Autonomous Agents and Multi-Agent Systems

, Volume 10, Issue 1, pp 131–164

A Distributed Approach for Coordination of Traffic Signal Agents

  • Ana L. C. Bazzan


Innovative control strategies are needed to cope with the increasing urban traffic chaos. In most cases, the currently used strategies are based on a central traffic-responsive control system which can be demanding to implement and maintain. Therefore, a functional and spatial decentralization is desired. For this purpose, distributed artificial intelligence and multi-agent systems have come out with a series of techniques which allow coordination and cooperation. However, in many cases these are reached by means of communication and centrally controlled coordination processes, giving little room for decentralized management. Consequently, there is a lack of decision-support tools at managerial level (traffic control centers) capable of dealing with decentralized policies of control and actually profiting from them. In the present work a coordination concept is used, which overcomes some disadvantages of the existing methods. This concept makes use of techniques of evolutionary game theory: intersections in an arterial are modeled as individually-motivated agents or players taking part in a dynamic process in which not only their own local goals but also a global one has to be taken into account. The role of the traffic manager is facilitated since s/he has to deal only with tactical ones, leaving the operational issues to the agents. Thus the system ultimately provides support for the traffic manager to decide on traffic control policies. Some application in traffic scenarios are discussed in order to evaluate the feasibility of transferring the responsibility of traffic signal coordination to agents. The results show different performances of the decentralized coordination process in different scenarios (e.g. the flow of vehicles is nearly equal in both opposing directions, one direction has a clearly higher flow, etc.). Therefore, the task of the manager is facilitate once s/he recognizes the scenario and acts accordingly.

