An Underwater Integrated Navigation Algorithm to Deal With DVL Malfunctions Based on Deep Learning

In underwater navigation systems, Global Navigation Satellite System (GNSS) information cannot be used for navigation. The mainstream method of autonomous underwater vehicles (AUV) underwater navigation system is Doppler Velocity Log (DVL) aided strapdown inertial navigation system (SINS). However,...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ding Li, Jiangning Xu, Hongyang He, Miao Wu
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Strapdown inertial navigation system DVL integrated navigation deep learning NARX Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/e52844d62069465ca66c6f7c43bd6ade
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:e52844d62069465ca66c6f7c43bd6ade
record_format	dspace
spelling	oai:doaj.org-article:e52844d62069465ca66c6f7c43bd6ade2021-11-23T00:01:18ZAn Underwater Integrated Navigation Algorithm to Deal With DVL Malfunctions Based on Deep Learning2169-353610.1109/ACCESS.2021.3083493https://doaj.org/article/e52844d62069465ca66c6f7c43bd6ade2021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9440454/https://doaj.org/toc/2169-3536In underwater navigation systems, Global Navigation Satellite System (GNSS) information cannot be used for navigation. The mainstream method of autonomous underwater vehicles (AUV) underwater navigation system is Doppler Velocity Log (DVL) aided strapdown inertial navigation system (SINS). However, because the DVL is an instrument based on Doppler frequency shift to measure velocity, it is easily affected by the external environment. In a complex underwater environment, DVL output is easily polluted by outliers or even interrupted. In this paper, A new integrated navigation algorithm based on deep learning model is proposed to deal with DVL malfunctions. First, use RKF based on Mahalanobis distance algorithm to eliminate outliers, and then train the Nonlinear AutoRegressive with eXogenous input (NARX) model when DVL is available. When DVL is interrupted, use the NARX model to predict the output of DVL and continue integrated navigation. The proposed NARX-RKF scheme’s effectiveness verification was performed on the data set collected by the SINS/DVL ship-mounted experimental system. For comparison, different methods are also compared in the experiment. Experimental results show that NARX-RKF can effectively predict the output of DVL and is significantly better than other methods.Ding LiJiangning XuHongyang HeMiao WuIEEEarticleStrapdown inertial navigation systemDVLintegrated navigationdeep learningNARXElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 82010-82020 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Strapdown inertial navigation system DVL integrated navigation deep learning NARX Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Strapdown inertial navigation system DVL integrated navigation deep learning NARX Electrical engineering. Electronics. Nuclear engineering TK1-9971 Ding Li Jiangning Xu Hongyang He Miao Wu An Underwater Integrated Navigation Algorithm to Deal With DVL Malfunctions Based on Deep Learning
description	In underwater navigation systems, Global Navigation Satellite System (GNSS) information cannot be used for navigation. The mainstream method of autonomous underwater vehicles (AUV) underwater navigation system is Doppler Velocity Log (DVL) aided strapdown inertial navigation system (SINS). However, because the DVL is an instrument based on Doppler frequency shift to measure velocity, it is easily affected by the external environment. In a complex underwater environment, DVL output is easily polluted by outliers or even interrupted. In this paper, A new integrated navigation algorithm based on deep learning model is proposed to deal with DVL malfunctions. First, use RKF based on Mahalanobis distance algorithm to eliminate outliers, and then train the Nonlinear AutoRegressive with eXogenous input (NARX) model when DVL is available. When DVL is interrupted, use the NARX model to predict the output of DVL and continue integrated navigation. The proposed NARX-RKF scheme’s effectiveness verification was performed on the data set collected by the SINS/DVL ship-mounted experimental system. For comparison, different methods are also compared in the experiment. Experimental results show that NARX-RKF can effectively predict the output of DVL and is significantly better than other methods.
format	article
author	Ding Li Jiangning Xu Hongyang He Miao Wu
author_facet	Ding Li Jiangning Xu Hongyang He Miao Wu
author_sort	Ding Li
title	An Underwater Integrated Navigation Algorithm to Deal With DVL Malfunctions Based on Deep Learning
title_short	An Underwater Integrated Navigation Algorithm to Deal With DVL Malfunctions Based on Deep Learning
title_full	An Underwater Integrated Navigation Algorithm to Deal With DVL Malfunctions Based on Deep Learning
title_fullStr	An Underwater Integrated Navigation Algorithm to Deal With DVL Malfunctions Based on Deep Learning
title_full_unstemmed	An Underwater Integrated Navigation Algorithm to Deal With DVL Malfunctions Based on Deep Learning
title_sort	underwater integrated navigation algorithm to deal with dvl malfunctions based on deep learning
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/e52844d62069465ca66c6f7c43bd6ade
work_keys_str_mv	AT dingli anunderwaterintegratednavigationalgorithmtodealwithdvlmalfunctionsbasedondeeplearning AT jiangningxu anunderwaterintegratednavigationalgorithmtodealwithdvlmalfunctionsbasedondeeplearning AT hongyanghe anunderwaterintegratednavigationalgorithmtodealwithdvlmalfunctionsbasedondeeplearning AT miaowu anunderwaterintegratednavigationalgorithmtodealwithdvlmalfunctionsbasedondeeplearning AT dingli underwaterintegratednavigationalgorithmtodealwithdvlmalfunctionsbasedondeeplearning AT jiangningxu underwaterintegratednavigationalgorithmtodealwithdvlmalfunctionsbasedondeeplearning AT hongyanghe underwaterintegratednavigationalgorithmtodealwithdvlmalfunctionsbasedondeeplearning AT miaowu underwaterintegratednavigationalgorithmtodealwithdvlmalfunctionsbasedondeeplearning
_version_	1718417409574961152

An Underwater Integrated Navigation Algorithm to Deal With DVL Malfunctions Based on Deep Learning

Ejemplares similares