Model-Based Explanations in Simulation-Based Training

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1452)


A simulation based training application is described that uses a dedicated machine expert for generating explanations. The expert considers the problems the user is having with specific tasks, and by examining a normative model of problem solving, it determines an appropriate response, which involves generating many kinds of knowledge from a space of domain models. By using multiple domain models, the training system extends current approaches to simulation based training and machine generated explanations to produce a flexible learning environment for experienced plant operators and new trainees.


Domain Expert Multiple Model Training System Request Type Expert Action 
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.

7 References

  1. 1.
    Rassmussen, J. Skills, Rules, and Knowledge; Signals, Signs, and Symbols, and other Distinctions in Human Performance Models, IEEE Transactions on Systems, Man and Cybernetics, Vol SMC-13 No.3 (1983) 257–266.Google Scholar
  2. 2.
    Leitch et al, Modelling Choices in Intelligent Systems, AISB Quarterly No 93 (1995) 54–60.Google Scholar
  3. 3.
    Khan, T.M., Brown, K.E., Leitch, R.R. Leitch, Didactic and Informational Explanation in Simulations with Multiple Models, Proceedings of AI-ED 1997, pp:355–362.Google Scholar
  4. 4.
    J Sime and R Leitch, A learning environment based on multiple qualitative models, proceedings of ITS’92. Montreal, Canada. Itsie from ITS’92Google Scholar
  5. 5.
    J.E.M. Mitchell, J. Liddle, K. Brown and R. Leitch, Integrating Simulations into Intelligent Training Systems, EuroAI-ed’ 96, Lisbon, September 1996. pp. 80–87.Google Scholar
  6. 6.
    J. Liddle, R. Leitch, K. Brown. Generic Approaches to Developing Practical Intelligent Industrial Training Systems, Proceedings of Third International Conference, ITS’ 96, Montreal, Canada, pp 512–520 (1996).Google Scholar
  7. 7.
    J.E.M. Mitchell, K. Brown, R. Leitch and P.J.P. Slater. MOBIT: Pragmatic Diagnosis for Industrial Training. pp99–112. The Intelligent Systems Integration Program: Proceedings of Expert System 96, Cambridge, UK (1996).Google Scholar
  8. 8.
    T.M. Khan, K.E. Brown, R.R. Leitch, EXTRAS: a multiple models based learning environment, submitted to Workshop 1, AI-ED (1997).Google Scholar
  9. 9.
    T.M. Khan, M Ravindranathan, K.E. Brown, R.R. Leitch, EXTRAS: a toolkit for simulation based training, International Conference on Cognitive Systems (ICCS’ 97) (1997), India.Google Scholar
  10. 10.
    E. Hollnagel, Human Reliability Analysis Context and Control, Academic Press, (1993).Google Scholar
  11. 11.
    R. Pilkington and C. Mallen, Dialogue Games to Support Reasoning and Reflection in Diagnostic Tasks, EuroAI-ed’ 96, Lisbon, September (1996), pp. 213–219.Google Scholar
  12. 12.
    A. Cawsey, Planning Interactive Explanations, International Journal of Man-Machine Studies 38 (1993) 169–199.CrossRefGoogle Scholar
  13. 13.
    B. Chandrasekaran, M.C. Tanner and J.R. Josephson, Explaining Control Strategies in Problem Solving, IEEE Expert Spring (1989) 9–24.Google Scholar
  14. 14.
    B.Y. White, and J.R. Frederiksen (1986) ACM SIGART, no.93, pp34–37.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1998

Authors and Affiliations

  1. 1.Department of Computing and Electrical EngineeringHeriot-Watt UniversityEdinburgh

Personalised recommendations