coordination of agents evolutionary game-theory learning in multi-agent systems traffic signal control 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    R. Allsop, and J. Charlesworth “Traffic in a signal controller network: an example of different signal timings inducing different routing,”. Traffic Eng. and Control, vol. 18, pp. 262–264, 1977.Google Scholar
  2. 2.
    A. L. C. Bazzan, “A game-theoretic approach to distributed control of traffic signals,”. in Proceedings of the First Int. Conf. on Multi–Agent Systems (ICMAS) San Francisco. extended abstract, 1995.Google Scholar
  3. 3.
    A. L. C. Bazzan, “Evolution of coordination as a metaphor for learning in multi–agent systems,” in G. Weiss (ed.), DAI Meets Machine Learning, no.1221 in LNAI. Springer–Verlag: Berlin Heidelberg, New York, pp. 117–136, 1997a.Google Scholar
  4. 4.
    A. L. C. Bazzan, “An evolutionary game–theoretic approach for coordination of traffic signal agents,” Ph.D. thesis, University of Karlsruhe, 1997b.Google Scholar
  5. 5.
    A. L. C. Bazzan, J. Wahle, and F. Klu¨ gl, “Agents in traffic modelling–from Reactive to Social Behaviour,” in Advances in Artificial Intelligence, Berlin/Heidelberg. Also appeared as Proc. of the U.K. Special Interest Group on Multi-Agent Systems (UKMAS), Bristol, UK, 1999.Google Scholar
  6. 6.
    F. Busch, and G. Kruse, “MOTION–Ein neues Verfahren fu¨ r die sta¨ dtische Lichtsignalsteurung und seine Erprobung in Rahmen des EG–Programms ATT,” in Heureka 93, pp. 79–93, 1993Google Scholar
  7. 7.
    S. Cammarata, D. McArthur, and R. Steeb, “Strategies of cooperation in distributed problem solving,” in Int. Joint Conf. on Artificial Intelligence. Karlsruhe, F. R. of Germany, 1983, pp. 767–770.Google Scholar
  8. 8.
    E. C. P., Chang, J. C. K. Lei, and C. J. Messer, “Arterial signal timing optimization using PASSER–II.” Technical Report 467, Texas Transportation Institute, 1988. BAZZAN 162Google Scholar
  9. 9.
    S. L. Cohen, and J. D. C. Little, “The MAXBAND program for arterial timing plans,” Public Roads, vol. 46, no.2, pp. 61–65, 1982.Google Scholar
  10. 10.
    J. Cuena, G. Ambrosino, and M. Boero, “A general knowledge–based architecture for traffic control: the KITS approach,” in Int. Conf. on Artificial Intelligence Applications in Transportation Engineering,. California, 1992.Google Scholar
  11. 11.
    M. Di Taranto, “UTOPIA, in Proceedings of the IFAC-IFIP-IFORS Conference on Control, Computers, Communication in Transportation. Paris, 1989.Google Scholar
  12. 12.
    S. Elhadouaj, A. Drogoul, and S. Espie’,“How to combine reactivity and anticipation: the case of conflicts resolution in a simulated road traffic,” in Proceedings of the Multiagent Based Simulation (MABS), 2000.Google Scholar
  13. 13.
    N. Findler, and J. Stapp, “Distributed approach to optimized control of street traffic signals,” Journal of Transportation Engineering, vol. 118, no.1, pp. 99–110, 1992.Google Scholar
  14. 14.
    K. Fischer, N. Kuhn, H. Mu¨ ller, J. Mu¨ ller, M. Pischel, and A. Schroth, “Verteiltes Problemlo¨ sen in Transportwesen,” Information Management, vol. 2, pp. 32–40, 1993.Google Scholar
  15. 15.
    K. Fischer, J. Mu¨ ller, M. Pischeland, and D. Schier, “A model for cooperative transportation scheduling,”in V. Lesser (ed.), Proceedings of the First International Conference on Multi–Agent Systems (ICMAS),1995, pp. 109–116.Google Scholar
  16. 16.
    B. Foraste, and G. Scemana, “Surveillance and congested traffic control in Paris by expert system,” in IEEE Int. Conf. on Road Traffic Control, London, pp. 91–94, 1986.Google Scholar
  17. 17.
    D. Fudenberg, and D. Levine, “Steady state learning and nash equilibrium,” Econometrica, vol. 61, pp. 547–573, 1993.Google Scholar
  18. 18.
    A. Garland, and R. Alterman, 2004, “Autonomous agents that learn to better coordinate,” Autonomous Agents and Multi-Agent Systems, vol. 8, no.3, 267–301, 2004.CrossRefGoogle Scholar
  19. 19.
    N. Gartner, “OPAC–A demand–responsive strategy for traffic signal control,” Transportation Research Record, vol. 906, pp. 75–81, 1983.Google Scholar
  20. 20.
    M. R., Genesereth, M. L. Ginsberg, and J. S. Rosenschein, “Cooperation without communication,” in Proceedings of the Fifth Nat. Conf. on Art. Intelligence, 1986.Google Scholar
  21. 21.
    J. Halpern, and Y. Moses, “Knowledge and common knowledge in a distributed environment,” in Third Annual ACM Symposium on Principles of Distributed Computing, Vancouver, 1984.Google Scholar
  22. 22.
    C. B. Harley, “Learning the evolutionary stable strategy,” Journal of Theoretical Biology, vol. 89, pp. 611–631, 1981.CrossRefPubMedGoogle Scholar
  23. 23.
    H. Haugeneder and D. Steiner, “MECCA/UTS: A multi-agent scenario for cooperation in urban traffic’. in Proceeedings of the Special Interest Group on Cooperating Knowledge Based Systems, 1993.Google Scholar
  24. 24.
    J. Henry, J. Farges, and J. Tuffal, “The PRODYN real time traffic algorithm,” in Proceedings of the Int. Fed. of Aut. Control (IFAC) Conf, Baden-Baden, 1983.Google Scholar
