Cooperative Control Method Using Evaluation Information on Objective Achievement

  • Hikari Fujii
  • Daiki Sakai
  • Kazuo Yoshida


This paper presents a cooperative control method for a multi-agent system. The fundamental concept of this method is the control based on the evaluation on objective achievement of multi-agent systems. Each robot communicates not directly by sensory data, but by qualitative evaluation of achievement level. Each robot calculates global evaluation on the achievement of the team’s objective by agents’ evaluations. This method enables a robot to perform flexible cooperation based on the global evaluation on achievement of objectives. As an example, the method is applied to the EIGEN team robots for the Middle Size League of RoboCup which is international soccer robot project, since it is necessary for the soccer robots to cooperate each other under dynamic environment. As a result its effectiveness was demonstrated.


Evaluation Information System Objective Cooperative Control Global Objective Autonomous Mobile Robot 
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]
    L. Parker, ALLIANCE: An Architecture for Fault Tolerant Multirobot Cooperation, IEEE Transaction on Robotics and Automation, vol.14, no.2, pp.220–240, 1998.CrossRefGoogle Scholar
  2. [2]
    K. Ozaki, H. Asama, Y. Ishida, A. Matsumoto, K. Yokota, H. Kaetsu and I. Endo, Synchronized Motion by Multiple Mobile Robots using Communication, Proceedings of the 1993 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp.1164–1170, 1993Google Scholar
  3. [3]
    E. Uchibe, T. Kato, M. Asada and K. Hosoda, Dynamic Task Assignment in a Multiagent/Multitask Environment based on Module Conflict Resolution, Proceedings of IEEE International Conference on Robotics & Automation, pp.3987–3992, 2001Google Scholar
  4. [4]
    R. Emery, K. Sikorski and T. Balch, Protocols for Collaboration, Coordination and Dynamic Role Assignment in a Robot Team, Proceedings of IEEE International Conference on Robotics & Automation, pp3008–3015, 2002Google Scholar
  5. [5]
    L. Chaimowicz, M.F.M. Campos and V. Kumar, Dynamic Role Assignment for Cooperative Robots Proceedings of IEEE International Conference on Robotics & Automation, pp3008–3015, 2002.Google Scholar
  6. [6]
    Thilo Weigel, Jens-Steffen Gutmann, Markus Dietl, Alexander Kleiner, and Bernhard Nobel, CS Freiburg: Coordination Robots for Successful Soccer Playing, IEEE Transactions on Robotics and Automation, Vol. 18, No.5, 2002Google Scholar
  7. [7]
    H. Kidohshi, K. Yoshida and M. Kamiya, Intelligent control method using cubic neural network with multi-levels of information abstraction, Proceedings of the IEEE International Conference on Neural Networks, Vol.5, pp.2326–2331, 1995.CrossRefGoogle Scholar
  8. [8]
    M. Takahashi and K. Yoshida, Intelligent Failure-Proof Control using Cubic Neural Network-Application to Swinging up and Stabilizing Double Pendulum-, Proceedings of the 6th International Conference on Motion and Vibration Control (MOVIC2003), Vol.1, No.02-201, pp.265–270, 2002.Google Scholar
  9. [9]
    Sakai, R. Hayashi, K. Yoshida, Cooperative Control Method Using Information on Purpose and Evaluation, the 20th Annual Conference of the Robotics Society of Japan (RSJ2002), CD-ROM(1B33), 2002.Google Scholar
  10. [10]
    R. Tsuzaki, K. Yoshida, Motion Control Based on Fuzzy Potential Method for Autonomous Moblie Robot with Omnidirectional Vision, Journal of the Robotics Society of Japan, Vol.21, No.6, pp.656–662, 2003Google Scholar

Copyright information

© Springer 2007

Authors and Affiliations

  • Hikari Fujii
    • 1
  • Daiki Sakai
    • 1
  • Kazuo Yoshida
    • 2
  1. 1.Graduate School of Science and TechnologyKeio UniversityJapan
  2. 2.Faculty of Science and TechnologyKeio UniversityJapan

Personalised recommendations