Iterated Posterior Linearization Smoother
Journal article, 2017

This note considers the problem of Bayesian smoothing in nonlinear state-space models with additive noise using Gaussian approximations. Sigma-point approximations to the general Gaussian Rauch-Tung-Striebel smoother are widely used methods to tackle this problem. These algorithms perform statistical linear regression (SLR) of the nonlinear functions considering only the previous measurements. We argue that SLR should be done taking all measurements into account. We propose the iterated posterior linearization smoother (IPLS), which is an iterated algorithm that performs SLR of the nonlinear functions with respect to the current posterior approximation. The algorithm is demonstrated to outperform conventional Gaussian nonlinear smoothers in two numerical examples.

sigma-points

Bayesian smoothing

iterated smoothing

statistical

Gauss-Newton Method

Rauch-Tung-Striebel smoothing

Author

Angel Garcia

Curtin University

Lennart Svensson

Chalmers, Signals and Systems, Signal Processing and Biomedical Engineering

S. Särkkä

Aalto University

IEEE Transactions on Automatic Control

0018-9286 (ISSN) 1558-2523 (eISSN)

Vol. 62 4 2056-2063 7515187

Subject Categories

Electrical Engineering, Electronic Engineering, Information Engineering

DOI

10.1109/TAC.2016.2592681

More information

Latest update

4/5/2022 7