SVRPF: An Improved Particle Filter for a Nonlinear/Non-Gaussian Environment
The performance of a particle filter (PF) in nonlinear and non-Gaussian environments is often affected by particle degeneracy and impoverishment problems. In this paper, these two problems are re-assessed using the concepts of importance region (IR) selection and particle density (PD), where IR desc...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2019-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8869858/ |
id |
doaj-8964258470f24902a84a03935bca7a37 |
---|---|
record_format |
Article |
spelling |
doaj-8964258470f24902a84a03935bca7a372021-03-29T23:03:35ZengIEEEIEEE Access2169-35362019-01-01715163815165110.1109/ACCESS.2019.29475408869858SVRPF: An Improved Particle Filter for a Nonlinear/Non-Gaussian EnvironmentXingzi Qiang0https://orcid.org/0000-0003-3559-0939Yanbo Zhu1Rui Xue2https://orcid.org/0000-0002-9188-175XSchool of Electronics and Information Engineering, Beihang University, Beijing, ChinaSchool of Electronics and Information Engineering, Beihang University, Beijing, ChinaSchool of Electronics and Information Engineering, Beihang University, Beijing, ChinaThe performance of a particle filter (PF) in nonlinear and non-Gaussian environments is often affected by particle degeneracy and impoverishment problems. In this paper, these two problems are re-assessed using the concepts of importance region (IR) selection and particle density (PD), where IR describes the distribution region of particles, and PD describes the density of particles in IR. Based on these two factors, a support vector regression PF (SVRPF) is proposed to overcome the problems from nonlinear and non-Gaussian environments, especially in regard to narrow observation noise. Furthermore, the consistency of the SVRPF and Bayes' filtering is demonstrated. A numerical simulation shows that the performance of the SVRPF is more stable than other filter algorithms. Provided that other conditions are the same, when the observation noise variance is 0.1 and 5, the root-mean-square errors of the SVRPF decrease by 0.5 and 0.03, respectively, compared with that of a general PF.https://ieeexplore.ieee.org/document/8869858/Particle filteringprobability density estimationnonlinear/non-Gaussian environmentsupport vector regression |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Xingzi Qiang Yanbo Zhu Rui Xue |
spellingShingle |
Xingzi Qiang Yanbo Zhu Rui Xue SVRPF: An Improved Particle Filter for a Nonlinear/Non-Gaussian Environment IEEE Access Particle filtering probability density estimation nonlinear/non-Gaussian environment support vector regression |
author_facet |
Xingzi Qiang Yanbo Zhu Rui Xue |
author_sort |
Xingzi Qiang |
title |
SVRPF: An Improved Particle Filter for a Nonlinear/Non-Gaussian Environment |
title_short |
SVRPF: An Improved Particle Filter for a Nonlinear/Non-Gaussian Environment |
title_full |
SVRPF: An Improved Particle Filter for a Nonlinear/Non-Gaussian Environment |
title_fullStr |
SVRPF: An Improved Particle Filter for a Nonlinear/Non-Gaussian Environment |
title_full_unstemmed |
SVRPF: An Improved Particle Filter for a Nonlinear/Non-Gaussian Environment |
title_sort |
svrpf: an improved particle filter for a nonlinear/non-gaussian environment |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2019-01-01 |
description |
The performance of a particle filter (PF) in nonlinear and non-Gaussian environments is often affected by particle degeneracy and impoverishment problems. In this paper, these two problems are re-assessed using the concepts of importance region (IR) selection and particle density (PD), where IR describes the distribution region of particles, and PD describes the density of particles in IR. Based on these two factors, a support vector regression PF (SVRPF) is proposed to overcome the problems from nonlinear and non-Gaussian environments, especially in regard to narrow observation noise. Furthermore, the consistency of the SVRPF and Bayes' filtering is demonstrated. A numerical simulation shows that the performance of the SVRPF is more stable than other filter algorithms. Provided that other conditions are the same, when the observation noise variance is 0.1 and 5, the root-mean-square errors of the SVRPF decrease by 0.5 and 0.03, respectively, compared with that of a general PF. |
topic |
Particle filtering probability density estimation nonlinear/non-Gaussian environment support vector regression |
url |
https://ieeexplore.ieee.org/document/8869858/ |
work_keys_str_mv |
AT xingziqiang svrpfanimprovedparticlefilterforanonlinearnongaussianenvironment AT yanbozhu svrpfanimprovedparticlefilterforanonlinearnongaussianenvironment AT ruixue svrpfanimprovedparticlefilterforanonlinearnongaussianenvironment |
_version_ |
1724190227224854528 |