Fuzzy-Neural-Genetic Layered Multi-Agent Reactive Control of Robotic Soccer

  • Andon V. Topalov
  • Spyros G. Tzafestas
Part of the Massive Computing book series (MACO, volume 3)


Robotic soccer belongs to the class of multi-agent systems and involves many challenging sub-problems. Teams of robotic players have to cooperate in order to put the ball in the opposing goal and at the same time defend their own goal. This paper is concerned with the problem of learning two basic reactive behaviors of robotic agents playing soccer, namely: (i) learning to intercept the moving ball while avoiding collisions with other players and play field walls, and (ii) learning to shoot the ball toward the goal or pass it in a desired direction. The approach adopted has a “layered structure”, i.e. the ball interception/obstacle avoidance (BIOA) behavior is first learned, and the skills obtained are then employed to learn the shooting ball (SB) behavior at a higher layer.

The proposed control scheme involves a fuzzy-neural trajectory generator (FNTG), which supplies data to a trajectory-tracking controller (TTC) consisting of a conventional PD feedback controller (CFC) followed by a fuzzy-neural controller (FNC). This allows the implementation of the robot behaviors (tasks) at a trajectory generator level using off-line learning and the robot kinematics model only. The complete dynamics of the mobile base is taken into account by the TTC, and it’s learning is performed on a real mobile robot. Considering the advantages of genetic algorithms (GAs), a GA approach is employed to perform the learning process of the FNTG layers. The overall system (including the play field) was simulated in the MATLAB® environment and the results obtained are very encouraging showing the effectiveness of the proposed layered fuzzy-neural-genetic learning control scheme.


