Skip to Main content Skip to Navigation
Journal articles

A variational marginalized particle filter for jump Markov nonlinear systems with unknown transition probabilities

Abstract : This paper studies a new variational marginalized particle filter for jointly estimating the state and the system mode parameters of jump Markov nonlinear systems. Contrary to the Markovian assumption usu- ally considered to model the evolution of the system modes, we introduce conjugate prior distributions for the system mode parameters. The joint posterior distribution of the state and system mode parame- ters is then marginalized with respect to the mode variables. The remaining state vector is sampled us- ing a sequential Monte Carlo algorithm, and the mode parameters are sampled using variational Bayesian inference. In order to obtain analytical solutions for the different variational distributions, we use an extended factorized approximation simplifying the variational distributions. A comprehensive simulation study is conducted to compare the performance of the proposed approach with the state-of-the-art for a modified nonlinear benchmark model and maneuvering target tracking scenarios.
Document type :
Journal articles
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03382639
Contributor : Open Archive Toulouse Archive Ouverte (oatao) Connect in order to contact the contributor
Submitted on : Monday, October 18, 2021 - 11:52:27 AM
Last modification on : Tuesday, October 26, 2021 - 3:58:13 AM
Long-term archiving on: : Wednesday, January 19, 2022 - 8:26:06 PM

File

Cheng_28131.pdf
Files produced by the author(s)

Identifiers

Citation

Cheng Cheng, Jean-Yves Tourneret. A variational marginalized particle filter for jump Markov nonlinear systems with unknown transition probabilities. Signal Processing, Elsevier, 2021, 188, pp.108226. ⟨10.1016/j.sigpro.2021.108226⟩. ⟨hal-03382639⟩

Share

Metrics

Les métriques sont temporairement indisponibles