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”.


Visual Sensor Assembly Task Behavioural Learn Camera Intrinsic Parameter Operating Command 
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.


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