Dynamically Iterated Filters: A unified framework for improved iterated filtering and smoothing

Abstract

Typical iterated filters, such as the iterated extended Kalman filter (IEKF), iterated unscented Kalman filter (IUKF), and iterated posterior linearization filter (IPLF), have been developed to improve the linearization point (or density) of the likelihood linearization in the well-known extended Kalman filter (EKF) and unscented Kalman filter (UKF). A shortcoming of typical iterated filters is that they do not treat the linearization of the transition model of the system. To remedy this shortcoming, we introduce dynamically iterated filters (DIFs), a unified framework for iterated linearization-based nonlinear filters that deals with nonlinearities in both the transition model and the likelihood, thereby constituting a generalization of the aforementioned iterated filters. We further establish a relationship between the general DIF and the approximate iterated Rauch-Tung-Striebel smoother. This relationship allows for a Gauss-Newton interpretation, which in turn enables explicit step-size correction, leading to damped versions of the DIFs. The developed algorithms, both damped and non-damped, are numerically demonstrated in three examples, showing superior mean-squared error as well as improved parameter tuning robustness as compared to the analogous standard iterated filters.