  25. 25.
    F. Klu¨ gl, and A. L. C. Bazzan, “Simulation of adaptive agents learning heuristics for route choice in a commuter scenario,” in Proceedings of the First International Joint Conference on Autonomous Agents and Multi-Agent Systems (AAMAS), vol. 1. Bologna, Italy, extended abstract, pp. 217–218, 2002.CrossRefGoogle Scholar
  26. 26.
    F. Klu¨ gl, and A. L. C. Bazzan, 2004,“Route decision behaviour in a commuting scenario,”Journal of Artificial Societies an Social Simulation, vol. 7, no.1, Scholar
  27. 27.
    F. Klu¨ gl, A. L. C. Bazzan, and J. Wahle, “Selection of information types based on personal utility-a testbed for traffic information markets,” in Proceedings of the Second International Joint Conference on Autonomous Agents and Multi-Agent Systems (AAMAS), Melbourne, Australia, 2003, pp. 377–384.Google Scholar
  28. 28.
    W. Leutzbach, Introduction to the Theory of Traffic Flow. Springer, Berlin, 1988.Google Scholar
  29. 29.
    G. List, and J. Pond, “A strategy for real-time control demand-sensitive signal networks,” in Advanced Air Transportation Technologies (AATT) Conference, 1989.Google Scholar
  30. 30.
    M. W. Macy, and A. Flache, “Learning dynamics in social dilemmas,” in Proceedings of the National Academy of Sciences, Vol. 99, pp. 7229–7236, 2002.CrossRefGoogle Scholar
  31. 31.
    J. Maynard-Smith, and G. R. Price, “The logic of animal conflict,” Nature, vol. 246, pp. 15–18, 1973.CrossRefPubMedGoogle Scholar
  32. 32.
    J. Morgan, and J. Little, “Synchronizing traffic signals for maximal bandwidth,” Operations Research, vol. 12, pp. 897–912,1964.Google Scholar
  33. 33.
    S. Ossowski, Co-ordination in artifical agent societies, social structures and its implications for autonomous problem-solving agents., no.1535 in Lecture Notes in Artificial Intelligence, Berlin Heidelberg New York: Springer, 1999.Google Scholar
  34. 34.
    P. Paruchuri, A. R. Pullalarevu, and K. Karlapalem, “Multi agent simulation of unorganized traffic,” in Proceedings of the First International Joint Conference on Autonomous Agents and Multi-Agent Systems (AAMAS), Bologna, Italy, 2002, vol. 1. pp. 176–183.CrossRefGoogle Scholar
  35. 35.
    Robertson, “TRANSYT: A traffic network study tool,” Rep. LR 253, Road Res. Lab., London, 1969.Google Scholar
  36. 36.
    J. Rosenschein, and M. Genesereth, “Deals among rational agents,” in Proceedings Nineth Int. Joint Conf. on Art. Intelligence,. 1985, pp. 91–99.Google Scholar
  37. 37.
    R. Rossetti, R. Liu, D. Van Vliet, S. Bampi, and H. Cybis, “Applying an agent–based approach to traffic modeling,” in Workshop on Agents in Traffic and Transportation (at Autonomous Agents), Barcelona, 2000a.Google Scholar
  38. 38.
    R. Rossetti, R. Liu, D. Van Vliet, and H. Cybis, “An agent–based framework for the assessment of drivers’ decision–making,” IEEE Intelligent Transportation Systems, Dearborn (MI), USA, 2000b.Google Scholar
  39. 39.
    R. J. F. Rossetti, R. H. Bordini, A. L. C. Bazzan, S. Bampi, R. Liu, and D. Van Vliet, “Using BDI agents to improve driver modelling in a commuter scenario,” Transportation Research Part C: Emerging Technologies, vol. 10, 5–6, pp. 47–72, 2002.Google Scholar
  40. 40.
    A. E. Roth, and I. Erev, “Learning in extensive form games: experimental data and simple dynamic models in the intermediate term,” Games Econ. Behav, vol. 8, pp. 164–212,1995.CrossRefGoogle Scholar
  41. 41.
    A. Schaerf, Y. Shoham, and M. Tennenholtz, “Adaptive balancing load: A study in multi-agent learning,” Journal of Artificial Intelligence Research, vol. 2, pp. 475–500,1995.Google Scholar
  42. 42.
    H. Strobel, Computer Controlled Urban Transportation. A Survey of Concepts, Methods and International Experiences, vol. 10 of IIASA Int. Series, John Wiley and Sons, 1982.Google Scholar
  43. 43.
    TRANSYT-7F, “TRANSYT-7F user’s manual,” Transportation Research Center, University of Florida, 1988.Google Scholar
  44. 44.
    F. Vanderborght, “PRODYN in Brussels,” in Traffic Technology International, Surrey, UK: International Press, 1995.Google Scholar
  45. 45.
    J. Wahle, A. L. C. Bazzan, F. Klu¨ gl, and M. Schreckenberg, “The impact of real time information in a two route scenario using agent based simulation,” Transportation Research Part C: Emerging Technologies, vol. 10, 5–6, pp. 73–91, 2002.Google Scholar
  46. 46.
    B. Wild, “SAPPORO–Toward an intelligent traffic management system,” in Int. Conf. on Artificial Intelligence Applications in Transportation Engineering, California, 1992.Google Scholar
  47. 47.
    C. Zozaya-Goristiza, and C. Hendrickson, “Expert systems for traffic signal setting assistance,” Journal of Transport. Engineering, vol. 2, pp. 113, 1987.Google Scholar

Copyright information

© Springer Science+Business Media, Inc. 2005

Authors and Affiliations

  • Ana L. C. Bazzan
    • 1
  1. 1.Instituto de InformáticaUniversidade Federal do Rio Grande do SulPorto AlegreBrazil

Personalised recommendations