OPTIMAL ADAPTIVE-CONTROL FOR A CLASS OF STOCHASTIC-SYSTEMS

We study Linear-quadratic adaptive tracking problems for a special cla ss of stochastic systems expressed in the state-space form. This is a long-standing problem in the control of aircraft flying through atmosp heric turbulence. Using an ELS-based algorithm and introducing dither in the control law we show that the resulting control achieves optimal cost in the limit, while simultaneously the unknown parameters conver ge to their true values.