Vision-based localization system suited to resident underwater vehicles

Petar Trslic*, Anthony Weir, James Riordan, Edin Omerdic, Daniel Toal, Gerard Dooly

*Corresponding author for this work

Research output: Contribution to journalArticle

4 Downloads (Pure)

Abstract

In recent years, we have seen significant interest in the use of permanently deployed resident robotic vehicles for commercial inspection, maintenance and repair (IMR) activities. This paper presents a concept and demonstration, through offshore trials, of a low-cost, low-maintenance, navigational marker that can eliminate drift in vehicle INS solution when the vehicle is close to the IMR target. The subsea localisation marker system is fixed on location on the resident field asset and is used in on-vehicle machine vision algorithms for pose estimation and facilitation of a high-resolution world coordinate frame registration with a high refresh rate. This paper presents evaluation of the system during trials in the North Atlantic Ocean during January 2019. System performances and propagation of position error is inspected and estimated, and the effect of intermittent visual based position update to Kalman filter and onboard INS solution is discussed. The paper presents experimental results of the commercial state-of-the-art inertial navigation system operating in the pure inertial mode for comparison.
Original languageEnglish
Article number529
Number of pages20
JournalSensors
Volume20
Issue number2
DOIs
Publication statusPublished - 18 Jan 2020

Fingerprint

underwater vehicles
vehicles
Maintenance
maintenance
Atlantic Ocean
markers
inspection
Repair
Inspection
Robotics
inertial navigation
position errors
Inertial navigation systems
computer vision
Kalman filters
robotics
Computer vision
Costs and Cost Analysis
Demonstrations
propagation

Keywords

  • Resident UUVs
  • Localization
  • Subsea navigation

Cite this

Trslic, P., Weir, A., Riordan, J., Omerdic, E., Toal, D., & Dooly, G. (2020). Vision-based localization system suited to resident underwater vehicles. Sensors, 20(2), [529]. https://doi.org/10.3390/s20020529
Trslic, Petar ; Weir, Anthony ; Riordan, James ; Omerdic, Edin ; Toal, Daniel ; Dooly, Gerard. / Vision-based localization system suited to resident underwater vehicles. In: Sensors. 2020 ; Vol. 20, No. 2.
@article{176c57bdfe20461bb3910a7e90d697e9,
title = "Vision-based localization system suited to resident underwater vehicles",
abstract = "In recent years, we have seen significant interest in the use of permanently deployed resident robotic vehicles for commercial inspection, maintenance and repair (IMR) activities. This paper presents a concept and demonstration, through offshore trials, of a low-cost, low-maintenance, navigational marker that can eliminate drift in vehicle INS solution when the vehicle is close to the IMR target. The subsea localisation marker system is fixed on location on the resident field asset and is used in on-vehicle machine vision algorithms for pose estimation and facilitation of a high-resolution world coordinate frame registration with a high refresh rate. This paper presents evaluation of the system during trials in the North Atlantic Ocean during January 2019. System performances and propagation of position error is inspected and estimated, and the effect of intermittent visual based position update to Kalman filter and onboard INS solution is discussed. The paper presents experimental results of the commercial state-of-the-art inertial navigation system operating in the pure inertial mode for comparison.",
keywords = "Resident UUVs, Localization, Subsea navigation",
author = "Petar Trslic and Anthony Weir and James Riordan and Edin Omerdic and Daniel Toal and Gerard Dooly",
year = "2020",
month = "1",
day = "18",
doi = "10.3390/s20020529",
language = "English",
volume = "20",
journal = "Sensors",
issn = "1424-8220",
publisher = "Multidisciplinary Digital Publishing Institute",
number = "2",

}

Trslic, P, Weir, A, Riordan, J, Omerdic, E, Toal, D & Dooly, G 2020, 'Vision-based localization system suited to resident underwater vehicles', Sensors, vol. 20, no. 2, 529. https://doi.org/10.3390/s20020529

Vision-based localization system suited to resident underwater vehicles. / Trslic, Petar ; Weir, Anthony; Riordan, James; Omerdic, Edin; Toal, Daniel; Dooly, Gerard.

In: Sensors, Vol. 20, No. 2, 529, 18.01.2020.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Vision-based localization system suited to resident underwater vehicles

AU - Trslic, Petar

AU - Weir, Anthony

AU - Riordan, James

AU - Omerdic, Edin

AU - Toal, Daniel

AU - Dooly, Gerard

PY - 2020/1/18

Y1 - 2020/1/18

N2 - In recent years, we have seen significant interest in the use of permanently deployed resident robotic vehicles for commercial inspection, maintenance and repair (IMR) activities. This paper presents a concept and demonstration, through offshore trials, of a low-cost, low-maintenance, navigational marker that can eliminate drift in vehicle INS solution when the vehicle is close to the IMR target. The subsea localisation marker system is fixed on location on the resident field asset and is used in on-vehicle machine vision algorithms for pose estimation and facilitation of a high-resolution world coordinate frame registration with a high refresh rate. This paper presents evaluation of the system during trials in the North Atlantic Ocean during January 2019. System performances and propagation of position error is inspected and estimated, and the effect of intermittent visual based position update to Kalman filter and onboard INS solution is discussed. The paper presents experimental results of the commercial state-of-the-art inertial navigation system operating in the pure inertial mode for comparison.

AB - In recent years, we have seen significant interest in the use of permanently deployed resident robotic vehicles for commercial inspection, maintenance and repair (IMR) activities. This paper presents a concept and demonstration, through offshore trials, of a low-cost, low-maintenance, navigational marker that can eliminate drift in vehicle INS solution when the vehicle is close to the IMR target. The subsea localisation marker system is fixed on location on the resident field asset and is used in on-vehicle machine vision algorithms for pose estimation and facilitation of a high-resolution world coordinate frame registration with a high refresh rate. This paper presents evaluation of the system during trials in the North Atlantic Ocean during January 2019. System performances and propagation of position error is inspected and estimated, and the effect of intermittent visual based position update to Kalman filter and onboard INS solution is discussed. The paper presents experimental results of the commercial state-of-the-art inertial navigation system operating in the pure inertial mode for comparison.

KW - Resident UUVs

KW - Localization

KW - Subsea navigation

U2 - 10.3390/s20020529

DO - 10.3390/s20020529

M3 - Article

VL - 20

JO - Sensors

JF - Sensors

SN - 1424-8220

IS - 2

M1 - 529

ER -