An Improved Iterative Maximum Correntropy Cubature Kalman Filter

Abstract

This paper investigates the problem of filtering for nonlinear system under outlier. To improve the reliability and precision of state estimation for nonlinear system with outlier, an improved iterative maximum correntropy cubature Kalman filter is proposed. In this work, cubature Kalman filter is applied to estimate the state of system. The sigma-point-based iterative strategy is designed, which uses the sigma points to iterate instead of the state estimation. Considering the effects of shot noise for nonlinear system, the rule of maximum correntropy is utilized to reduce the effect of shot noise existing in the measurement. Finally, the simulation results proves the validity of the proposed method.