Damped Posterior Linearization Filter

Matti Raitoharju; Lennart Svensson; Angel Froilan Garcia-Fernandez; Robert Piche

doi:10.1109/LSP.2018.2806304

Damped Posterior Linearization Filter

Matti Raitoharju, Lennart Svensson, Angel Froilan Garcia-Fernandez, Robert Piche

Research output: Contribution to journal › Article › Scientific › peer-review

20 Citations (Scopus)

48 Downloads (Pure)

Abstract

In this letter, we propose an iterative Kalman type algorithm based on posterior linearization. The proposed algorithm uses a nested loop structure to optimize the mean of the estimate in the inner loop and update the covariance, which is a computationally more expensive operation, only in the outer loop. The optimization of the mean update is done using a damped algorithm to avoid divergence. Our simulations show that the proposed algorithm is more accurate than existing iterative Kalman filters.

Original language	English
Journal	IEEE Signal Processing Letters
Volume	25
Issue number	4
Early online date	13 Feb 2018
DOIs	https://doi.org/10.1109/LSP.2018.2806304
Publication status	Published - 2018
Publication type	A1 Journal article-refereed

Keywords

Bayesian state estimation
Computational modeling
Convergence
Cost function
estimation
Kalman filters
Noise measurement
nonlinear
Signal processing algorithms

Publication forum classification

Publication forum level 2

ASJC Scopus subject areas

Signal Processing
Electrical and Electronic Engineering
Applied Mathematics

Access to Document

10.1109/LSP.2018.2806304

dampedPLF
© 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Accepted author manuscript, 296 KB

http://urn.fi/URN:NBN:fi:tty-201803281444

Cite this

@article{c06da2b948ec44bf950641dd85be593d,

title = "Damped Posterior Linearization Filter",

abstract = "In this letter, we propose an iterative Kalman type algorithm based on posterior linearization. The proposed algorithm uses a nested loop structure to optimize the mean of the estimate in the inner loop and update the covariance, which is a computationally more expensive operation, only in the outer loop. The optimization of the mean update is done using a damped algorithm to avoid divergence. Our simulations show that the proposed algorithm is more accurate than existing iterative Kalman filters.",

keywords = "Bayesian state estimation, Computational modeling, Convergence, Cost function, estimation, Kalman filters, Noise measurement, nonlinear, Signal processing algorithms",

author = "Matti Raitoharju and Lennart Svensson and Garcia-Fernandez, \{Angel Froilan\} and Robert Piche",

note = "EXT={"}Raitoharju, Matti{"}",

year = "2018",

doi = "10.1109/LSP.2018.2806304",

language = "English",

volume = "25",

journal = "IEEE Signal Processing Letters",

issn = "1070-9908",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "4",

}

TY - JOUR

T1 - Damped Posterior Linearization Filter

AU - Raitoharju, Matti

AU - Svensson, Lennart

AU - Garcia-Fernandez, Angel Froilan

AU - Piche, Robert

N1 - EXT="Raitoharju, Matti"

PY - 2018

Y1 - 2018

N2 - In this letter, we propose an iterative Kalman type algorithm based on posterior linearization. The proposed algorithm uses a nested loop structure to optimize the mean of the estimate in the inner loop and update the covariance, which is a computationally more expensive operation, only in the outer loop. The optimization of the mean update is done using a damped algorithm to avoid divergence. Our simulations show that the proposed algorithm is more accurate than existing iterative Kalman filters.

AB - In this letter, we propose an iterative Kalman type algorithm based on posterior linearization. The proposed algorithm uses a nested loop structure to optimize the mean of the estimate in the inner loop and update the covariance, which is a computationally more expensive operation, only in the outer loop. The optimization of the mean update is done using a damped algorithm to avoid divergence. Our simulations show that the proposed algorithm is more accurate than existing iterative Kalman filters.

KW - Bayesian state estimation

KW - Computational modeling

KW - Convergence

KW - Cost function

KW - estimation

KW - Kalman filters

KW - Noise measurement

KW - nonlinear

KW - Signal processing algorithms

U2 - 10.1109/LSP.2018.2806304

DO - 10.1109/LSP.2018.2806304

M3 - Article

AN - SCOPUS:85042110206

SN - 1070-9908

VL - 25

JO - IEEE Signal Processing Letters

JF - IEEE Signal Processing Letters

IS - 4

ER -

Damped Posterior Linearization Filter

Abstract

Keywords

Publication forum classification

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this