Abstract
Controlling complex dynamic systems requires skills that operators often cannot completely describe, but can demonstrate. This paper describes research into the understanding of such tacit control skills. Understanding tacit skills has practical motivation in respect of communicating skill to other operators, operator training, and also mechanising and optimising human skill. This paper is concerned with approaches whereby, using techniques of machine learning, controllers that emulate the human operators are generated from examples of control traces. This process is also called ”behavioural cloning”. The paper gives a review of ML-based approaches to behavioural cloning, representative experiments, and an assessment of the results. Some recent work is presented with particular emphasis on understanding human tacit skill, and generating explanation of how it works. This includes the extraction of the operator’s subconscious sub-goals and the use of qualitative control strategies. We argue for qualitative problem representations and decomposition of the machine learning problem involved.
Keywords
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.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Bain, M., Sammut, C.: A framework for behavioural cloning. In: Furukawa, K., Michie., D, Muggleton, S. (eds.): Machine Intelligence 15. Oxford University Press (1999).
Bratko, I.: Prolog Programming for Artificial Intelligence, 3rd edition, Chapter 20. Addison-Wesley (2001).
Bratko, I.: Qualitative reconstruction of control skill. In: Ironi, L. (ed.): Qualitative reasoning: 11th International Workshop, 41–52. Cortona, Italy (1997).
Bratko, I., Urbančič, T.: Control skill, machine learning and hand-crafting in controller design. In: Furukawa, K., Michie., D, Muggleton, S. (eds.): Machine Intelligence 15. Oxford University Press (1999).
Camacho, R.: Inducing models of human control skills. In Proc. 10th European Conf. Machine Learning. Chemnitz, Germany (1998).
Karalič, A., Bratko, I.: First Order Regression. Machine Learning, (1997), 26:147–176.
Križman, V.: Automated Discovery of the Structure of Dynamic System Models. Ph.D. Dissertation, Faculty of Computer and Information Sc., University of Ljubljana (in Slovenian) (1998).
Kuipers, B.: Qualitative Reasoning: Modeling and Simulation with Incomplete Knowledge. MIT Press (1994).
Michie, D.: Knowledge, learning and machine intelligence. In: Sterling, L. (ed.): Intelligent Systems, 2–19. New York: Plenum Press (1993).
Michie, D., Bain, M., Hayes-Michie, J.: Cognitive models from subcognitive skills. In: Grimble, M., McGhee, J., Mowforth, P. (eds.): Knowledge-Based Systems in Industrial Control. Stevenage: Peter Peregrinus (1990).
Michie, D., Camacho, R.: Building symbolic representations of intuitive real-time skills from performance data. In: Furukawa, K., Muggleton, S. (eds.): Machine Intelligence and Inductive Learning. Oxford: Oxford University Press (1994).
Šuc, D: Machine reconstruction of human control strategies. Ph.D. Dissertation, Faculty of Computer and Information Sc., University of Ljubljana, Slovenia (2001).
Sammut, C., Hurst, S., Kedzier, D., Michie, D.: Learning to fly. In: Proc. 9th International Workshop on Machine Learning, 385–393. Morgan Kaufmann (1992).
Šuc, D., Bratko, I.: Skill reconstruction as induction of LQ controllers with sub-goals. In: Mellish, C. (ed.): Proc. 15th International Joint Conference on Artificial Intelligence, vol. 2, 914–920 (1997).
Šuc, D., Bratko, I.: Skill modelling through symbolic reconstruction of operator’s trajectories. In: Brandt, D. (ed.): Automated systems based on human skill, 6th IFAC Symposium, 35–38. Kranjska gora, Slovenia (1997).
Šuc, D., and Bratko, I.: Problem decomposition for behavioural cloning. In: Mántaras, R., Plaza, E. (eds.): Proc. 11th European Conference on Machine Learning, 382–391. Springer (2000).
Šuc, D., Bratko, I.: Skill modelling through symbolic reconstruction of operator’s trajectories. IEEE Transaction on Systems, Man and Cybernetics, Part A (2000), 30(06):617–624.
Urbančič, T., Bratko, I.: Reconstructing human skill with machine learning. In Cohn, A., ed., Proceedings of the 11th European Conference on Artificial Intelligence, 498–502. John Wiley & Sons, Ltd (1994).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Bratko, I., Šuc, D. (2002). Using Machine Learning to Understand Operator’s Skill. In: Hendtlass, T., Ali, M. (eds) Developments in Applied Artificial Intelligence. IEA/AIE 2002. Lecture Notes in Computer Science(), vol 2358. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-48035-8_78
Download citation
DOI: https://doi.org/10.1007/3-540-48035-8_78
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-43781-9
Online ISBN: 978-3-540-48035-8
eBook Packages: Springer Book Archive