PP. 41-50.
  29. Szymanezyk, O. & Dickinson, P., 2014, Validation of Pedestrian Groups in Agent-Based Simulation, Transportation Research Procedia, 2, PP. 706-714.
  30. Taale, H., Kampen, J.V. & Hoogendoorn, S., 2015, Integrated Signal Control and Route Guidance Based on Back-Pressure Principles, Transportation Research Procedia, 10, PP. 226-235.
  31. Wahle, J., Bazzan, A.L.C, Klügl, F. & Schreckenberg, M., 2000, Anticipatory Traffic Forecast Using Multiagent Techniques, Traffic and Granular Flow ’99, D. Helbing, H. Hermann, M. Schreckenberg & D. Wolf, Eds. Heidelberg, Germany: Springer-Verlag.
  32. Wahle, J., Bazzan, A.L.C, Klügl, F. & Schreckenberg, M., 2002, The Impact of Real-Time Information in a Two-Route Scenario Using Agent-Based Simulation, Transp. Res. Part C: Emerging Technol., 10(5/6), PP. 399-417.
  33. Weyns, D., Holvoet, T. & Helleboogh, A., 2007, Anticipatory Vehicle Routing Using Delegate Multi-Agent Systems, Proc. IEEE Intell. Transp. Syst. Conf., PP. 87-93.