Model-Based Learning of Rules for Error Diagnosis

  • Kai Zercher
Part of the Informatik-Fachberichte book series (INFORMATIK, volume 181)


For robot applications, automatic error diagnosis becomes an ever more important capability. Diagnosis from first principles (DFP), a technique previously applied mostly to fault diagnosis of digital circuits, promises to be a fruitful approach. Unfortunately, this technique normally fails to meet the real time requirements of robot applications. It is shown how this problem can be overcome by using explanation-based generalization (EBG). The proposed technique uses the diagnosis and its explanation from a DFP-based system and generates an error diagnosis rule. After an initial learning phase, the DFP-based system can be replaced by a rule-based diagnosis system utilizing the rules learned by EBG. This replacement can speed up the diagnosis process considerably without loosing relevant diagnosis power. The proposed combination of DFP and EBG is not limited to robot applications. It is applicable whenever DFP can be used in a given domain.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [Davis 84]
    Davis, R., “Diagnostic reasoning based on structure and behavior,” Artificial Intelligence 24, p.347–410, 1984CrossRefGoogle Scholar
  2. [Davis 87]
    Davis, E., “Constraint propagation with interval labels”, Artificial Intelligence 32, p.281–331, 1987MathSciNetzbMATHCrossRefGoogle Scholar
  3. [Genesereth 84]
    Genesereth, M.R., “The use of design descriptions in automated diagnosis,” Artificial Intelligence 24, p.411–436, 1984CrossRefGoogle Scholar
  4. [Gini 88]
    Gini, M., “Automatic error detection and recovery,” to appear in Rembold, U. (ed.), “Robot technology and applications,” 1988Google Scholar
  5. [Keller 87]
    Keller, R.M., “Defining Operationality for Explanation-Based Learning,” AAAI-87Google Scholar
  6. [Mitchell 86]
    Mitchell, T.M., Keller, R., Kedar-Cabelli, S., “Explanation-based generalization: a unifying view,” Machine Learning 1, 1986Google Scholar
  7. [Mostow 87]
    Mostow, J., Bhatnagar, N., “FAILSAFE - A Floor Planer that Uses EBG to Learn from its Failures,” IJCAI 87Google Scholar
  8. [Reiter 87]
    Reiter, R., “A theory of diagnosis from first principles,” Artificial Intelligence 32, p. 57–95, 1987MathSciNetzbMATHCrossRefGoogle Scholar
  9. [Steels 85]
    Steels, L., “Second generation expert systems,” Future Generations Computer Systems, Vol. 1, 1985Google Scholar
  10. [Van de Velde 86]
    Van de Velde, W., “Explainable knowledge production,” Proceedings of the Seventh European Conference on Artificial Intelligence, Brighton, 1986Google Scholar
  11. [Zercher 88]
    Zercher, K., “Modellbasiertes Lernen von Regeln zur Fehlerdiagnose”, Diplomarbeit, Universität Karlsruhe, April 1988Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1988

Authors and Affiliations

  • Kai Zercher
    • 1
  1. 1.Fakultät für Informatik Institut für Prozeßrechentechnik und Robotik Prof. Dr.-Ing. U. Rembold Prof. Dr.-Ing. R. DillmannUniversität KarlsruheKarlsruheGermany

Personalised recommendations