Uncertainty in Data-Driven Kalman Filtering for Partially Known State-Space Models

Providing a metric of uncertainty alongside a state estimate is often crucial when tracking a dynamical system. Classic state estimators, such as the Kalman filter (KF), provide a time-dependent uncertainty measure from knowledge of the underlying statistics, however, deep learning based tracking sy...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Klein, Itzik, Revach, Guy, Shlezinger, Nir, Mehr, Jonas E, van Sloun, Ruud J. G, Eldar, Yonina. C
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Klein, Itzik
Revach, Guy
Shlezinger, Nir
Mehr, Jonas E
van Sloun, Ruud J. G
Eldar, Yonina. C
description Providing a metric of uncertainty alongside a state estimate is often crucial when tracking a dynamical system. Classic state estimators, such as the Kalman filter (KF), provide a time-dependent uncertainty measure from knowledge of the underlying statistics, however, deep learning based tracking systems struggle to reliably characterize uncertainty. In this paper, we investigate the ability of KalmanNet, a recently proposed hybrid model-based deep state tracking algorithm, to estimate an uncertainty measure. By exploiting the interpretable nature of KalmanNet, we show that the error covariance matrix can be computed based on its internal features, as an uncertainty measure. We demonstrate that when the system dynamics are known, KalmanNet-which learns its mapping from data without access to the statistics-provides uncertainty similar to that provided by the KF; and while in the presence of evolution model-mismatch, KalmanNet pro-vides a more accurate error estimation.
doi_str_mv 10.48550/arxiv.2110.04738
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2110_04738</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2110_04738</sourcerecordid><originalsourceid>FETCH-LOGICAL-a678-1375cd76494aa1d26813732e376eeb367cffafb3643082d35523eefe47c175973</originalsourceid><addsrcrecordid>eNotj81OAjEURrtxYdAHcGVfoDj9L0sDogaMRnA9uXZuTZPSIaVB5-0dwdX35SxOcgi54c1UOa2bOyg_8TgVfASNstJdkveP7LFUiLkONGa6gApsUeIRM11B2kGmy5gqlpi_aOgLfYNSI6Q00FXuvzPdVKjINnvwSF_6DtPhilwESAe8_t8J2S4ftvMntn59fJ7frxkY6xiXVvvOGjVTALwTxo1ECpTWIH5KY30IEMajZONEJ7UWEjGgsp5bPbNyQm7P2lNUuy9xB2Vo_-LaU5z8BZEnSWw</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Uncertainty in Data-Driven Kalman Filtering for Partially Known State-Space Models</title><source>arXiv.org</source><creator>Klein, Itzik ; Revach, Guy ; Shlezinger, Nir ; Mehr, Jonas E ; van Sloun, Ruud J. G ; Eldar, Yonina. C</creator><creatorcontrib>Klein, Itzik ; Revach, Guy ; Shlezinger, Nir ; Mehr, Jonas E ; van Sloun, Ruud J. G ; Eldar, Yonina. C</creatorcontrib><description>Providing a metric of uncertainty alongside a state estimate is often crucial when tracking a dynamical system. Classic state estimators, such as the Kalman filter (KF), provide a time-dependent uncertainty measure from knowledge of the underlying statistics, however, deep learning based tracking systems struggle to reliably characterize uncertainty. In this paper, we investigate the ability of KalmanNet, a recently proposed hybrid model-based deep state tracking algorithm, to estimate an uncertainty measure. By exploiting the interpretable nature of KalmanNet, we show that the error covariance matrix can be computed based on its internal features, as an uncertainty measure. We demonstrate that when the system dynamics are known, KalmanNet-which learns its mapping from data without access to the statistics-provides uncertainty similar to that provided by the KF; and while in the presence of evolution model-mismatch, KalmanNet pro-vides a more accurate error estimation.</description><identifier>DOI: 10.48550/arxiv.2110.04738</identifier><language>eng</language><subject>Computer Science - Learning</subject><creationdate>2021-10</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2110.04738$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2110.04738$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Klein, Itzik</creatorcontrib><creatorcontrib>Revach, Guy</creatorcontrib><creatorcontrib>Shlezinger, Nir</creatorcontrib><creatorcontrib>Mehr, Jonas E</creatorcontrib><creatorcontrib>van Sloun, Ruud J. G</creatorcontrib><creatorcontrib>Eldar, Yonina. C</creatorcontrib><title>Uncertainty in Data-Driven Kalman Filtering for Partially Known State-Space Models</title><description>Providing a metric of uncertainty