A Novel Inverse-Wishart-Student’s t Mixture Distribution-Based Variational Bayesian Kalman Filter
IEEE Sensors Journal · 01.12.2024 · 24 (23) · 39325-39333
DOI: 10.1109/jsen.2024.3472092 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Sensors Journal, erschienen am 01.12.2024. Verfasst von Shuaiyong Li und 1 weiteren Autor:innen. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 26 Literaturangaben. Gefördert von: Chongqing Natural Science Foundation Innovation and Development Joint Foundation, Science and Technology Research Project of Chongqing Education Commission, Nanning “Yongjiang Plan” Youth Talent Project.
Abstract (Originalsprache)
Considering the conventional Kalman filter (KF) has insufficient accuracy in state estimation under nonsmooth thick-tailed noise, a novel inverse-Wishart-student’s t mixed distribution (IWSTM) is proposed to adaptively learn the state vectors and associated auxiliary parameters using variational Bayesian (VB) approach. Then, a novel VB adaptive Kalman filter (VBAKF-IWSTM) is proposed to enhance state estimation accuracy under the conditions of nonsmooth thick-tailed measurement noise. Compared with RSTKF and GSTMKF, the novel VBAKF-IWSTM has a better fitting effect of nonsmooth thick-tailed noise based on the two auxiliary parameters, which are learned adaptively by VB to realize the correction of location parameter and scale parameter of the student’s t-distribution. The performance of the novel IWSTM is also demonstrated to outperform the existing KF in the simulation experiments and real trajectory experiments of the mobile robot conducted in this article.
Förderung
- Chongqing Natural Science Foundation Innovation and Development Joint Foundation
- Science and Technology Research Project of Chongqing Education Commission
- Nanning “Yongjiang Plan” Youth Talent Project
- Chongqing Research Institution Performance Incentive Guidance Special Project
- Special General Project for Chongqing’s Technological Innovation and Application Development
Zitieren
APA
Li, S., & Guo, C. (2024). A Novel Inverse-Wishart-Student’s t Mixture Distribution-Based Variational Bayesian Kalman Filter. IEEE Sensors Journal, 24(23), 39325-39333. https://doi.org/10.1109/jsen.2024.3472092
Vancouver
Li S, Guo C. A Novel Inverse-Wishart-Student’s t Mixture Distribution-Based Variational Bayesian Kalman Filter. IEEE Sensors Journal. 2024;24(23):39325-39333. doi:10.1109/jsen.2024.3472092
BibTeX
@article{Li2024,
author = {Li, Shuaiyong and Guo, Chengchun},
title = {A Novel Inverse-Wishart-Student’s t Mixture Distribution-Based Variational Bayesian Kalman Filter},
journal = {IEEE Sensors Journal},
year = {2024},
volume = {24},
number = {23},
pages = {39325--39333},
doi = {10.1109/jsen.2024.3472092}
}
EUVIMED