Adaptive unscented Gaussian likelihood approximation filter

This paper focuses on the update step of Bayesian nonlinear filtering. We first derive the unscented Gaussian likelihood approximation filter (UGLAF), which provides a Gaussian approximation to the likelihood by applying the unscented transformation to the inverse of the measurement function. The UG...

Full description

Bibliographic Details
Main Authors: Garcia Fernandez, Angel, Morelande, M., Grajal, J., Svensson, L.
Format: Journal Article
Published: Pergamon Press 2015
Online Access:http://hdl.handle.net/20.500.11937/54227
_version_ 1848759319159373824
author Garcia Fernandez, Angel
Morelande, M.
Grajal, J.
Svensson, L.
author_facet Garcia Fernandez, Angel
Morelande, M.
Grajal, J.
Svensson, L.
author_sort Garcia Fernandez, Angel
building Curtin Institutional Repository
collection Online Access
description This paper focuses on the update step of Bayesian nonlinear filtering. We first derive the unscented Gaussian likelihood approximation filter (UGLAF), which provides a Gaussian approximation to the likelihood by applying the unscented transformation to the inverse of the measurement function. The UGLAF approximation is accurate in the cases where the unscented Kalman filter (UKF) is not and the other way round. As a result, we propose the adaptive UGLAF (AUGLAF), which selects the best approximation to the posterior (UKF or UGLAF) based on the Kullback-Leibler divergence. This enables AUGLAF to outperform both the UKF and UGLAF.
first_indexed 2025-11-14T09:57:59Z
format Journal Article
id curtin-20.500.11937-54227
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T09:57:59Z
publishDate 2015
publisher Pergamon Press
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-542272017-11-20T07:23:35Z Adaptive unscented Gaussian likelihood approximation filter Garcia Fernandez, Angel Morelande, M. Grajal, J. Svensson, L. This paper focuses on the update step of Bayesian nonlinear filtering. We first derive the unscented Gaussian likelihood approximation filter (UGLAF), which provides a Gaussian approximation to the likelihood by applying the unscented transformation to the inverse of the measurement function. The UGLAF approximation is accurate in the cases where the unscented Kalman filter (UKF) is not and the other way round. As a result, we propose the adaptive UGLAF (AUGLAF), which selects the best approximation to the posterior (UKF or UGLAF) based on the Kullback-Leibler divergence. This enables AUGLAF to outperform both the UKF and UGLAF. 2015 Journal Article http://hdl.handle.net/20.500.11937/54227 10.1016/j.automatica.2015.02.005 Pergamon Press restricted
spellingShingle Garcia Fernandez, Angel
Morelande, M.
Grajal, J.
Svensson, L.
Adaptive unscented Gaussian likelihood approximation filter
title Adaptive unscented Gaussian likelihood approximation filter
title_full Adaptive unscented Gaussian likelihood approximation filter
title_fullStr Adaptive unscented Gaussian likelihood approximation filter
title_full_unstemmed Adaptive unscented Gaussian likelihood approximation filter
title_short Adaptive unscented Gaussian likelihood approximation filter
title_sort adaptive unscented gaussian likelihood approximation filter
url http://hdl.handle.net/20.500.11937/54227