Robust Kalman filtering of discrete-time Markovian jump systems based on state estimation performance

Robust Kalman filtering problems for a class of discrete-time Markovian jump systems with unknown bounded noises are investigated in this paper. The upper bound of the disturbance of the noise covariance matrix is given based on the estimation error performance, and an optimal state estimation is therefore adopted under the worst condition. Not only can this method minimize the worst performance function of the uncertainty, but the error performance can also be guaranteed to be within the given range of precision. A numerical example shows the validity of the method.