Data-Driven State Estimation for Nonlinear Stochastic Systems Using Gaussian Process-Based Adaptive Interacting Multiple Model Particle Filtering
Automation · 18.06.2026 · 7 (3) · 97
DOI: 10.3390/automation7030097 ↗Kurz gefasst
Fachartikel in der Zeitschrift Automation, online erschienen am 18.06.2026. Verfasst von Xueqi Yuan und 1 weiteren Autor:innen. Die Arbeit nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
This paper focuses on state estimation for nonlinear stochastic systems with multiple switching models, especially under challenging conditions where the model dynamics are unknown and the transition probability matrix is uniformly distributed. Gaussian process regression is employed to learn the unknown system dynamics from an offline discrete dataset and is integrated into an interacting multiple model particle filtering framework. GPR enables data-driven learning of both state transition and observation functions. To cope with model uncertainty and uninformative prior transition knowledge, particularly under uniformly initialized TPM, a dual-layer adaptive TPM update strategy based on hidden Markov model inference is further incorporated. Finally, the proposed method is validated through simulations and compared with IMMPF under different assumptions on system dynamics and TPMs. The results show that, even without prior knowledge of the system dynamics or precise TPM information, the proposed GP-AIMMPF maintains robust and accurate state estimation performance.
Zitieren
APA
Yuan, X., & Sun, Q. (2026). Data-Driven State Estimation for Nonlinear Stochastic Systems Using Gaussian Process-Based Adaptive Interacting Multiple Model Particle Filtering. Automation, 7(3), 97. https://doi.org/10.3390/automation7030097
Vancouver
Yuan X, Sun Q. Data-Driven State Estimation for Nonlinear Stochastic Systems Using Gaussian Process-Based Adaptive Interacting Multiple Model Particle Filtering. Automation. 2026;7(3):97. doi:10.3390/automation7030097
BibTeX
@article{Yuan2026,
author = {Yuan, Xueqi and Sun, Qing},
title = {Data-Driven State Estimation for Nonlinear Stochastic Systems Using Gaussian Process-Based Adaptive Interacting Multiple Model Particle Filtering},
journal = {Automation},
year = {2026},
volume = {7},
number = {3},
pages = {97},
doi = {10.3390/automation7030097}
}
EUVIMED