Tuning-free filtering for stochastic systems with unmodeled measurement dynamics

Abstract

This paper applies variational Bayesian to the stochastic system filtering problem for arbitrary measurement disturbances. Considering the system’s robustness when confronted with disturbances, we model its dynamics with a random walk model. Afterward, by assuming an inverse-Gamma distribution, the newly introduced covariance is estimated under a variational Bayesian (VB) framework. The proposed filter improves robustness against additive disturbance and degrades automatically into a Kalman filter when without disturbance. Moreover, this filter avoids the labor-intensive process of tuning parameters. A numerical simulation and an on-site vehicle navigation experiment are given to illustrate the effectiveness of the proposed filter.