Advertisement

Evolving electronic robot controllers that exploit hardware resources

  • Adrian Thompson
5. Robotics and Emulation of Animal Behavior
Part of the Lecture Notes in Computer Science book series (LNCS, volume 929)

Abstract

Artificial evolution can operate upon reconfigurable electronic circuits to produce efficient and powerful control systems for autonomous mobile robots. Evolving physical hardware instead of control systems simulated in software results in more than just a raw speed increase: it is possible to exploit the physical properties of the implementation (such as the semiconductor physics of integrated circuits) to obtain control circuits of unprecedented power. The space of these evolvable circuits is far larger than the space of solutions in which a human designer works, because to make design tractable, a more abstract view than that of detailed physics must be adopted. To allow circuits to be designed at this abstract level, constraints are applied to the design that limit how the natural dynamical behaviour of the components is reflected in the overall behaviour of the system. This paper reasons that these constraints can be removed when using artificial evolution, releasing huge potential even from small circuits. Experimental evidence is given for this argument, including the first reported evolution of a real hardware control system for a real robot.

Keywords

Evolvable Hardware Evolutionary Robotics Physics of Computation 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Valentino Braitenberg. Vehicles: Experiments in Synthetic Psychology. MIT Press, 1984.Google Scholar
  2. 2.
    Dave Cliff, Inman Harvey, and Phil Husbands. Explorations in evolutionary robotics. Adaptive Behaviour, 2(1):73–110, 1993.Google Scholar
  3. 3.
    David J. Comer. Digital Logic & State Machine Design. Holt, Rinehart and Winston, 1984.Google Scholar
  4. 4.
    Hugo de Garis. Evolvable hardware: Genetic programming of a Darwin Machine. In C.R. Reeves R.F. Albrecht and N.C. Steele, editors, Artificial Neural Nets and Genetic Algorithms — Proceedings of the International Conference in Innsbruck, Austria, pages 441–449. Springer-Verlag, 1993.Google Scholar
  5. 5.
    David E. Goldberg. Genetic Algorithms in Search, Optimisation & Machine Learning. Addison Wesley, 1989.Google Scholar
  6. 6.
    I. Harvey, P. Husbands, and D. Cliff. Genetic convergence in a species of evolved robot control architectures. CSRP 267, School of Cognitive and Computing Sciences, University of Sussex, 1993.Google Scholar
  7. 7.
    Inman Harvey, Phil Husbands, and Dave Cliff. Seeing the light: Artificial evolution, real vision. In Dave Cliff, Philip Husbands, Jean-Arcady Meyer, and Stewart W. Wilson, editors, From animals to animats 3: Proceedings of the third international conference on simulation of adaptive behaviour, pages 392–401. MIT Press, 1994.Google Scholar
  8. 8.
    Hitoshi Hemmi, Jun'ichi Mizoguchi, and Katsunori Shimohara. Development and evolution of hardware behaviours. In Rodney Brooks and Pattie Maes, editors, Artificial Life IV, pages 317–376. MIT Press, 1994.Google Scholar
  9. 9.
    Tetsuya Higuchi, Hitoshi Iba, and Bernard Manderick. Massively Parallel Artificial Intelligence, chapter “Evolvable Hardware”, pages 195–217. MIT Press, 1994. Edited by Hiroaki Kitano.Google Scholar
  10. 10.
    Tetsuya Higuchi, Tatsuya Niwa, Toshio Tanaka, Hitoshi Iba, Hugo de Garis, and Tatsumi Furuya. Evolving hardware with genetic learning: A first step towards building a Darwin Machine. In Proceedings of the 2nd Int. Conf. on the Simulation of Adaptive Behaviour (SAB92). MIT Press, 1993.Google Scholar
  11. 11.
    J. H. Holland. Adaptation in Natural and Artificial Systems. Ann Arbor: University of Michigan Press, 1975.Google Scholar
  12. 12.
    Philip Husbands, Inman Harvey, Dave Cliff, and Geoffrey Miller. The use of genetic algorithms for development of sensorimotor control systems. In P. Gaussier and J-D. Nicoud, editors, From Perception to Action Conference, pages 110–121. IEEE Computer Society Press, 1994.Google Scholar
  13. 13.
    Nick Jakobi, Phil Husbands, and Inman Harvey. Noise and the reality gap: The use of simulation in evolutionary robotics. In To appear: Proceedings of the 3rd European Conference on Artificial Life (ECAL95), Granada, June 4–6 1995. Springer-Verlag.Google Scholar
  14. 14.
    D. Mange. Wetware as a bridge between computer engineering and biology. In Proceedings of the 2nd European Conference on Artificial Life (ECAL93), pages 658–667, Brussels, May 24–26 1993.Google Scholar
  15. 15.
    Daniel Mange and André Stauffer. Artificial Life and Virtual Reality, chapter “Introduction to Embryonics: Towards new self-repairing and self-reproducing hardware based on biological-like properties”, pages 61–72. John Wiley, Chichester, England, 1994.Google Scholar
  16. 16.
    P. Marchal, C. Piguet, D. Mange, A. Stauffer, and S. Durand. Achieving von Neumann's dream: Artificial life on silicon. In Proc. of the IEEE International Conference on Neural Networks, icNN'94, volume IV, pages 2321–2326, 1994.Google Scholar
  17. 17.
    P. Marchal, C. Piguet, D. Mange, A. Stauffer, and S. Durand. Embryological development on silicon. In Rodney Brooks and Pattie Maes, editors, Artificial Life IV, pages 365–366. MIT Press, 1994.Google Scholar
  18. 18.
    Carver A. Mead. Analog VLSI and Neural Systems. Addison Wesley, 1989.Google Scholar
  19. 19.
    Alexander Miczo. Digital Logic Testing and Simulation. Wiley New York, 1987.Google Scholar
  20. 20.
    Jun'ichi Mizoguchi, Hitoshi Hemmi, and Katsunori Shimohara. Production genetic algorithms for automated hardware design through an evolutionary process. In IEEE Conference on Evolutionary Computation, 1994.Google Scholar
  21. 21.
    A. F. Murray et al. Pulsed silicon neural networks — following the biological leader. In Ramacher and Rückert, editors, VLSI Design of Neural Networks, pages 103–123. Kluwer Academic Publishers, 1991.Google Scholar
  22. 22.
    Alan F. Murray. Analogue neural VLSI: Issues, trends and pulses. Artificial Neural Networks, (2):35–43, 1992.Google Scholar
  23. 23.
    Stefano Nolfi, Orazio Miglino, and Domenico Parisi. Phenotypic plasticity in evolving neural networks. In P. Gaussier and J-D. Nicoud, editors, From Perception to Action Conference, pages 146–157. IEEE Computer Society Press, 1994.Google Scholar
  24. 24.
    David P.M. Northmore and John G. Elias. Evolving synaptic connections for a silicon neuromorph. In Proc of the 1st IEEE Conference on Evolutionary Computation, IEEE World Congress on Computational Intelligence, volume 2, pages 753–758. IEEE, New York, 1994.Google Scholar
  25. 25.
    Trevor A. York. Survey of field programmable logic devices. Microprocessors and Microsystems, 17(7):371–381, 1993.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1995

Authors and Affiliations

  • Adrian Thompson
    • 1
  1. 1.School of Cognitive and Computing SciencesUniversity of SussexBrightonEngland

Personalised recommendations