Robust Kalman filtering for discrete-time Markovian jump systems with parameter uncertainty (Q1877195)

The objective of the paper is to study the state estimation for linear discrete-time systems with Markovian jump parameters. A Kalman Markovian jump filter is given and it is shown that the filtering problem can be solved if two sets of coupled Riccati-like equations have symmetric positive definite solutions. Moreover, the stochastic quadratic estimator guarantees both stochastic stability and estimation error boundedness.