Increasing the Efficiency of Cooperation among Agents by Sharing Actions

  • Kazunori Iwata
  • Mayumi Miyazaki
  • Nobuhiro Ito
  • Naohiro Ishii
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3026)


Recently, multi-agent techniques are being studied with keen interest to develop flexible information systems for complicated problems. In particular, rescue systems for reducing the damage caused by serious disasters are of international interest. The RoboCupRescue Project[1], launched in Japan in 1999, is an international research project aimed at developing a rescue system for serious disasters. In this paper, we focus on the system controlling the rescue agents. One aspect of great interest regarding multi-agent techniques is the design of systems that realize efficient cooperative behavior. Traditional frameworks for cooperative behavior design include cooperative protocols, hierarchical approaches and so on. However, autonomous robot agents such as rescue agents can not communicate with each other and form groups to cooperate within these traditional frameworks, because these agents have limited mobility and can obtain only restricted information. Moreover, they need to behave in a real-time environment which is complicated and changing continuously.

In this paper, we propose a new cooperative model for multi-agent systems which improves the performance of the systems by reducing redundant actions among the agents. Moreover, the results of disaster simulations confirm that our model is efficient for such complicated environments.


Rescue Agent Agent Agent Cooperative Model International Research Project Traditional Framework 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Robocuprescue official web page,
  2. 2.
    Ossowsk, S.: Co-ordination in Artificial Agent Societies. LNCS (LNAI), vol. 1535. Springer, Heidelberg (1999)Google Scholar
  3. 3.
    Carlos, A., Iglesias, M., Jose, C.: A survey of agent-oriented methodologies. In: Rao, A.S., Singh, M.P., Müller, J.P. (eds.) ATAL 1998. LNCS (LNAI), vol. 1555, pp. 317–330. Springer, Heidelberg (1999)Google Scholar
  4. 4.
    Davis, R., Smith, R.G.: Negotiation as a metaphor for distributed problem solving. Artificiall Intelligence 20(1), 63–109 (1983)CrossRefGoogle Scholar
  5. 5.
    Tambe, M.: Towards flexible teamwork. Journal of Artificial Intelligence Research 7(4) (1997)Google Scholar
  6. 6.
    Cohen, P., Levesque, H., Smith, I.: On team formation. Contemporary Action Theory 2, 87–114 (1997)Google Scholar
  7. 7.
    Haddadi, A. (ed.): Communication and Cooperation in Agent Systems. LNCS (LNAI), vol. 1056. Springer, Heidelberg (1996)Google Scholar
  8. 8.
    Nakayama, Y.: Communication and attitude change. In: The Second International Conference on Cognitive Science and The 16th Annual Meeting of the Japanese Cognitive Science Society Joint Conference (ICCS/JCSS 1999) (1999)Google Scholar
  9. 9.
    Ito, N., Ishii, T.N.: A cooperative agent model by forming a group. In: 2002 IEEE International Conference on Industrial Technology Proccedings, vol. 2, pp. 1260–1265 (2002)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Kazunori Iwata
    • 1
  • Mayumi Miyazaki
    • 2
  • Nobuhiro Ito
    • 3
  • Naohiro Ishii
    • 4
  1. 1.Dept. of Business AdministrationAichi UniversityNishikamo-gun, AichiJapan
  2. 2.Dept. of Intelligence and Computer ScienceNagoya Institute of Technology 
  3. 3.Dept. of Computer Science and Engineering, Graduate School of EngineeringNagoya Institute of TechnologyNagoya, AichiJapan
  4. 4.Dept. of Information and Network EngineeringAichi Institute of TechnologyToyotaJapan

Personalised recommendations