Abstract
This paper considers the adaptive control of a special class of linear stochastic systems where unknown parameters in the driving vector are Gaussian random variables while other unknown parameters are discrete ones. First, an optimal state-parameter estimator using the parallel computation of the Kalman filters is constructed. Since the optimal control is not obtainable, an algorithm of the suboptimal control based on the well-known OLFO method is derived. In spite of the theoretical importance of the OLFO control, the resulting algorithm requires extensive on-line computation. Therefore, a simple suboptimal control which makes full use of the structure of the estimator is proposed. The performance of the proposed control is compared with that of the OLFO control by using the Monte Carlo simulation. The results show that the proposed control is not inferior to the OLFO control.
