Exploiting the Power of Sensory-Motor Coordination

  • Stefano Nolfi
  • Domenico Parisi
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1674)


One important implication of embodiment is that, by acting, agents partially determine the sensory patterns they receive from the environment. The motor actions performed by an agent, by modifying the agent’s position with respect to the external environment and/or the external environment itself, partially determine the type of sensory patterns received from the environment In this paper we investigate how agents can take advantage of this ability. In particular, we discuss how agents coordinate sensory and motor processes in order to (1) select sensory patterns which are not affected by the aliasing problem and avoid those which are; (2) select sensory patterns such that groups of patterns which require different responses do not strongly overlap; (3) exploit emergent behaviors that result from the interaction between the agent and the environment.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Pfeifer, R. & Scheier, C. Sensory-motor coordination: The metaphor and beyond. Robotics and Autonomous Systems. 20 (1997) 157–178.CrossRefGoogle Scholar
  2. 2.
    Nolfi, S. Parisi, D.: Learning to adapt to changing environments in evolving neural networks. Adaptive Behavior. 1: (1997) 99–105Google Scholar
  3. 3.
    Whitehead, S.D. & Ballard, D. H.: Learning to perceive and act by trial and error. Machine Learning. 7 (1991) 45–83.Google Scholar
  4. 4.
    Mondada, R., Franzi, E. & Ienne, P.: Mobile robot miniaturization: A tool for investigation in control algorithms: In: T. Yoshikawa & F. Miyazaki (eds.): Proceedings of the Third International Symposium on Experimental Robots, Kyoto, Japan (1993)Google Scholar
  5. 5.
    Bajcsy, R.: Active Perception. Proceedings of the IEEE (76) 8: (1988) 996–1005CrossRefGoogle Scholar
  6. 6.
    Dill, M., Wolf, R., Heisenberg, M.: Visual pattern recognition in drosophila involves retinotopic matching. Nature. 355: (1993) 751–753.CrossRefGoogle Scholar
  7. 7.
    Clark, A. & Thornton, C: Trading spaces: Computation, representation, and the limits of uniformed learning. Behavioral and Brain Sciences. 20 (1997) 57–90.CrossRefGoogle Scholar
  8. 8.
    Elman, J.L.: Learning and development in neural networks: The importance of starting small. Cognition. 48 (1993) 71–99.CrossRefGoogle Scholar
  9. 9.
    Scheier, C., Pfeifer, R. & Kunyioshi, Y. Embedded neural networks: exploiting constraints. Neural Networks. 11: (1998) 1551–1596.CrossRefGoogle Scholar
  10. 10.
    Nolfi, S.: Adaptation as a more powerful tool than decomposition and integration. In: T. Fogarty and G. Venturini (Eds), Proceedings of the workshop on Evolutionary computing and Machine Learning, 13th International Conference on Machine Learning, Bari (1996)Google Scholar
  11. 11.
    Nolfi, S.: Evolving non-trivial behavior on autonomous robots: Adaptation is more powerful than decomposition and integration. In T. Gomi (ed.): Evolutionary Robotics, Kanata, Canada: AAI Books (1997)Google Scholar
  12. 12.
    Thornton C: Separability is a learner’s best friend. In: J.A. Bullinaria, D.W. Glasspool, & G. Houghton (eds.): Proceedings of the Neural Computation and Psychology Workshop: Connectionist Representations, London, Springer (1997).Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1999

Authors and Affiliations

  • Stefano Nolfi
    • 1
  • Domenico Parisi
    • 1
  1. 1.Institute of PsychologyNational Research Council (CNR)RomeItaly

Personalised recommendations