MODELLING HUMAN CONTROL BEHAVIOUR WITH CONTEXT-DEPENDENT MARKOV-SWITCHING MULTIPLE MODELS

A probabilistic model of human control behaviour is described. It assumes that human behaviour can be represented by switching among a number of relatively simple be- haviours. The model structure is closely related to the Hidden Markov Models (HMMs) com- monly used for speech recognition. An HMM with context-dependent transition functions switching between linear control laws is identified from experimental data. The applicability of the approach is demonstrated in a pitch control task for a simplified helicopter model. Copyright c 1998 IFAC

[1]  Yangsheng Xu,et al.  Hidden Markov model approach to skill learning and its application to telerobotics , 1993, IEEE Trans. Robotics Autom..

[2]  A. Pentland,et al.  Toward augmented control systems , 1995, Proceedings of the Intelligent Vehicles '95. Symposium.

[3]  Yoshua Bengio,et al.  Input-output HMMs for sequence processing , 1996, IEEE Trans. Neural Networks.

[4]  Roderick Murray-Smith,et al.  The operating regime approach to nonlinear modelling and control , 1997 .

[5]  W. T. Singleton,et al.  Man-machine systems , 1974 .

[6]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[7]  Finn Verner Jensen,et al.  Introduction to Bayesian Networks , 2008, Innovations in Bayesian Networks.

[8]  Yangsheng Xu,et al.  On discontinuous human control strategies , 1998, Proceedings. 1998 IEEE International Conference on Robotics and Automation (Cat. No.98CH36146).