Advertisement

Biological inspirations in neural network implementations of Autonomous Agents

  • M. Roisenberg
  • J. M. Barreto
  • F. M. Azevedo
Distributed AI and Multi-Agent Systems II
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1159)

Abstract

This paper describes the development of an Artificial Neural Network (ANN) architecture that is capable to implement reactive behavior in Autonomous Agents (AAs). We make considerations about biological paradigms, as evolutionary mechanisms and animals' behaviors, trying to find solutions that, once applied to the development of artificial devices, provide more robust and useful AAs to operate in the real world. To have higher survival chances, life beings must have developed more complex behaviors, as reactive and internally motivated, in which the agent's action must depend on the past history of sensory values in order to be effective. This work shows that reactive behaviors can be described through Finite State Machines (FSMs) that requires a recurrent neural network architecture to be implemented, in order to insert dynamics and memory in the system. After the description of such network architecture and a biologically inspired learning algorithm, we make some experiments. Finally, conclusions for future work are given.

Keywords

Autonomous Agents Behavior-Based Agents Connectionist Models Robotics and Artificial Life Systems 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Anderson, T. L. and Donath, M. Animal Behavior as a Paradigm for Developing Robot Autonomy. In. Maes, P. (ed.) Designing Autonomous Agents. Theory and Practice from Biology to Engineering and Back. MIT Press. 1991. p. 145–168.Google Scholar
  2. 2.
    Angeline, P. J. Evolutionary Algorithms and Emergent Intelligence, Ph.D. Thesis — Ohio State University. USA. 1993. pp. 172.Google Scholar
  3. 3.
    Barreto, J. M. Connectionism in Problem Solving, Titular Professor contest Monograph, UFSC, Florianópolis, March 1996 (in Portuguese).Google Scholar
  4. 4.
    Beer, R. D. et al. A Biological Perspective on Autonomous Agent Design. In. Maes, P. (ed.) Designing Autonomous Agents. Theory and Practice from Biology to Engineering and Back. MIT Press. 1991. p. 169–186.Google Scholar
  5. 5.
    Brooks, R. A. Elephants Don't Play Chess. In. Maes, P. (ed.) Designing Autonomous Agents. Theory and Practice from Biology to Engineering and Back. MIT Press. 1991. p. 3–15.Google Scholar
  6. 6.
    Freeman, J. A. and Skapura, D. M. Neural Networks, Algorithms, Applications and Programming Techniques. Addison-Wesley. 1991. pp 401.Google Scholar
  7. 7.
    Kaelbling, L. P. Learning in Embedded Systems. MIT Press. 1993. pp 176.Google Scholar
  8. 8.
    Kuperstein, M. Neural Networks that Create their Own Goals with Growth Cycles. In Proc. of the World Congress on Neural Networks. Portland, Oregon. 1993. p.111–122. Vol. 3.Google Scholar
  9. 9.
    Lin, L. Programming Robots Using Reinforcement Learning and Teaching. In. Proc. of the Ninth Nat. Conf. on Artif. Intel. USA. 1991. p.781–786.Google Scholar
  10. 10.
    Maes, P. Guest Editorial. In Maes, P. (ed.) Designing Autonomous Agents. Theory and Practice from Biology to Engineering and Back. MIT Press. 1991. p.1–2.Google Scholar
  11. 11.
    Mahadevan, S. and Connell, J. Automatic Programming of Behavior-based Robots using Reinforcement Learning. In. Proc. of the Ninth Nat. Conf. on Artif. Intel. USA. 1991. p. 768–773.Google Scholar
  12. 12.
    Manning, A. An introduction to Animal Behavior. 3rd ed. Addison-Wesley, Massachusetts, 1979.Google Scholar
  13. 13.
    Piggott, P. and Sattar, S. Reinforcement Learning of Iterative Behaviour with Multiple Sensors. Journal of Applied Intel., 4, 1994. p.351–365.Google Scholar
  14. 14.
    Vaario, J. An Emergent Modeling Method for Artificial Neural Networks. Doctor Dissertation of Engineering-The Univ. of Tokyo. Japan. 1993. pp. 216.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1996

Authors and Affiliations

  • M. Roisenberg
    • 1
  • J. M. Barreto
    • 2
  • F. M. Azevedo
    • 2
  1. 1.Computer Science Institute, Dept. of Applied Computer ScienceUniversidade Federal do Rio Grande do SulPorto AlegreBrazil
  2. 2.Biomedical Engineering Research Group, Dept. of Electrical EngineeringUniversidade Federal de Santa CatarinaFlorianópolisBrazil

Personalised recommendations