An outlier-robust Kalman filter with mixture correntropy
share
We consider the robust filtering problem for a nonlinear state-space model with outliers in measurements. A novel robust cubature Kalman filtering algorithm is proposed based on mixture correntropy with two Gaussian kernels. We have formulated the robust filtering problem by employing the mixture correntropy induced cost to replace the quadratic one in the conventional Gaussian approximation filter for the measurement fitting error. In addition, a tradeoff weighting coefficient is introduced to make sure the proposed approach can provide reasonable state estimates in scenarios with small measurement fitting errors. The robust filtering problem is iteratively solved by using the cubature Kalman filtering framework with a reweighted measurement covariance. Numerical results show that the proposed method can achieve a performance improvement over existing robust solutions.
READ FULL TEXT
