A novel robust kalman filter with non-stationary heavy-tailed measurement noise

Guangle Jia; Yulong Huang; Mingming Bai; Yonggang Zhang

doi:10.1016/j.ifacol.2020.12.188

A novel robust kalman filter with non-stationary heavy-tailed measurement noise

Guangle Jia^*
, Yulong Huang^*
, Mingming Bai^*
, Yonggang Zhang^*

^*Corresponding author for this work

Harbin Engineering University
City University of Hong Kong

Research output: Contribution to journal › Conference article › peer-review

21 Scopus citations

Abstract

A novel robust Kalman filter based on Gaussian-Student's t mixture (GSTM) distribution is proposed to address the filtering problem of a linear system with non-stationary heavy-tailed measurement noise. The mixing probability is recursively estimated by using its previous estimates as prior information, and the state vector, the auxiliary parameter, the Bernoulli random variable and the mixing probability are jointly estimated utilizing the variational Bayesian method. The excellent performance of the proposed robust Kalman filter, compared with the existing state-of-the-art filters, is illustrated by a target tracking simulation results under the case of non-stationary heavy-tailed measurement noise.

Original language	English
Pages (from-to)	368-373
Number of pages	6
Journal	IFAC-PapersOnLine
Volume	53
Issue number	2
DOIs	https://doi.org/10.1016/j.ifacol.2020.12.188
State	Published - 2020
Externally published	Yes
Event	21st IFAC World Congress 2020 - Berlin, Germany Duration: 12 Jul 2020 → 17 Jul 2020

Keywords

Gaussian-Student's t mixture
Non-stationary heavy-tailed measurement noise
Robust Kalman filter
Variational Bayesian

Access to Document

10.1016/j.ifacol.2020.12.188

Cite this

@article{c5ba3844628942328b532b3ef7b86233,

title = "A novel robust kalman filter with non-stationary heavy-tailed measurement noise",

abstract = "A novel robust Kalman filter based on Gaussian-Student's t mixture (GSTM) distribution is proposed to address the filtering problem of a linear system with non-stationary heavy-tailed measurement noise. The mixing probability is recursively estimated by using its previous estimates as prior information, and the state vector, the auxiliary parameter, the Bernoulli random variable and the mixing probability are jointly estimated utilizing the variational Bayesian method. The excellent performance of the proposed robust Kalman filter, compared with the existing state-of-the-art filters, is illustrated by a target tracking simulation results under the case of non-stationary heavy-tailed measurement noise.",

keywords = "Gaussian-Student's t mixture, Non-stationary heavy-tailed measurement noise, Robust Kalman filter, Variational Bayesian",

author = "Guangle Jia and Yulong Huang and Mingming Bai and Yonggang Zhang",

note = "Publisher Copyright: Copyright {\textcopyright} 2020 The Authors. This is an open access article under the CC BY-NC-ND license; 21st IFAC World Congress 2020 ; Conference date: 12-07-2020 Through 17-07-2020",

year = "2020",

doi = "10.1016/j.ifacol.2020.12.188",

language = "英语",

volume = "53",

pages = "368--373",

journal = "IFAC-PapersOnLine",

issn = "2405-8971",

publisher = "Elsevier B.V.",

number = "2",

}

TY - JOUR

T1 - A novel robust kalman filter with non-stationary heavy-tailed measurement noise

AU - Jia, Guangle

AU - Huang, Yulong

AU - Bai, Mingming

AU - Zhang, Yonggang

PY - 2020

Y1 - 2020

N2 - A novel robust Kalman filter based on Gaussian-Student's t mixture (GSTM) distribution is proposed to address the filtering problem of a linear system with non-stationary heavy-tailed measurement noise. The mixing probability is recursively estimated by using its previous estimates as prior information, and the state vector, the auxiliary parameter, the Bernoulli random variable and the mixing probability are jointly estimated utilizing the variational Bayesian method. The excellent performance of the proposed robust Kalman filter, compared with the existing state-of-the-art filters, is illustrated by a target tracking simulation results under the case of non-stationary heavy-tailed measurement noise.

AB - A novel robust Kalman filter based on Gaussian-Student's t mixture (GSTM) distribution is proposed to address the filtering problem of a linear system with non-stationary heavy-tailed measurement noise. The mixing probability is recursively estimated by using its previous estimates as prior information, and the state vector, the auxiliary parameter, the Bernoulli random variable and the mixing probability are jointly estimated utilizing the variational Bayesian method. The excellent performance of the proposed robust Kalman filter, compared with the existing state-of-the-art filters, is illustrated by a target tracking simulation results under the case of non-stationary heavy-tailed measurement noise.

KW - Gaussian-Student's t mixture

KW - Non-stationary heavy-tailed measurement noise

KW - Robust Kalman filter

KW - Variational Bayesian

UR - https://www.scopus.com/pages/publications/85105035934

U2 - 10.1016/j.ifacol.2020.12.188

DO - 10.1016/j.ifacol.2020.12.188

M3 - 会议文章

AN - SCOPUS:85105035934

SN - 2405-8971

VL - 53

SP - 368

EP - 373

JO - IFAC-PapersOnLine

JF - IFAC-PapersOnLine

IS - 2

T2 - 21st IFAC World Congress 2020

Y2 - 12 July 2020 through 17 July 2020

ER -

A novel robust kalman filter with non-stationary heavy-tailed measurement noise

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this