Advertisement

Evolutionary Active Vision Toward Three Dimensional Landmark-Navigation

  • Mototaka Suzuki
  • Dario Floreano
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4095)

Abstract

Active vision may be useful to perform landmark-based navigation where landmark relationship requires active scanning of the environment. In this article we explore this hypothesis by evolving the neural system controlling vision and behavior of a mobile robot equipped with a pan/tilt camera so that it can discriminate visual patterns and arrive at the goal zone. The experimental setup employed in this article requires the robot to actively move its gaze direction and integrate information over time in order to accomplish the task. We show that the evolved robot can detect separate features in a sequential manner and discriminate the spatial relationships. An intriguing hypothesis on landmark-based navigation in insects derives from the present results.

Keywords

Mobile Robot Object Detector Hide Neuron Visual Pattern Active Vision 
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.
    Bajcsy, R.: Active Perception. Proceedings of the IEEE 76, 996–1005 (1988)CrossRefGoogle Scholar
  2. 2.
    Aloimonos, J., Weiss, I., Bandopadhay, A.: Active Vision. International Journal of Computer Vision 1(4), 333–356 (1987)CrossRefGoogle Scholar
  3. 3.
    Aloimonos, J.: Purposive and Qualitative Active Vision. In: Proceedings of International Conference on Pattern Recognition, vol. 1, pp. 346–360 (1990)Google Scholar
  4. 4.
    Ballard, D.H.: Animate Vision. Artificial Intelligence 48(1), 57–86 (1991)MathSciNetCrossRefGoogle Scholar
  5. 5.
    Horn, B.: Robot Vision. McGraw-Hill, New York (1986)Google Scholar
  6. 6.
    Nolfi, S., Floreano, D.: Evolutionary Robotics: Biology, Intelligence, and Technology of Self-Organizing Machines. MIT Press, Cambridge (2000)Google Scholar
  7. 7.
    Elman, J.L.: Finding Structure in Time. Cognitive Science 14, 179–211 (1990)CrossRefGoogle Scholar
  8. 8.
    Hinton, G.E., Sejnowski, T.J. (eds.): Unsupervised Learning: Foundations of Neural Computation. MIT Press, Cambridge (1999)Google Scholar
  9. 9.
    Floreano, D., Kato, T., Marocco, D., Sauser, E.: Coevolution of Active Vision and Feature Selection. Biological Cybernetics 90(3), 218–228 (2004)MATHCrossRefGoogle Scholar
  10. 10.
    Floreano, D., Suzuki, M., Mattiussi, C.: Active Vision and Receptive Field Development in Evolutionary Robots. Evolutionary Computation 13(4), 527–544 (2005)CrossRefGoogle Scholar
  11. 11.
    Judd, S.P.D., Collett, T.S.: Multiple Stored Views and Landmark Guidance in Ants. Nature 392, 710–714 (1998)CrossRefGoogle Scholar
  12. 12.
    Land, M.F., Furneaux, S.: The Knowledge Base of The Oculomotor System. Philosophical Transactions of the Royal Society of London, Series B 352, 1231–1239 (1997)CrossRefGoogle Scholar
  13. 13.
    Land, M.F., McLeod, P.: From Eye Movements to Actions: How Batsmen Hit The Ball. Nature Neuroscience 3(12), 1340–1345 (2000)CrossRefGoogle Scholar
  14. 14.
    Noton, D., Stark, L.: Scanpaths in Saccadic Eye Movements while Viewing and Recognizing Patterns. Vision Research 11, 929–942 (1971)CrossRefGoogle Scholar
  15. 15.
    Noton, D., Stark, L.: Scanpaths in Eye Movements during Pattern Perception. Science 171, 308–311 (1971)CrossRefGoogle Scholar
  16. 16.
    Suzuki, M., van der Blij, J., Floreano, D.: Omnidirectional Active Vision for Evolutionary Car Driving. In: Arai, T., Pfeifer, R., Balch, T., Yokoi, H. (eds.) Proceedings of the 9th International Conference on Intelligent Autonomous Systems, Tokyo, Japan, March 7 - 9, 2006, pp. 153–161. IOS Press, Amsterdam (2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Mototaka Suzuki
    • 1
  • Dario Floreano
    • 1
  1. 1.Laboratory of Intelligent SystemsEcole Polytechnique Fédérale de Lausanne (EPFL)LausanneSwitzerland

Personalised recommendations