Advertisement

A Robotic Scenario for Programmable Fixed-Weight Neural Networks Exhibiting Multiple Behaviors

  • Guglielmo Montone
  • Francesco Donnarumma
  • Roberto Prevete
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6593)

Abstract

Artificial neural network architectures are systems which usually exhibit a unique/special behavior on the basis of a fixed structure expressed in terms of parameters computed by a training phase. In contrast with this approach, we present a robotic scenario in which an artificial neural network architecture, the Multiple Behavior Network (MBN), is proposed as a robotic controller in a simulated environment. MBN is composed of two Continuous-Time Recurrent Neural Networks (CTRNNs), and is organized in a hierarchial way: Interpreter Module (IM) and Program Module (PM). IM is a fixed-weight CTRNN designed in such a way to behave as an interpreter of the signals coming from PM, thus being able to switch among different behaviors in response to the PM output programs. We suggest how such an MBN architecture can be incrementally trained in order to show and even acquire new behaviors by letting PM learn new programs, and without modifying IM structure.

Keywords

Multiple behaviors fixed-weights CTRNN programmability robotics 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Anderson, M.L.: Neural re-use as a fundamental organizational principle of the brain - target article. Behavioral and Brain Sciences 33(04) (2010)Google Scholar
  2. 2.
    Beer, R.D.: On the dynamics of small continuous-time recurrent neural networks. Adaptive Behavior 3(4), 469–509 (1995)CrossRefGoogle Scholar
  3. 3.
    Blynel, J., Floreano, D.: Exploring the T-Maze: Evolving Learning-Like Robot Behaviors using CTRNNs. In: 2nd European Workshop on Evolutionary Robotics (2003)Google Scholar
  4. 4.
    De Falco, I., Cioppa, A.D., Donnarumma, F., Maisto, D., Prevete, R., Tarantino, E.: CTRNN parameter learning using differential evolution. In: ECAI 2008, vol. 178, pp. 783–784 (July 2008)Google Scholar
  5. 5.
    Donnarumma, F.: A Model for Programmability and Virtuality in Dynamical Neural Networks. PhD thesis, Università di Napoli Federico II (2010)Google Scholar
  6. 6.
    Donnarumma, F., Prevete, R., Trautteur, G.: Virtuality in neural dynamical systems. In: International Conference on Morphological Computation, Venice, Italy (2007)Google Scholar
  7. 7.
    Donnarumma, F., Prevete, R., Trautteur, G.: How and over what timescales does neural reuse actually occur? Behavioral and Brain Sciences 33(04), 272–273 (2010)CrossRefGoogle Scholar
  8. 8.
    Floreano, D., Mondada, F.: Automatic creation of an autonomous agent: Genetic evolution of a neural-network driven robot. In: Proceedings of the Conference on Simulation of Adaptive Behavior, pp. 421–430. MIT Press, Cambridge (1994)Google Scholar
  9. 9.
    Garzillo, C., Trautteur, G.: Computational virtuality in biological systems. Theoretical Computer Science 410(4-5), 323–331 (2009); Computational Paradigms from NatureMathSciNetCrossRefzbMATHGoogle Scholar
  10. 10.
    Hopfield, J.J., Tank, D.W.: Computing with neural circuits: A model. Science 233, 625–633 (1986)CrossRefGoogle Scholar
  11. 11.
    Paine, R.W., Tani, J.: Evolved motor primitives and sequences in a hierarchical recurrent neural network. In: Deb, K., et al. (eds.) GECCO 2004. LNCS, vol. 3102, pp. 603–614. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  12. 12.
    Pearlmutter, B.A.: Gradient calculations for dynamic recurrent neural networks: A survey. IEEE Transactions on Neural Networks 6(5), 1212–1228 (1995)CrossRefGoogle Scholar
  13. 13.
    Riesenhuber, M., Poggio, T.: Models of object recognition. Nature Neuroscience 3, 1199–1204 (2000)CrossRefGoogle Scholar
  14. 14.
    Trautteur, G., Tamburrini, G.: A note on discreteness and virtuality in analog computing. Theoretical Computer Science 371, 106–114 (2007)MathSciNetCrossRefzbMATHGoogle Scholar
  15. 15.
    Yamauchi, B.M., Beer, R.D.: Sequential behavior and learning in evolved dynamical neural networks. Adaptive Behavior 2(3), 219–246 (1994)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Guglielmo Montone
    • 1
  • Francesco Donnarumma
    • 1
  • Roberto Prevete
    • 1
  1. 1.Dipartimento di Scienze FisicheUniversità di Napoli Federico IIItaly

Personalised recommendations