Receding-horizon estimation for switching discrete-time linear systems

Receding-horizon state estimation is addressed for a class of discrete-time systems that may switch among different modes taken from a finite set. The dynamics and measurement equations for each mode are assumed to be linear and perfectly known, but the current mode of the system is unknown, and the state variables are not perfectly measurable and are affected by disturbances. The system mode is regarded as an unknown discrete state to be estimated together with the state vector. Observability conditions have been found to distinguish the system mode in the presence of bounded system and measurement noises. These results allow one to construct a receding-horizon estimator that relies on the combination of the identification of the discrete state with the estimation of the state variables by minimizing a receding-horizon quadratic cost function. The convergence properties of such an estimator are studied, and simulation results are reported to show the effectiveness of the proposed approach.