Learning to Fly Simple and Robust

  • Dorian Šuc
  • Ivan Bratko
  • Claude Sammut
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3201)

Abstract

We report on new experiments with machine learning in the reconstruction of human sub-cognitive skill. The particular problem considered is to generate a clone of a human pilot performing a flying task on a simulated aircraft. The work presented here uses the human behaviour to create constraints for a search process that results in a controller – pilot’s clone. Experiments in this paper indicate that this approach, called “indirect controllers”, results in pilot clones that are, in comparison with those obtained with traditional “direct controllers”, simpler, more robust and easier to understand. An important feature of indirect controllers in this paper is the use of qualitative constraints.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Sammut, C., Hurst, S., Kedzier, D., Michie, D.: Learning to fly. In: Proc. 9th International Workshop on Machine Learning, pp. 385–393. Morgan Kaufmann, San Francisco (1992)Google Scholar
  2. 2.
    Camacho, R.: Using machine learning to extract models of human control skill. In: Proceedings of AIT 1995, Brno, Czech Republic (1995)Google Scholar
  3. 3.
    Bain, M., Sammut, C.: A framework for behavioural cloning. In: Machine Intelligence, vol. 15, pp. 103–129. Oxford University Press, Oxford (1999)Google Scholar
  4. 4.
    Isaac, A., Sammut, C.: Goal-directed learning to fly. In: Machine Learning, Proc. 20th International Conference (ICML 2003), pp. 258–265. AAAI Press, Menlo Park (2003)Google Scholar
  5. 5.
    Šuc, D., Bratko, I.: Problem decomposition for behavioural cloning. In: Proc. of the 11th European Conference on Machine Learning, pp. 382–391. Springer, Heidelberg (2000)Google Scholar
  6. 6.
    Šuc, D., Bratko, I.: Symbolic and qualitative reconstruction of control skill. Electronic Transactions on Artificial Intelligence, Section B 3, 1–22 (1999)Google Scholar
  7. 7.
    Šuc, D.: Machine Reconstruction of Human Control Strategies. In: Frontiers in Artificial Intelligence and Applications, vol. 99, IOS Press, Amsterdam (2003)Google Scholar
  8. 8.
    Šuc, D., Bratko, I.: Induction of qualitative trees. In: Proc. of the 12th European Conference on Machine Learning, pp. 442–453. Springer, Heidelberg (2001)Google Scholar
  9. 9.
    Breiman, L., Friedman, J., Olshen, R., Stone, C.: Classification and Regression Trees. Wadsworth, Belmont (1984)MATHGoogle Scholar
  10. 10.
    Thom, T.: The Air Pilot’s Manual. 7 edn. Air Pilot Publishing Ltd (2003)Google Scholar
  11. 11.
    Atkeson, C., Moore, A., Schaal, S.: Locally weighted learning. Artificial Intelligence Review 11, 11–73 (1997)CrossRefGoogle Scholar
  12. 12.
    Šuc, D., Vladušič, D., Bratko, I.: Qualitatively faithful quantitative prediction. Artificial Intelligence (2004) (accepted for publication)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Dorian Šuc
    • 1
  • Ivan Bratko
    • 1
  • Claude Sammut
    • 2
  1. 1.Faculty of Computer and Information ScienceUniversity of LjubljanaLjubljanaSlovenia
  2. 2.School of Computer Science and EngineeringUniversity of New South WalesSydneyAustralia

Personalised recommendations