Mobile Robot Multiagent System Obstacle Avoidance Trajectory Generator Mobile Base 
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. Arkin, R. C., Behavior-Based Robotics. The MPf Press, Cambridge, Mass., 1998.Google Scholar
  2. Asada, M., Noda, S., Tawaratsumida, S., and Hosoda, K., “Purposive Behavior Acquisition on a Real Robot by Vision-based Reinforcement Learning,” in Proceedings of MLC COLT Workshop on Robot Learning, pp. 1–9, 1994a.Google Scholar
  3. Asada, M., Uchibe, E., Noda, S., Tawaratsumida, S., and Hosoda, K., “Coordination of Multiple Behaviors Acquired by Vision-Based Reinforcement Learning,” in Proceedings of IEEE/RSJ/GI International Conference on Intelligent Robots and Systems 1994 (IROS’94), pp. 917–924, 1994b.Google Scholar
  4. Asada, M., Kuniyoshi, Y., Drogoul, A., Asama, H., Mataric, M., Duhaut, D., Stone, P., and Kitano, H., “The RoboCup physical agent challenge: Phase-I,” Applied Artificial Intelligence, 12, pp. 127–134, 1998.CrossRefGoogle Scholar
  5. Asada, M., and Kitano H., (Eds.), RoboCup-98: Robot Soccer World Cup II, Springer, Berlin, 1999.Google Scholar
  6. Fierro, R., and Lewis, F. L., “Control of a Nonholonomic Mobile Robot: Backstepping Kinematics into Dynamics,” in Proceedings of the 34th Conf. On Decision &Control, pp. 381–385, 1995.Google Scholar
  7. Gomi, H., and Kawato, M., “Neural Network Control of a Closed-Loop System Using Feedback-Error-Learning,” Neural Networks, Vol. 6, pp. 933–946, 1993.CrossRefGoogle Scholar
  8. Izumi, K., and Watanabe, K., “Fuzzy Behavior-based Control with Local Learning,” in Tzafestas, S. G., (Ed.), Computational Intelligence in Systems and Control Design and Applications, Kluwer, Boston/Dordrecht, 1999.Google Scholar
  9. Johnson, J., de la Rosa Evista, P., and Kim, J.-H., Benchmark Tests of Robot Soccer Ball Control Skills, (, 1999.
  10. Kanayama, Y., Kimura, Y., Miyazaki, F., and Noguchi, T., “A Stable Tracking Control Method for an Autonomous Mobile Robot,” in Proceedings of IEEE Int. Conf. On Robotics and Automation, Vol. 1, pp. 384–389, 1990.CrossRefGoogle Scholar
  11. Kim, J.-H. (Ed.), Proceedings of the Micro-Robot World Cup Soccer Tournament, Taejon, Korea, 1996.Google Scholar
  12. Kitano, H., Veloso, M., Matsubara, H., Tambe, M., Coradeschi, S., Noda, I., Stone, P., Osawa, E., and Asada, M., “The RoboCup Syntethic Agent Challenge 97,” in Proceedings of the Fifteen International Joint Conference on Artificial Intelligence, San Francisco, CA, Morgan Kaufman, 1997.Google Scholar
  13. Kitano, H. (Ed.), RoboCup-97: Robot Soccer World Cup I. Springer, Berlin, 1998.Google Scholar
  14. Mackworth, A. K., On seeing robots, in A. Basu and X. Li, (Eds.), Computer Vision: Systems, Theory, and Applications, Word Scientific Press, Singapore, pp. 1–13, 1993.CrossRefGoogle Scholar
  15. Matsubara, H., Noda, I., and Hiraki, K., “Learning of Cooperative Actions in Multi-agent Systems: a Case Study of Pass Play in Soccer,” in Adaptation, Coevolution and Learning in Multiagent Systems: Papers from the 1996 AAAI Spring Symposium, Menlo Park, CA. AAAI Press, pp. 63–67, 1996.Google Scholar
  16. Michalewicz, Z., Genetic Algorithms + Data Structures — Evolution Programs, Springer, Berlin, 1992.CrossRefzbMATHGoogle Scholar
  17. Stone, P., Veloso, M., and Achim, S., “Collaboration and Learning in Robotic Soccer,” in Proceedings of the Micro-Robot World Cup Soccer Tournament, Taejon, Korea, 1996.Google Scholar
  18. Stone, P., and Veloso, M., “Towards Collaborative and Adversarial Learning: A Case Study in Robotic Soccer,” International Journal of Human Computer Studies, 48, 1998.Google Scholar
  19. Stonier, R, and Kim, J.-H., (Eds.), FIRA Robot World Cup France’98 Proceedings, FIRA, 1999.Google Scholar
  20. Topalov, A. V., Kim, J.-H., and Proychev, T. Ph., “Fuzzy-Net Control of Non-Holonomic Mobile Robot Using Evolutionary Feedback-Error-Learning,” Robotics and Autonomous Systems, 23, pp. 187–200, 1998.CrossRefGoogle Scholar
  21. Topalov, A. V., and Tsankova, D. D., “Goal-Directed, Collision-Free Mobile Robot Navigation and Control,” in Proceedings of First 1FAC Workshop on Multi-Agent Systems in Production, pp. 31–36, 1999.Google Scholar
  22. Tzafestas, S. G., (Ed.), Advances in Intelligent Autonomous Systems, Kluwer, Boston/Dordrecht, 1999.zbMATHGoogle Scholar
  23. Veloso, M., Stone, P., and Han, K., “The CMUnited-97 Robotic Soccer Team: Perception and Multi-Agent Control,” Robotics and Autonomous Systems, 29, pp. 133–143, 1999a.CrossRefGoogle Scholar
  24. Veloso, M., Bowling, M., Achim, S., Han, K., and Stone, P., “The CMUnited-98 Champion Small-Robot Team,” in Asada, M., and Kitano, H. (Eds.), RoboCup98: Robot Soccer World Cup II, Springer Verlag, 1999b.Google Scholar

Copyright information

© Springer Science+Business Media Dordrecht 2001

Authors and Affiliations

  • Andon V. Topalov
    • 1
  • Spyros G. Tzafestas
    • 2
  1. 1.Department of Control SystemsTechnical University of Sofia — branch PlovdivPlovdivBulgaria
  2. 2.Intelligent Robotics and Automation Laboratory, Computer Science Division, Department of Electrical and Computer EngineeringNational Technical University of AthensZografou, AthensGreece

Personalised recommendations