Bayesian KalmanNet: Quantifying Uncertainty in Deep Learning Augmented Kalman Filter

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F25%3A43976518" target="_blank" >RIV/49777513:23520/25:43976518 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/TSP.2025.3581703" target="_blank" >https://doi.org/10.1109/TSP.2025.3581703</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/TSP.2025.3581703" target="_blank" >10.1109/TSP.2025.3581703</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Bayesian KalmanNet: Quantifying Uncertainty in Deep Learning Augmented Kalman Filter

Popis výsledku v původním jazyce

Recent years have witnessed a growing interest in tracking algorithms that augment Kalman filters (KFs) with deep neural networks (DNNs). By transforming KFs into trainable deep learning models, one can learn from data to reliably track a latent state in complex and partially known dynamics. However, unlike classic KFs, conventional DNN-based systems do not naturally provide an uncertainty measure, such as error covariance, alongside their estimates, which is crucial in various applications that rely on KF-type tracking. This work bridges this gap by studying error covariance extraction in DNN-aided KFs. We begin by characterizing how uncertainty can be extracted from existing DNN-aided algorithms and distinguishing between approaches by their ability to associate internal features with meaningful KF quantities, such as the Kalman gain and prior covariance. We then identify that uncertainty extraction from existing architectures necessitates additional domain knowledge not required for state estimation. Based on this insight, we propose Bayesian KalmanNet, a novel DNN-aided KF that integrates Bayesian deep learning techniques with the recently proposed KalmanNet and transforms the KF into a stochastic machine learning architecture. This architecture employs sampling techniques to predict error covariance reliably without requiring additional domain knowledge, while retaining KalmanNet&apos;s ability to accurately track in partially known dynamics. Our numerical study demonstrates that Bayesian KalmanNet provides accurate and reliable tracking in various scenarios representing partially known dynamic systems.

Název v anglickém jazyce

Bayesian KalmanNet: Quantifying Uncertainty in Deep Learning Augmented Kalman Filter

Popis výsledku anglicky

Recent years have witnessed a growing interest in tracking algorithms that augment Kalman filters (KFs) with deep neural networks (DNNs). By transforming KFs into trainable deep learning models, one can learn from data to reliably track a latent state in complex and partially known dynamics. However, unlike classic KFs, conventional DNN-based systems do not naturally provide an uncertainty measure, such as error covariance, alongside their estimates, which is crucial in various applications that rely on KF-type tracking. This work bridges this gap by studying error covariance extraction in DNN-aided KFs. We begin by characterizing how uncertainty can be extracted from existing DNN-aided algorithms and distinguishing between approaches by their ability to associate internal features with meaningful KF quantities, such as the Kalman gain and prior covariance. We then identify that uncertainty extraction from existing architectures necessitates additional domain knowledge not required for state estimation. Based on this insight, we propose Bayesian KalmanNet, a novel DNN-aided KF that integrates Bayesian deep learning techniques with the recently proposed KalmanNet and transforms the KF into a stochastic machine learning architecture. This architecture employs sampling techniques to predict error covariance reliably without requiring additional domain knowledge, while retaining KalmanNet&apos;s ability to accurately track in partially known dynamics. Our numerical study demonstrates that Bayesian KalmanNet provides accurate and reliable tracking in various scenarios representing partially known dynamic systems.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

20205 - Automation and control systems

Projekt

<a href="/cs/project/EH22_008%2F0004590" target="_blank" >EH22_008/0004590: Robotika a pokročilá průmyslová výroba</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2025

Kód důvěrnosti údajů

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

Název periodika

IEEE Transactions on Signal Processing

ISSN

1053-587X

e-ISSN

1941-0476

Svazek periodika

73

Číslo periodika v rámci svazku

June 2025

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

16

Strana od-do

2558-2573

Kód UT WoS článku

001525462300004

EID výsledku v databázi Scopus

2-s2.0-105009290864