Intelligent sensory decision-making for error identification in autonomous robotic systems

  • H. C. Shen
  • W. P. Yan
  • G. E. Taylor


Successful automatic assembly of complex artefacts requires the robotic system to have the capability of detecting, identifying and recovering from various errors. Efficient error identification process is essential to ensure fast recovery and minimum loss of production time. It is not cost-effective to interrogate every sensor for every pass through the assembly process. This paper presents a machine-learning approach to identify error. The basic idea is to construct a decision tree based on some sensor and error attributes in the knowledge base.


Autonomous robotic systems Automatic error recovery Automatic assembly process Error identification tree 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    H. C. Shen, “Automatic error recovery in sensor based robotic assembly”, presentation at the Automatic Assembly Workshop, British Aerospace Military Aircraft Ltd, Preston, UK, 25–26 June, 1991.Google Scholar
  2. 2.
    K. K. W. Selke, H. C. Shen, G. E. Deacon and A. Pugh, “A strategy for sensors and rules in flexible robotic assembly”,International Journal of Production Research,29(2), pp. 277–291, 1991.Google Scholar
  3. 3.
    H. C. Shen, K. K. W. Selke, G. E. Deacon and A. Pugh, “A sensory data-driven rule-based strategy for error recovery in robotic assembly”, in G. E. Taylor (ed.)Kinematic and Dynamic Issues in Sensor Based Control, NATO ASI Series,F57, Springer-Verlag, Berlin Heidelberg New York London pp. 97–110, 1990.Google Scholar
  4. 4.
    H. C. Shen and W. P. Yan, “A finite automaton model for an autonomous workcell”, Proceedings, Pacific Conference on Manufacturing, Sydney and Melbourne, Australia, pp. 109–116, December 1990.Google Scholar
  5. 5.
    H. C. Shen and W. P. Yan, “Modelling autonomous assembly systems and FMS using cellular automata”.International Journal of Advanced Manufacturing Technology 7(6), pp. 333–338, 1992.Google Scholar
  6. 6.
    R. A. Brooks, “Symbolic error analysis and robot planning”,International Journal of Robotics Research.1(4), pp. 29–68, 1982.Google Scholar
  7. 7.
    K. H. Chang and M. Edhala, “Error recovery: a condition-oriented replanning approach”.IEEE Transactions on Systems, Man and Cybernetics,19(1), pp. 130–134, January–February 1989.Google Scholar
  8. 8.
    G. E. Taylor and P. M. Taylor, “Dynamic error probability vectors: a framework for sensory decision making”, Proceedings, IEEE Conference on Robotics and Automation, Philadelphia, Pennsylvania, pp. 1096–1100, 1988.Google Scholar
  9. 9.
    P. M. Taylor, I. Halleron and X. K. Song, “The application of a dynamic error frame-work to robotic assembly”, Proceedings, IEEE International Conference on Robotics and Automation, Cincinnati, Ohio, pp. 170–175, May 1990.Google Scholar
  10. 10.
    D. E. Wilkins, “Recovering from execution errors in SIPE”,Computer Intelligence,1, pp. 33–45, 1985.Google Scholar
  11. 11.
    W. P. Yan and H. C. Shen, “A knowledge base system for intelligent robot error detection, identification and recovery” (in preparation).Google Scholar
  12. 12.
    D. A. Huffman, “A method for the construction of minimum redundancy codes”,Proceedings of the Institute of Radio Engineers,40, pp. 1098–1101, September 1952.Google Scholar
  13. 13.
    D. R. Kemp, G. E. Taylor and A. Pugh, “A prototype robot workstation for the motif application process within the garment manufacturing industry”, Proceedings, 2nd IASTED International Symposium on Robotics and Automation, Lugano, Switzerland, June 1983.Google Scholar
  14. 14.
    X. Song, “Control of an autonomous robotic assembly workcell”, PhD thesis, University of Hull, UK, 1990.Google Scholar

Copyright information

© Springer-Verlag London Limited 1993

Authors and Affiliations

  1. 1.Pattern Analysis and Machine Intelligence Group, Department of Systems Design EngineeringUniversity of WaterlooWaterlooCanada
  2. 2.Department of Electronic EngineeringUniversity of HullUK

Personalised recommendations