Class Of Kalman Filters Research Articles

On the equivalence between steady-state Kalman filter and DPLL

Fundamental results in the literature showed that a class of Kalman filters (KF) converges to a digital phase lock loop (DPLL) structure. Results were proved for second- and third-order KFs. We extend these results to KFs of any order and derive in closed form the equivalent loop filter constants as a linear combination of the steady-state Kalman gains. We also give the inverse relation. Both closed-form relations involve Stirling numbers of the first or second kind. We implement both filters in a global navigation satellite system (GNSS) receiver and illustrate their equivalence with real-world data. These extended theoretical results provide a deeper understanding of the equivalence between KF and DPLL and may be of practical interest in highly dynamic scenarios to design and tune tracking filters.

Bayesian estimation for target tracking: part II, the Gaussian sigma‐point Kalman filters

AbstractThis is the second part of a three part article examining methods for Bayesian estimation and tracking. In the first part we presented the general theory of Bayesian estimation where we showed that Bayesian estimation methods can be divided into two very general classes: a class where the observation conditioned posterior densities are propagated in time through a predictor/corrector method; and a second class where the first two moments are propagated in time, with state and observation moment prediction steps followed by state moment update steps that use the latest observations. In this second part, we make the assumption that all densities are Gaussian and, after applying an affine transformation and approximating all nonlinear functions by interpolating polynomials, we recover the sigma‐point class of Kalman filters, including the unscented, spherical simplex, and Gauss‐Hermite Kalman filters. In part 3, we will show that approximating a density by a set of Monte Carlo samples leads to particle filter methods, where the posterior density is propagated in time and moment integrals are approximated by sample moments. WIREs Comput Stat 2012 doi: 10.1002/wics.1215This article is categorized under: Statistical and Graphical Methods of Data Analysis > Bayesian Methods and Theory