Advertisement

Classification as sensory-motor coordination

A case study on autonomous agents
  • Christian Scheier
  • Rolf Pfeifer
5. Robotics and Emulation of Animal Behavior
Part of the Lecture Notes in Computer Science book series (LNCS, volume 929)

Abstract

In psychology classification is studied as a separate cognitive capacity. In the field of autonomous agents the robots are equipped with perceptual mechanisms for classifying objects in the environment, either by preprogramming or by some sorts of learning mechanisms. One of the well-known hard and fundamental problems is the one of perceptual aliasing, i.e. that the sensory stimulation caused by one and the same object varies enormously depending on distance from object, orientation, lighting conditions, etc. Efforts to solve this problem, say in classical computer vision, have only had limited success. In this paper we argue that classification cannot be viewed as a separate perceptual capacity of an agent but should be seen as a sensory-motor coordination which comes about through a self-organizing process. This implies that the whole organism is involved, not only sensors and neural circuitry. In this perspective, “action selection” becomes an integral part of classification. These ideas are illustrated with a case study of a robot that learns to distinguish between graspable and non-graspable pegs

Keywords

Classification Sensory-Motor Coordination Autonomous Agents 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    D. Ballard. Animate vision. Artificial Intelligence, 48:57–86, 1991.Google Scholar
  2. 2.
    H. Bloch and B. Bertenthal, editors. Sensory-Motor Coordination and Development in Infancy and Early Childhood. Kluwer Academic Publishers, 1990.Google Scholar
  3. 3.
    V. Braitenberg. Vehicles. Kluwer Academic Publishers, 1984.Google Scholar
  4. 4.
    R. Brooks. A robust layered control system for a mobile robot. IEEE Journal of Robotics and Automation, RA-2:14–23, September/October 1986.Google Scholar
  5. 5.
    G. Butterworth. Dynamic approaches to infant perception and action. In Z.B. Smith and E. Thelen, editors, A Dynamic Systems Approach to Development, pages 1–25. MIT Press, Massachusetts, 1993.Google Scholar
  6. 6.
    J. Dewey. The reflex arc concept in psychology. Psychological Review, (3):357–370, 1896.Google Scholar
  7. 7.
    M. Dill, R. Wolf, and M. Heisenberg. Visual pattern recognition in drosophila involves retinotopic matching. Nature, (365):751–753, 1993.Google Scholar
  8. 8.
    G. M. Edelman. Neural Darwinism. Basic Books, New York, 1987.Google Scholar
  9. 9.
    G. M. Edelman. The Remembered Present. Basic Books, New York, 1987.Google Scholar
  10. 10.
    Leslie Pack Kaelbling. Learning in Embedded Systems. PhD thesis, Department of Computer Science, Standford University, 1990.Google Scholar
  11. 11.
    D. Lambrinos. Navigating with an adaptive light compass. In to appear in: Proceedings of the Third European Conference on Artificial Life ECAL95, 1995.Google Scholar
  12. 12.
    R. Pfeifer and C. Scheier. From perception to action: the right direction? In Proceedings “From Perception to Action” Conference, pages 1–11, Los Alamitos, 1994. IEEE Computer Society Press.Google Scholar
  13. 13.
    R. Pfeifer and P. Verschure. The challenge of autonomous agents: Pitfalls and how to avoid them. In L. Steels and R. Brooks, editors, The “Artificial Life” Route to “Artificial Intelligence”. Erlbaum, Hillsdale, NJ, 1994.Google Scholar
  14. 14.
    M.A. Schmuckler. Perception-action coupling in infancy. In J.P. Geert and Z. Savelsbergh, editors, The Development of Coordination in Infancy. Elsevier, Amsterdam, 1993.Google Scholar
  15. 15.
    L. Steels. Building agents with autonomous behavior systems. In L. Steels and R. Brooks, editors, The “Artificial Life” Route to “Artificial Intelligence”. Erlbaum, Hillsdale, NJ, 1994.Google Scholar
  16. 16.
    S. Thrun. Efficient exploration ia reinforcement learning. Technical report, School of Computer Science, Carnegie Mellon University, Pittsburgh, 1992.Google Scholar
  17. 17.
    T. Tyrell. Computational Mechanisms for Action Selection. PhD thesis, University of Edingburgh, 1990.Google Scholar
  18. 18.
    S.D. Whitehead and D.H. Ballard. Active pprception and reinforcement learning. In W. Porter and R.J. Mooney, editors, Machine Learning. Proceedings of the Seventh International Conference, pages 179–190, 1990.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1995

Authors and Affiliations

  • Christian Scheier
    • 1
  • Rolf Pfeifer
    • 1
  1. 1.AILab, Computer Science DepartmementUniversity of Zurich-IrchelZurichSwitzerland

Personalised recommendations