Advertisement

Evolving Recurrent Dynamical Networks for Robot Control

  • D. T. Cliff
  • P. Husbands
  • I. Harvey

Abstract

This paper describes aspects of our research into the development of artificial evolution techniques for the creation of control systems for autonomous mobile robots operating in complex, noisy and generally hostile environments. At the heart of our method is an extended genetic algorithm which allows the openended formation of control architectures based on artificial neural networks. After outlining the rationale for our work, and giving the background to our techniques and experimental method, results are presented from experiments in which we contrast the behaviours of robots evolved under the same evaluation function but with different sensory capabilities. One set of robots have tactile sensing only, whereas the other have both tactile and primitive visual sensors. Although the evaluation task does not explicitly rely on vision, results show conclusively that evolution is able to exploit visual input to produce very successful controllers, far better than those for robots without vision.

Keywords

Adaptive Behaviour Visual Input Hide Unit Wheel Speed Autonomous Mobile 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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    R. D. Beer. Intelligence as Adaptive Behaviour: An Experiment in Computational Neuroethology. Academic Press, 1990.Google Scholar
  2. [2]
    R.A. Brooks. Intelligence without reason. In Proceedings IJCAI-91. Morgan Kaufmann, 1991.Google Scholar
  3. [3]
    R.A. Brooks. Intelligence without representation. Artificial Intelligence, 47:139–159, 1991.CrossRefGoogle Scholar
  4. [4]
    A. Bundy. Clear thinking on artificial intelligence. The Guardian, 5th Dec, 1991.Google Scholar
  5. [5]
    W.J. Clancey. The frame of reference problem in the design of intelligent machines. In K. vanLehn, editor, Architectures for Intelligence: The 22nd Carnegie Symposium on Cognition. Lawrence Erlbaum Associates, 1991.Google Scholar
  6. [6]
    D. Cliff, I. Harvey, and P. Husbands. Incremental evolution of neural network architectures for adaptive behaviour. In Proc. 1st European Symposium on Artificial Neural Networks, Brussels, 1993.Google Scholar
  7. [7]
    D. Cliff, P. Husbands, and I. Harvey. Evolving visually guided robots. In H. Roitblat J. Meyer and S. Wilson, editors, Animals to Animats: Proceedings of the 2nd International conference on the Simulation of Adaptive Behaviour. MIT Press/Bradford Books, 1993.Google Scholar
  8. [8]
    D. Cliff, P. Husbands, and I. Harvey. Analysis of evolved sensory-motor controllers. Technical Report CSRP-264, COGS, University of Sussex [submitted to ECAL 93], 1993.Google Scholar
  9. [9]
    D. T. Cliff. Computational neuroethology: A provisional manifesto. In J.-A. Meyer and S.W. Wilson, editors, From Animals to Animais: Proceedings of The First International Conference on Simulation of Adaptive Behavior, pages 29–39. MIT Press/Bradford Books, Cambridge, MA, 1991.Google Scholar
  10. [10]
    I. Harvey, P. Husbands, and D. Cliff. Issues in evolutionary robotics. In H. Roitblat J. Meyer and S. Wilson, editors, Animals to Animats: Proceedings of the 2nd International conference on the Simulation of Adaptive Behaviour. MIT Press/Bradford Books, 1993.Google Scholar
  11. [11]
    I. Harvey, P. Husbands, and D. Cliff. Genetic convergence in a species of evolved robot control architectures. In (submitted to) Proc. 5th Int. Conf. on GAs. Urbana-Champaign, July 1993.Google Scholar
  12. [12]
    Inman Harvey. Species adaptation genetic algorithms: The basis for a continuing SAGA. In Proceedings of the First European Conference on Artificial Life, pages 346–354. MIT Press/Bradford Books, Cambridge, MA, 1992.Google Scholar
  13. [13]
    P. Husbands, I. Harvey, and D. Cliff. An evolutionary approach to situated AI. In Proc. 9th bi-annual conference of the Society for the Study of Artificial Intelligence and the Simulation of Behaviour (AISB 93). IOS Press, 1993.Google Scholar
  14. [14]
    P. Husbands, I. Harvey, and D. Cliff. Analysing recurrent dynamical networks evolved for robot control. In Proc. 3rd IEE Int. Conf. on ANNs. IEE Press, 1993.Google Scholar
  15. [15]
    F. Varela, E. Thompson, and E. Rosch. The Embodied Mind. MIT Press, 1991.Google Scholar

Copyright information

© Springer-Verlag/Wien 1993

Authors and Affiliations

  • D. T. Cliff
    • 1
  • P. Husbands
    • 1
  • I. Harvey
    • 1
  1. 1.School of Cognitive and Computing SciencesUniversity of SussexBrightonEngland

Personalised recommendations