alongside a state estimate is often crucial when tracking a dynamical system. Classic state estimators, such as the Kalman filter (KF), provide a time-dependent uncertainty measure from knowledge of the underlying statistics, however, deep learning based tracking systems struggle to reliably characterize uncertainty. In this paper, we investigate the ability of KalmanNet, a recently proposed hybrid model-based deep state tracking algorithm, to estimate an uncertainty measure. By exploiting the interpretable nature of KalmanNet, we show that the error covariance matrix can be computed based on its internal features, as an uncertainty measure. We demonstrate that when the system dynamics are known, KalmanNet-which learns its mapping from data without access to the statistics-provides uncertainty similar to that provided by the KF; and while in the presence of evolution model-mismatch, KalmanNet pro-vides a more accurate error estimation.</description><subject>Computer Science - Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj81OAjEURrtxYdAHcGVfoDj9L0sDogaMRnA9uXZuTZPSIaVB5-0dwdX35SxOcgi54c1UOa2bOyg_8TgVfASNstJdkveP7LFUiLkONGa6gApsUeIRM11B2kGmy5gqlpi_aOgLfYNSI6Q00FXuvzPdVKjINnvwSF_6DtPhilwESAe8_t8J2S4ftvMntn59fJ7frxkY6xiXVvvOGjVTALwTxo1ECpTWIH5KY30IEMajZONEJ7UWEjGgsp5bPbNyQm7P2lNUuy9xB2Vo_-LaU5z8BZEnSWw</recordid><startdate>20211010</startdate><enddate>20211010</enddate><creator>Klein, Itzik</creator><creator>Revach, Guy</creator><creator>Shlezinger, Nir</creator><creator>Mehr, Jonas E</creator><creator>van Sloun, Ruud J. G</creator><creator>Eldar, Yonina. C</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20211010</creationdate><title>Uncertainty in Data-Driven Kalman Filtering for Partially Known State-Space Models</title><author>Klein, Itzik ; Revach, Guy ; Shlezinger, Nir ; Mehr, Jonas E ; van Sloun, Ruud J. G ; Eldar, Yonina. C</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a678-1375cd76494aa1d26813732e376eeb367cffafb3643082d35523eefe47c175973</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Computer Science - Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Klein, Itzik</creatorcontrib><creatorcontrib>Revach, Guy</creatorcontrib><creatorcontrib>Shlezinger, Nir</creatorcontrib><creatorcontrib>Mehr, Jonas E</creatorcontrib><creatorcontrib>van Sloun, Ruud J. G</creatorcontrib><creatorcontrib>Eldar, Yonina. C</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Klein, Itzik</au><au>Revach, Guy</au><au>Shlezinger, Nir</au><au>Mehr, Jonas E</au><au>van Sloun, Ruud J. G</au><au>Eldar, Yonina. C</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Uncertainty in Data-Driven Kalman Filtering for Partially Known State-Space Models</atitle><date>2021-10-10</date><risdate>2021</risdate><abstract>Providing a metric of uncertainty alongside a state estimate is often crucial when tracking a dynamical system. Classic state estimators, such as the Kalman filter (KF), provide a time-dependent uncertainty measure from knowledge of the underlying statistics, however, deep learning based tracking systems struggle to reliably characterize uncertainty. In this paper, we investigate the ability of KalmanNet, a recently proposed hybrid model-based deep state tracking algorithm, to estimate an uncertainty measure. By exploiting the interpretable nature of KalmanNet, we show that the error covariance matrix can be computed based on its internal features, as an uncertainty measure. We demonstrate that when the system dynamics are known, KalmanNet-which learns its mapping from data without access to the statistics-provides uncertainty similar to that provided by the KF; and while in the presence of evolution model-mismatch, KalmanNet pro-vides a more accurate error estimation.</abstract><doi>10.48550/arxiv.2110.04738</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2110.04738
ispartof
issn
language eng
recordid cdi_arxiv_primary_2110_04738
source arXiv.org
subjects Computer Science - Learning
title Uncertainty in Data-Driven Kalman Filtering for Partially Known State-Space Models
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-22T05%3A06%3A19IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Uncertainty%20in%20Data-Driven%20Kalman%20Filtering%20for%20Partially%20Known%20State-Space%20Models&rft.au=Klein,%20Itzik&rft.date=2021-10-10&rft_id=info:doi/10.48550/arxiv.2110.04738&rft_dat=%3Carxiv_GOX%3E2110_04738%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true