Robust Extended Kalman Filter for Nonlinear Singular System

In this paper, for the stochastic singular systems with nonlinear measurement, a robust extended Kalman filtering algorithm is proposed. The original singular system is transformed into a standard system through the application of the Singular Value Decomposition (SVD) method and the state augmented approach. The nonlinear measurement is handled using the Taylor series expansion method, where the higher-order terms of the linearization error are represented by norm-bounded uncertainties. Further, a time-varying filter is designed by defining a new augmented system and introducing the variance constraint method, which ensures the upper bound of the filtering error covariance. Finally, to demonstrate the effectiveness of the proposed filtering algorithm, a simulation example is provided.