Title:	Hybrid Neural Network Augmented Physics-based Models for Nonlinear Filtering
Authors:	Imbiriba, Tales Demirkaya, Ahmet Duník, Jindřich Straka, Ondřej Erdoğmuş, Deniz Closas, Pau
Citation:	IMBIRIBA, T. DEMIRKAYA, A. DUNÍK, J. STRAKA, O. ERDOĞMUŞ, D. CLOSAS, P. Hybrid Neural Network Augmented Physics-based Models for Nonlinear Filtering. In Proceedings of the 25th International Conference on Information Fusion, FUSION 2022. Linköping, Sweden: IEEE, 2022. s. 1-6. ISBN: 978-1-73774-972-1 , ISSN: neuvedeno
Issue Date:	2022
Publisher:	IEEE
Document type:	konferenční příspěvek ConferenceObject
URI:	2-s2.0-85136554327 http://hdl.handle.net/11025/51459
ISBN:	978-1-73774-972-1
ISSN:	neuvedeno
Keywords in different language:	Nonlinear filtering;Target tracking;Hybrid Neural Network;Physics-based Neural Models;Gaussian filtering
Abstract in different language:	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.
Rights:	Plný text je přístupný v rámci univerzity přihlášeným uživatelům. © IEEE
Appears in Collections:	Konferenční příspěvky / Conference papers (NTIS) Konferenční příspěvky / Conference Papers (KKY) OBD

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.