ROBUST LQ OPTIMAL CONTROL BY STATISTICAL LEARNING THEORY

摘要

Monte Carlo approach is used in this paper to solve optimal control problem of an uncertain system - robust control problem. Monte Carlo approach uses samples of unknown variables. This approach enables to solve the minimization problem and the mean value computation of the chosen criterion. Recently, firm theoretical base of this approach was developed - see. For nonlinear uncertain systems there is no general analytical method how to solve the optimal control problem and our approach gives the solution with prescribed accuracy. In this paper LQ (Linear system, Quadratic criterion) robust optimal problem is solved.