Iterated posterior linearisation smoother

Angel Garcia Fernandez, Lennart Svensson, Simo Särkkä

Research output: Contribution to journalArticleScientificpeer-review

18 Citations (Scopus)

Abstract

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.
Original languageEnglish
Article number7515187
Pages (from-to)2056-2063
Number of pages8
JournalIEEE Transactions on Automatic Control
Volume62
Issue number4
Early online date2016
DOIs
Publication statusPublished - 2017
MoE publication typeA1 Journal article-refereed

Keywords

  • Bayesian smoothing
  • iterated smoothing
  • Rauch-Tung-Striebel smoothing
  • sigma-points
  • statistical linear smoothing

Fingerprint Dive into the research topics of 'Iterated posterior linearisation smoother'. Together they form a unique fingerprint.

Cite this