Robust variational Bayesian adaptive Kalman filtering algorithm

A robust adaptive Kalman filtering (RAKF) algorithm based on variational Bayes was presented. This algorithm models the measurement model with a Student's distribution which could characterize the heavy-tailed phenomenon to replace Gaussian distribution and hence the sensitivity to outliers decreases. Variational Bayes was also used in this algorithm to approximate time-variant parameters of the modified model. In this manner, the states were estimated recursively together with the time-variant noise covariance, and the introduced degree of freedom was updated. Therefore, the adaptive filtering was carried out with strong robustness. Simulation results demonstrate that the adaptability and robustness of the proposed filter are corrupted with outliers when the time-variant noisy is measured.