Behavioural Learning: Neural Control of a Visual Sensor

  • C. A. Moneta
Part of the Research Reports Esprit book series (ESPRIT, volume 1)


The visual sensing system presented in this paper has been developed in the context of a research aimed at joining Robotics and Machine Learning. In particular, the main overall goal is to enhance a robotic architecture by means of both symbolic and sub-symbolic learning capabilities. The application case is related to navigation and assembly tasks.

This work was partially funded by-the ESPRIT Basic Research project 7274 “Behavioural Learning: Combining Sensing and Action”.




Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    P. Liang, Y.L. Chang, and S. Hackwood “Adaptive Self-Calibration of Vision-Based Robot Systems”, IEEE Trans, on System, Man & Cybernetics, Vol.19, pp. 811–824, July/August 1989.CrossRefGoogle Scholar
  2. 2.
    Z. Li and L. Uhr “Pyramid vision using key features to integrate image- driven bottom-up and model-driven top-down processes”, IEEE Trans, on System, Man & Cybernetics, pp. 422–428, March/April 1989.Google Scholar
  3. 3.
    T. Tollanaere “Super SAB: fast adaptive Back Propagtion with good scaling properties”, Neural Networks, Vol. 3, pp. 561–573, 1990.CrossRefGoogle Scholar
  4. 4.
    T.P. Vogl et al. “Accelerating the convergence of the Back-Propagation method”, Biological Cybernetics, Vol. 59, pp. 257–263, 1988.CrossRefGoogle Scholar

Copyright information

© ECSC-EC-EAEC, Brussels-Luxembourg 1995

Authors and Affiliations

  • C. A. Moneta
    • 1
  1. 1.Department of Biophysical and Electronic EngineeringUniversity of GenoaGenovaItaly

Personalised recommendations