Hybrid Neural Network Augmented Physics-based Models for Nonlinear Filtering

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F22%3A43966078" target="_blank" >RIV/49777513:23520/22:43966078 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.23919/FUSION49751.2022.9841291" target="_blank" >https://doi.org/10.23919/FUSION49751.2022.9841291</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.23919/FUSION49751.2022.9841291" target="_blank" >10.23919/FUSION49751.2022.9841291</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Hybrid Neural Network Augmented Physics-based Models for Nonlinear Filtering

Popis výsledku v původním jazyce

In this paper we present a hybrid neural network augmented physics-based modeling (APBM) framework for Bayesian nonlinear latent space estimation. The proposed APBM strategy allows for model adaptation when new operation conditions come into play or the physics-based model is insufficient (or incomplete) to properly describe the latent phenomenon. One advantage of the APBMs and our estimation procedure is the capability of maintaining the physical interpretability of estimated states. Furthermore, we propose a constraint filtering approach to control the neural network contributions to the overall model. We also exploit assumed density filtering techniques and cubature integration rules to present a flexible estimation strategy that can easily deal with nonlinear models and high-dimensional latent spaces. Finally, we demonstrate the efficacy of our methodology by leveraging a target tracking scenario with nonlinear and incomplete measurement and acceleration models, respectively.

Název v anglickém jazyce

Hybrid Neural Network Augmented Physics-based Models for Nonlinear Filtering

Popis výsledku anglicky

In this paper we present a hybrid neural network augmented physics-based modeling (APBM) framework for Bayesian nonlinear latent space estimation. The proposed APBM strategy allows for model adaptation when new operation conditions come into play or the physics-based model is insufficient (or incomplete) to properly describe the latent phenomenon. One advantage of the APBMs and our estimation procedure is the capability of maintaining the physical interpretability of estimated states. Furthermore, we propose a constraint filtering approach to control the neural network contributions to the overall model. We also exploit assumed density filtering techniques and cubature integration rules to present a flexible estimation strategy that can easily deal with nonlinear models and high-dimensional latent spaces. Finally, we demonstrate the efficacy of our methodology by leveraging a target tracking scenario with nonlinear and incomplete measurement and acceleration models, respectively.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20205 - Automation and control systems

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach<br>I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2022

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of the 25th International Conference on Information Fusion, FUSION 2022

ISBN

978-1-73774-972-1

ISSN

—

e-ISSN

—

Počet stran výsledku

6

Strana od-do

1-6

Název nakladatele

IEEE

Místo vydání

Linköping, Sweden

Místo konání akce

Linköping, Sweden

Datum konání akce

4. 7. 2022

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000855689000065