Advertisement

Modular Design of Irreducible Systems

  • Martin Hülse
  • Frank Pasemann
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4095)

Abstract

Strategies of incremental evolution of artificial neural systems have been suggested over the last decade to overcome the scalability problem of evolutionary robotics. In this article two methods are introduced that support the evolution of neural couplings and extensions of recurrent neural networks of general type. These two methods are applied to combine and extend already evolved behavioral functionality of an autonomous robot in order to compare the structure-function relations of the resulting networks with those of the initial structures. The results of these investigations indicate that the emergent dynamics of the resulting networks turn these control structures into irreducible systems. We will argue that this leads to several consequences. One is, that the scalability problem of evolutionary robotics remains unsolved, no matter which type of incremental evolution is applied.

Keywords

Hide Neuron Basic Module Recurrent Neural Network Behavior Control Input Neuron 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Husbands, P., Harvey, I., Cliff, D., Miller, G.: Artificial Evolution: A New Path for Artifical Intelligence? Brain and Cognition 34, 130–159 (1997)CrossRefGoogle Scholar
  2. 2.
    Nolfi, S., Floreano, D.: Evolutionary Robotics: The Biology, Intelligence, and Technology of Self-Organizing Machines. MIT Press, Cambridge (2000)Google Scholar
  3. 3.
    Ziemke, T.: On ’Parts’ and ’Wholes’ of Adaptive Behavior: Functional Modularity Dichronic Structure in Recurrent Neural Robot Controllers. In: Proc. of the 6th Int. Conf. on Simulation of Adaptive Behavior, pp. 115–124 (2000)Google Scholar
  4. 4.
    Husbands, P., Harvey, I., Cliff, D.: Circle in the Round: State Space Attractors for Evolved Sighted Robots. Robotics and Autonomous Systems 20, 83–106 (1995)CrossRefGoogle Scholar
  5. 5.
    Nolfi, S.: Using emergent modularity to develop control systems for mobile robots. Adaptive Behavior 5, 343–363 (1997)CrossRefGoogle Scholar
  6. 6.
    Callebaut, W., Rasskin-Gutman, D.: Modularity. Bradford Book (2005)Google Scholar
  7. 7.
    Simon, H.: The Science of the Artificial. Cambridge University Press, Cambridge (1969)Google Scholar
  8. 8.
    Pasemann, F.: Neuromodules: A dynamical systems approach to brain modellling. In: Herrmann, H.J., Wolf, D.E., Pöppel, E. (eds.) Supercomputing in brain research: From tomography to neural networks. World Scientific, Singapore (1995)Google Scholar
  9. 9.
    Dieckmann, U.: Coevolution as an autonomous learning strategy for neuromodules. In: Herrmann, H.J., Wolf, D.E., Pöppel, E. (eds.) Supercomputing in brain research: From tomography to neural networks. World Scientific, Singapore (1995)Google Scholar
  10. 10.
    Strogatz, S.H.: Nonlinear Dynamics and Chaos. Addison-Wesley, Reading (1994)Google Scholar
  11. 11.
    Pasemann, F.: Complex dynamics and the structure of small neural networks. Network: Computation in Neural Systems 13, 195–216 (2002)zbMATHGoogle Scholar
  12. 12.
    Hopfield, J.J., Tank, D.W.: Computing with neural circuits: A model. Science 233, 625–633 (1986)CrossRefGoogle Scholar
  13. 13.
    Bäck, T., Schwefel, H.-P.: An overview on evolutionary algorithms for parameter optimization. Evolutionary Computation 1, 1–23 (1995)CrossRefGoogle Scholar
  14. 14.
    Hülse, M., Wischmann, S., Pasemann, F.: Structure and Function of Evolved Neuro-Controllers for Autonomous Robots. Connection Science 16, 249–266 (2004)CrossRefGoogle Scholar
  15. 15.
    Mondada, F., Franzi, E., Ienne, P.: Mobile robots miniturization: a tool for investigation in control algorithms. In: Proc. of ISER 1993, Kyoto (1993)Google Scholar
  16. 16.
    Michel, O.: Khepera Simulator, Package version 2.0. Freeware mobile robot simulator written at the University of Nice Sophia-Antipolis by Olivier Michel (1995), Downloadable from the World Wide Web at: http://wwwi3s.unice.fr/~om/khep-sim.html
  17. 17.
    Pasemann, F.: Dynamics of a single model neuron. International Journal of Bifurcation and Chaos 3, 271–278 (1993)zbMATHCrossRefMathSciNetGoogle Scholar
  18. 18.
    Beer, R.D.: An dynamical systems perspective on agent-environment interaction. Artificial Intelligence 72, 173–215 (1995)CrossRefGoogle Scholar
  19. 19.
    Bianco, R., Nolfi, M.: Toward open-ended evolutionary robotics: evolving elementary robotic units able to self-assamble and self-reproduce. Connection Science 16, 227–248 (2004)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Martin Hülse
    • 1
  • Frank Pasemann
    • 1
  1. 1.Fraunhofer Institute for Autonomous Intelligent SystemsSankt AugustinGermany

Personalised recommendations