Adaptive Learning Application of the MDB Evolutionary Cognitive Architecture in Physical Agents

  • F. Bellas
  • A. Faiña
  • A. Prieto
  • R. J. Duro
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4095)


This work is concerned with the study of the application of the MDB (Multilevel Darwinist Brain) evolution based Cognitive Architecture in real robots performing adaptive learning tasks. The experiments described here display the capabilities of this architecture when dealing with tasks that involve real time learning from a teacher and real time adaptation to changes in the goals provided or the communication pattern used by the teacher. One of the consequences of the interaction of the robot with the environment through the MDB is the generation of induced behaviors that allow the robot to continue its operation when no teacher is present. The experiments were carried out using a Sony AIBO robot and a Pioneer 2 robot with the same mechanism running on both just to demonstrate the robustness of the approach.


Internal Model Physical Agent Cognitive Architecture World Model Real 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.
    Walker, J., Garrett, A., Wilson, M.: Evolving Controllers for Real Robots: A Survey of the Literature. Adaptive Behavior 11, 179–203 (2003)CrossRefGoogle Scholar
  2. 2.
    Floreano, D., Mondada, F.: Evolution on homing navigation in a real mobile robot. IEEE Transactions on Systems, Man and Cybernetics, 396–407 (1996)Google Scholar
  3. 3.
    Marocco, D., Floreano, D.: Active vision and feature selection in evolutionary behavioural systems. In: From Animals to Animats: Proceeings SAB 2002, pp. 247–255 (2002)Google Scholar
  4. 4.
    Watson, J.B.: Behavior-Based Control for Autonomous Robotics. In: Proc. of the 3rd Annual Conf. on Evolutionary Programming, pp. 185–190. World Scientific, Singapore (1994)Google Scholar
  5. 5.
    Nordin, P., Banzhaf, W., Brameier, M.: Evolution of a World Model for a Miniature Robot Using Genetic Programming. Robotics and Auton. Systems 25, 105–116 (1998)CrossRefGoogle Scholar
  6. 6.
    Walker, J.: Experiments in evolutionary robotics: investigating the importance of training and lifelong adaptation by evolution. PhD thesis, University of Wales (2003)Google Scholar
  7. 7.
    Nehmzow, U.: Physically embedded genetic algorithm learning in multi-robot scenarios: The PEGA algorithm. In: 2nd International Workshop on Epigenetic Robotics: Modelling Cognitive Development in Robotic Systems (2002)Google Scholar
  8. 8.
    Floreano, D., Nolfi, S., Mondada, F.: Co-evolution and ontogenetic change in competing robots. In: Advances in the Evolutionary Synthesis of Intelligent Agents. MIT Press, Cambridge (2001)Google Scholar
  9. 9.
    Østergaard, E.H., Hautop Lund, H.: Co-evolving Complex Robot Behavior. In: Tyrrell, A.M., Haddow, P.C., Torresen, J. (eds.) ICES 2003. LNCS, vol. 2606, pp. 308–319. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  10. 10.
    Duro, R.J., Santos, J., Bellas, F., Lamas, A.: On Line Darwinist Cognitive Mechanism for an Artificial Organism. In: Proceedings supplement book SAB 2000, pp. 215–224 (2000)Google Scholar
  11. 11.
    Changeux, J., Courrege, P., Danchin, A.: A Theory of the Epigenesis of Neural Networks by Selective Stabilization of Synapses. Proc. Nat. Acad. Sci. USA 70, 2974–2978 (1973)MATHCrossRefMathSciNetGoogle Scholar
  12. 12.
    Conrad, M.: Evolutionary Learning Circuits. Journal of Theoretical Biology 46 (1974)Google Scholar
  13. 13.
    Edelman, G.: Neural Darwinism. In: The Theory of Neuronal Group Selection, pp. 167–188. Basic Books, New York (1987)Google Scholar
  14. 14.
    Genesereth, M.R., Nilsson, N.: Logical Foundations of Artificial Intelligence. Morgan Kaufmann, San Francisco (1987)MATHGoogle Scholar
  15. 15.
    Mascaro, S., Korb, K.B., Nicholson, A.E.: Suicide as an Evolutionarily Stable Strategy. In: Kelemen, J., Sosík, P. (eds.) ECAL 2001. LNCS, vol. 2159, pp. 120–132. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  16. 16.
    Yao, X.: Automatic Acquisition of Strategies by co-evolutionary Learning. In: Proc. of the Int. Conf. on Computational Intelligence and Multimedia Applications, pp. 23–29 (1987)Google Scholar
  17. 17.
    Bellas, F., Duro, R.J.: Multilevel Darwinist Brain in Robots: Initial Implementation. In: ICINCO 2004 Proceedings Book, vol. 2, pp. 25–32 (2004)Google Scholar
  18. 18.
    Bellas, F., Duro, R.J.: Introducing Long Term Memory in an ANN based Multilevel Darwinist Brain. In: Mira, J., Álvarez, J.R. (eds.) IWANN 2003. LNCS, vol. 2686, pp. 590–598. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  19. 19.
    Bellas, F., Becerra, J.A., Duro, R.J.: Construction of a Memory Management System in an On-line Learning Mechanism. In: ESANN 2006 Proceedings book (2006)Google Scholar
  20. 20.
    Bellas, F., Duro, R.J.: Statistically neutral promoter based GA for evolution with dynamic fitness functions. In: Proceedings of IASTE 2002, pp. 335–340 (2002)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • F. Bellas
    • 1
  • A. Faiña
    • 1
  • A. Prieto
    • 1
  • R. J. Duro
    • 1
  1. 1.Integrated Group for Engineering ResearchUniversidade da CoruñaSpain

Personalised recommendations