Open Access Repository

Position estimation for underwater vehicles using unscented Kalman filter with Gaussian process prediction

Downloads

Downloads per month over past year

Ariza Ramirez, W, Leong, ZQ ORCID: 0000-0002-0644-1822, Nguyen, H ORCID: 0000-0003-0118-8597 and Jayasinghe, SG ORCID: 0000-0002-3304-9455 2019 , 'Position estimation for underwater vehicles using unscented Kalman filter with Gaussian process prediction' , Underwater Technology, vol. 36, no. 2 , pp. 29-35 , doi: 10.3723/ut.36.029.

[img]
Preview
PDF (Published version)
145438-Position...pdf | Download (783kB)

| Preview

Abstract

The present paper explores the use of Gaussian processunscented Kalman filter (GP-UKF) algorithm for position estimation of underwater vehicles. GP-UKF has a number of advantages over parametric unscented Kalman filters (UKFs) and Bayesian filters, such as improved tracking quality and graceful degradation with the increase of model uncertainty. The advantage of Gaussian process (GP) over parametric models is that GP considers noise and uncertainty in model identification. These qualities are highly desired for underwater vehicles as the number and quality of sensors available for position estimation are limited. The application of non-parametric models on navigation for underwater vehicles can lead to faster deployment of the platform, reduced costs and better performance than parametric methodologies. In the present study, a REMUS 100 parametric model was employed for the generation of data and internal model in the calculation to compare the performance of an ideal UKF against GP-UKF for position estimation. GP-UKF demonstrated better performance and robustness in the estimation of vehicle position and state correction compared to the ideal UKF.

Item Type: Article
Authors/Creators:Ariza Ramirez, W and Leong, ZQ and Nguyen, H and Jayasinghe, SG
Keywords: machine learning, AUV, positioning, unscented Kalman filter, GP-UKF, Gaussian process, underwater vehicles
Journal or Publication Title: Underwater Technology
Publisher: Society for Underwater Technology
ISSN: 1756-0543
DOI / ID Number: 10.3723/ut.36.029
Copyright Information:

Copyright 2019. Society for Underwater Technology. This article is Open Access under the terms of the Creative Commons Attribution 4.0 International (CC BY 4.0) licence. (https://creativecommons.org/licenses/by/4.0/)

Related URLs:
Item Statistics: View statistics for this item

Actions (login required)

Item Control Page Item Control Page
TOP