Data-Driven Strategies for Coping with Incomplete DVL Measurements

Nadav Cohen, Itzik Klein

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Autonomous underwater vehicles are specialized platforms engineered for deep underwater operations. Critical to their functionality is autonomous navigation, typically relying on an inertial navigation system and a Doppler velocity log. In real-world scenarios, incomplete Doppler velocity log measurements occur, resulting in positioning errors and mission aborts. To cope with such situations, a model and learning approaches were derived. This paper presents a comparative analysis of two cutting-edge deep learning methodologies, namely LiBeamsNet and MissBeamNet, alongside a model-based average estimator. These approaches are evaluated for their efficacy in regressing missing Doppler velocity log beams when two beams are unavailable. In our study, we used data recorded by a DVL mounted on an autonomous underwater vehicle operated in the Mediterranean Sea. We found that both deep learning architectures outperformed model-based approaches by over 16% in velocity prediction accuracy.

Original languageEnglish
Title of host publicationOCEANS 2024 - Singapore, OCEANS 2024
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798350362077
DOIs
StatePublished - 2024
EventOCEANS 2024 - Singapore, OCEANS 2024 - Singapore, Singapore
Duration: 15 Apr 202418 Apr 2024

Publication series

NameOceans Conference Record (IEEE)
ISSN (Print)0197-7385

Conference

ConferenceOCEANS 2024 - Singapore, OCEANS 2024
Country/TerritorySingapore
CitySingapore
Period15/04/2418/04/24

Bibliographical note

Publisher Copyright:
© 2024 IEEE.

Keywords

  • Autonomous underwater vehicle (AUV)
  • Deep Learning
  • Doppler velocity log (DVL)

ASJC Scopus subject areas

  • Oceanography
  • Ocean Engineering

Fingerprint

Dive into the research topics of 'Data-Driven Strategies for Coping with Incomplete DVL Measurements'. Together they form a unique fingerprint.

Cite this