Title :
An actively adaptive control policy for linear models
Author :
Pronzato, L. ; Kulcsár, C. ; Walter, E.
Author_Institution :
CNRS, Valbonne, France
fDate :
6/1/1996 12:00:00 AM
Abstract :
Considers the quadratic optimal control of a discrete-time linear system with unknown parameters. The control action affects both the future behavior of the system and the precision of the future state and parameter estimates (dual effect). Using the information matrix, the posterior uncertainty on the parameters can be predicted, in order to design an actively adaptive control policy. The case of an autoregressive model is considered. Illustrative examples are presented, together with possible extensions and remaining open questions
Keywords :
adaptive control; autoregressive processes; control system synthesis; discrete time systems; optimal control; parameter estimation; state estimation; uncertain systems; actively adaptive control policy; autoregressive model; discrete-time linear system; future behavior; information matrix; linear models; posterior uncertainty; precision; quadratic optimal control; Adaptive control; Control systems; Dynamic programming; Feedback control; Linear systems; Optimal control; Parameter estimation; State estimation; Stochastic processes; Uncertainty;
Journal_Title :
Automatic Control, IEEE Transactions on
