A New Strategy for Combining Nonlinear Kalman Filters With Smooth Variable Structure Filters

Bayesian filters exemplified by the celebrated Kalman Filter (KF), and its non-linear variants rely on a fairly accurate state-space model of the system under study. To address the issue of modelling uncertainty in state estimation, the Smooth Variable Structure Filter (SVSF) was proposed in 2007. Since then, several SVSF variants have been proposed to extend its domain of applicability. In some of these algorithms, SVSF has been viewed as a complementary approach alongside the well-established nonlinear Kalman Filters. This paper seeks a general framework for SVSF formulation to unify some of the recent developments in SVSF literature under one umbrella. In this way, the SVSF variants are revisited as special cases of the proposed framework. This paper proposes a new strategy to combine SVSF filters with other nonlinear filters and puts existing SVSF filters under one umbrella. Six filters are formulated based on the proposed method of combining filters. The proposed filters relax limitations of existing SVSF variants, making the proposed filters more universal. In simulations, the new filters outperform state-of-the-art nonlinear KFs and some existing SVSF filters. To demonstrate the merits of the proposed framework, the new filters are applied to target tracking and are comparatively evaluated.