<XML><RECORDS><RECORD><REFERENCE_TYPE>7</REFERENCE_TYPE><REFNUM>7896</REFNUM><AUTHORS><AUTHOR>Sbarbaro,D.</AUTHOR><AUTHOR>Murray-Smith,R.</AUTHOR></AUTHORS><YEAR>2005</YEAR><TITLE>Self-tuning control of non-linear systems using Gaussian process prior models</TITLE><PLACE_PUBLISHED>Proceedings of the Hamilton Summer School on Switching and Learning in Feedback systems, Ed. R. Murray-Smith, R. Shorten, Springer-Verlag, Lecture Notes in Computing Science, Vol. 3355 </PLACE_PUBLISHED><PUBLISHER>Springer Verlag</PUBLISHER><PAGES>p140-157</PAGES><LABEL>Sbarbaro:2005:7896</LABEL><ABSTRACT>Gaussian Process prior models, as used in Bayesian non-parametric statistical models methodology are applied to implement a nonlinear adaptive control law. The expected value of a quadratic cost function is minimised, without ignoring the variance of the model predictions. This leads to implicit regularisation of the control signal (caution) in areas of high uncertainty. As a consequence, the controller has dual features, since it both tracks a reference signal and learns a model of the system from observed responses. The general method and its unique features are illustrated on simulation examples. </ABSTRACT></RECORD></RECORDS></XML>