An Integrated Deep Ensemble-Unscented Kalman Filter for Sideslip Angle Estimation With Sensor Filtering Network

An integration scheme for sideslip angle estimation is proposed where a deep neural network and a simple kinematics-based model are combined in an unscented Kalman filter. The deep neural network contains two modules: a sensor filtering network designed to overcome the limitations of the kinematics-...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Dongchan Kim, Gihoon Kim, Seungwon Choi, Kunsoo Huh
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Sideslip angle estimation kinematic model unscented Kalman filter deep ensemble uncertainty sensor filtering network Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/567956f92829457190db4a9feb76fb1d
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:567956f92829457190db4a9feb76fb1d
record_format	dspace
spelling	oai:doaj.org-article:567956f92829457190db4a9feb76fb1d2021-11-18T00:08:23ZAn Integrated Deep Ensemble-Unscented Kalman Filter for Sideslip Angle Estimation With Sensor Filtering Network2169-353610.1109/ACCESS.2021.3125351https://doaj.org/article/567956f92829457190db4a9feb76fb1d2021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9604007/https://doaj.org/toc/2169-3536An integration scheme for sideslip angle estimation is proposed where a deep neural network and a simple kinematics-based model are combined in an unscented Kalman filter. The deep neural network contains two modules: a sensor filtering network designed to overcome the limitations of the kinematics-based model and a deep ensemble network to estimate the sideslip angle and its uncertainty. Both networks use recurrent neural networks with long short-term memory to analyze sequential sensor data. The networks were trained using only input signal sets that can be obtained from on- board sensor measurements. The filtering network reduces the noise and bias of the input signals to match the model used for the unscented Kalman filter. Next, the initial estimate and its uncertainty obtained from the deep ensemble network are utilized as a new measurement in the unscented Kalman filter, inducing an adaptive measurement variance. The algorithm was verified through both simulation and experiment, and the results demonstrate the effectiveness of the proposed algorithm.Dongchan KimGihoon KimSeungwon ChoiKunsoo HuhIEEEarticleSideslip angle estimationkinematic modelunscented Kalman filterdeep ensembleuncertaintysensor filtering networkElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 149681-149689 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Sideslip angle estimation kinematic model unscented Kalman filter deep ensemble uncertainty sensor filtering network Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Sideslip angle estimation kinematic model unscented Kalman filter deep ensemble uncertainty sensor filtering network Electrical engineering. Electronics. Nuclear engineering TK1-9971 Dongchan Kim Gihoon Kim Seungwon Choi Kunsoo Huh An Integrated Deep Ensemble-Unscented Kalman Filter for Sideslip Angle Estimation With Sensor Filtering Network
description	An integration scheme for sideslip angle estimation is proposed where a deep neural network and a simple kinematics-based model are combined in an unscented Kalman filter. The deep neural network contains two modules: a sensor filtering network designed to overcome the limitations of the kinematics-based model and a deep ensemble network to estimate the sideslip angle and its uncertainty. Both networks use recurrent neural networks with long short-term memory to analyze sequential sensor data. The networks were trained using only input signal sets that can be obtained from on- board sensor measurements. The filtering network reduces the noise and bias of the input signals to match the model used for the unscented Kalman filter. Next, the initial estimate and its uncertainty obtained from the deep ensemble network are utilized as a new measurement in the unscented Kalman filter, inducing an adaptive measurement variance. The algorithm was verified through both simulation and experiment, and the results demonstrate the effectiveness of the proposed algorithm.
format	article
author	Dongchan Kim Gihoon Kim Seungwon Choi Kunsoo Huh
author_facet	Dongchan Kim Gihoon Kim Seungwon Choi Kunsoo Huh
author_sort	Dongchan Kim
title	An Integrated Deep Ensemble-Unscented Kalman Filter for Sideslip Angle Estimation With Sensor Filtering Network
title_short	An Integrated Deep Ensemble-Unscented Kalman Filter for Sideslip Angle Estimation With Sensor Filtering Network
title_full	An Integrated Deep Ensemble-Unscented Kalman Filter for Sideslip Angle Estimation With Sensor Filtering Network
title_fullStr	An Integrated Deep Ensemble-Unscented Kalman Filter for Sideslip Angle Estimation With Sensor Filtering Network
title_full_unstemmed	An Integrated Deep Ensemble-Unscented Kalman Filter for Sideslip Angle Estimation With Sensor Filtering Network
title_sort	integrated deep ensemble-unscented kalman filter for sideslip angle estimation with sensor filtering network
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/567956f92829457190db4a9feb76fb1d
work_keys_str_mv	AT dongchankim anintegrateddeepensembleunscentedkalmanfilterforsideslipangleestimationwithsensorfilteringnetwork AT gihoonkim anintegrateddeepensembleunscentedkalmanfilterforsideslipangleestimationwithsensorfilteringnetwork AT seungwonchoi anintegrateddeepensembleunscentedkalmanfilterforsideslipangleestimationwithsensorfilteringnetwork AT kunsoohuh anintegrateddeepensembleunscentedkalmanfilterforsideslipangleestimationwithsensorfilteringnetwork AT dongchankim integrateddeepensembleunscentedkalmanfilterforsideslipangleestimationwithsensorfilteringnetwork AT gihoonkim integrateddeepensembleunscentedkalmanfilterforsideslipangleestimationwithsensorfilteringnetwork AT seungwonchoi integrateddeepensembleunscentedkalmanfilterforsideslipangleestimationwithsensorfilteringnetwork AT kunsoohuh integrateddeepensembleunscentedkalmanfilterforsideslipangleestimationwithsensorfilteringnetwork
_version_	1718425226301145088

An Integrated Deep Ensemble-Unscented Kalman Filter for Sideslip Angle Estimation With Sensor Filtering Network

Ejemplares similares