Cargando…

DANAE(++): A Smart Approach for Denoising Underwater Attitude Estimation †

One of the main issues for the navigation of underwater robots consists in accurate vehicle positioning, which heavily depends on the orientation estimation phase. The systems employed to this end are affected by different noise typologies, mainly related to the sensors and to the irregular noise of...

Descripción completa

Detalles Bibliográficos
Autores principales: Russo, Paolo, Di Ciaccio, Fabiana, Troisi, Salvatore
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7926897/
https://www.ncbi.nlm.nih.gov/pubmed/33671819
http://dx.doi.org/10.3390/s21041526
_version_ 1783659567987556352
author Russo, Paolo
Di Ciaccio, Fabiana
Troisi, Salvatore
author_facet Russo, Paolo
Di Ciaccio, Fabiana
Troisi, Salvatore
author_sort Russo, Paolo
collection PubMed
description One of the main issues for the navigation of underwater robots consists in accurate vehicle positioning, which heavily depends on the orientation estimation phase. The systems employed to this end are affected by different noise typologies, mainly related to the sensors and to the irregular noise of the underwater environment. Filtering algorithms can reduce their effect if opportunely configured, but this process usually requires fine techniques and time. This paper presents DANAE [Formula: see text] , an improved denoising autoencoder based on DANAE (deep Denoising AutoeNcoder for Attitude Estimation), which is able to recover Kalman Filter (KF) IMU/AHRS orientation estimations from any kind of noise, independently of its nature. This deep learning-based architecture already proved to be robust and reliable, but in its enhanced implementation significant improvements are obtained in terms of both results and performance. In fact, DANAE [Formula: see text] is able to denoise the three angles describing the attitude at the same time, and that is verified also using the estimations provided by an extended KF. Further tests could make this method suitable for real-time applications in navigation tasks.
format Online
Article
Text
id pubmed-7926897
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-79268972021-03-04 DANAE(++): A Smart Approach for Denoising Underwater Attitude Estimation † Russo, Paolo Di Ciaccio, Fabiana Troisi, Salvatore Sensors (Basel) Article One of the main issues for the navigation of underwater robots consists in accurate vehicle positioning, which heavily depends on the orientation estimation phase. The systems employed to this end are affected by different noise typologies, mainly related to the sensors and to the irregular noise of the underwater environment. Filtering algorithms can reduce their effect if opportunely configured, but this process usually requires fine techniques and time. This paper presents DANAE [Formula: see text] , an improved denoising autoencoder based on DANAE (deep Denoising AutoeNcoder for Attitude Estimation), which is able to recover Kalman Filter (KF) IMU/AHRS orientation estimations from any kind of noise, independently of its nature. This deep learning-based architecture already proved to be robust and reliable, but in its enhanced implementation significant improvements are obtained in terms of both results and performance. In fact, DANAE [Formula: see text] is able to denoise the three angles describing the attitude at the same time, and that is verified also using the estimations provided by an extended KF. Further tests could make this method suitable for real-time applications in navigation tasks. MDPI 2021-02-22 /pmc/articles/PMC7926897/ /pubmed/33671819 http://dx.doi.org/10.3390/s21041526 Text en © 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Russo, Paolo
Di Ciaccio, Fabiana
Troisi, Salvatore
DANAE(++): A Smart Approach for Denoising Underwater Attitude Estimation †
title DANAE(++): A Smart Approach for Denoising Underwater Attitude Estimation †
title_full DANAE(++): A Smart Approach for Denoising Underwater Attitude Estimation †
title_fullStr DANAE(++): A Smart Approach for Denoising Underwater Attitude Estimation †
title_full_unstemmed DANAE(++): A Smart Approach for Denoising Underwater Attitude Estimation †
title_short DANAE(++): A Smart Approach for Denoising Underwater Attitude Estimation †
title_sort danae(++): a smart approach for denoising underwater attitude estimation †
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7926897/
https://www.ncbi.nlm.nih.gov/pubmed/33671819
http://dx.doi.org/10.3390/s21041526
work_keys_str_mv AT russopaolo danaeasmartapproachfordenoisingunderwaterattitudeestimation
AT diciacciofabiana danaeasmartapproachfordenoisingunderwaterattitudeestimation
AT troisisalvatore danaeasmartapproachfordenoisingunderwaterattitudeestimation