Outlook for Navigation - Comparing Human Performance with a Robotic Solution

Mogens Blanke*, Søren Hansen, Jonathan Dyssel Stets, T. Koester, J. E. Brøsted, Adrian Llopart Maurin, Nicolai Nykvist, J. Bang

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

71 Downloads (Pure)

Abstract

Considering whether a temporarily unattended bridge could be allowed, Maritime Authorities wish to investigate whether sensor technology is available that, when seconded by sophisticated computer algorithms, is able to provide outlook with the same reliability and safety as that of the average human outlook. This paper reports findings from a comparative study of human versus electronic outlook. Assessment of navigator’s outlook is based on measurements with a wearable eye-tracker and areas of their visual attention are recorded on video. Simultaneously, a set of electro-optical sensors provides image-data as input to computer algorithms that detect and classify objects at sea within visual range. The paper presents the methodology used to deduct, from the observations of fixations, when the navigator turned his attention to a particular object and compares this with the Electronic Outlook. On the technology side, the paper details on how machine learning is used for object detection and classification, an discusses quality attributes, including efficiency and robustness of detection and classification, expressed through statistical measures.
Original languageEnglish
Title of host publicationICMASS 2018. Proceedings of the 1st International Conference on Maritime Autonomous Surface Ships
Number of pages9
PublisherSINTEF
Publication date2019
ISBN (Print)978-82-536-1628-5
Publication statusPublished - 2019
EventInternational Conference on Maritime Autonomous Surface Ships - Busan Exhibition and Convention Center, Busan, Korea, Republic of
Duration: 8 Nov 20189 Nov 2018

Conference

ConferenceInternational Conference on Maritime Autonomous Surface Ships
LocationBusan Exhibition and Convention Center
CountryKorea, Republic of
CityBusan
Period08/11/201809/11/2018

Keywords

  • Outlook for navigation
  • Autonomous vessels
  • Electronic outlook
  • Human outlook

Cite this

Blanke, M., Hansen, S., Stets, J. D., Koester, T., Brøsted, J. E., Maurin, A. L., ... Bang, J. (2019). Outlook for Navigation - Comparing Human Performance with a Robotic Solution. In ICMASS 2018. Proceedings of the 1st International Conference on Maritime Autonomous Surface Ships SINTEF.
Blanke, Mogens ; Hansen, Søren ; Stets, Jonathan Dyssel ; Koester, T. ; Brøsted, J. E. ; Maurin, Adrian Llopart ; Nykvist, Nicolai ; Bang, J. / Outlook for Navigation - Comparing Human Performance with a Robotic Solution. ICMASS 2018. Proceedings of the 1st International Conference on Maritime Autonomous Surface Ships. SINTEF, 2019.
@inproceedings{a657c5290ca74e77ae324eb8b7f18a56,
title = "Outlook for Navigation - Comparing Human Performance with a Robotic Solution",
abstract = "Considering whether a temporarily unattended bridge could be allowed, Maritime Authorities wish to investigate whether sensor technology is available that, when seconded by sophisticated computer algorithms, is able to provide outlook with the same reliability and safety as that of the average human outlook. This paper reports findings from a comparative study of human versus electronic outlook. Assessment of navigator’s outlook is based on measurements with a wearable eye-tracker and areas of their visual attention are recorded on video. Simultaneously, a set of electro-optical sensors provides image-data as input to computer algorithms that detect and classify objects at sea within visual range. The paper presents the methodology used to deduct, from the observations of fixations, when the navigator turned his attention to a particular object and compares this with the Electronic Outlook. On the technology side, the paper details on how machine learning is used for object detection and classification, an discusses quality attributes, including efficiency and robustness of detection and classification, expressed through statistical measures.",
keywords = "Outlook for navigation, Autonomous vessels, Electronic outlook, Human outlook",
author = "Mogens Blanke and S{\o}ren Hansen and Stets, {Jonathan Dyssel} and T. Koester and Br{\o}sted, {J. E.} and Maurin, {Adrian Llopart} and Nicolai Nykvist and J. Bang",
year = "2019",
language = "English",
isbn = "978-82-536-1628-5",
booktitle = "ICMASS 2018. Proceedings of the 1st International Conference on Maritime Autonomous Surface Ships",
publisher = "SINTEF",

}

Blanke, M, Hansen, S, Stets, JD, Koester, T, Brøsted, JE, Maurin, AL, Nykvist, N & Bang, J 2019, Outlook for Navigation - Comparing Human Performance with a Robotic Solution. in ICMASS 2018. Proceedings of the 1st International Conference on Maritime Autonomous Surface Ships. SINTEF, International Conference on Maritime Autonomous Surface Ships, Busan, Korea, Republic of, 08/11/2018.

Outlook for Navigation - Comparing Human Performance with a Robotic Solution. / Blanke, Mogens; Hansen, Søren; Stets, Jonathan Dyssel; Koester, T. ; Brøsted, J. E. ; Maurin, Adrian Llopart; Nykvist, Nicolai; Bang, J.

ICMASS 2018. Proceedings of the 1st International Conference on Maritime Autonomous Surface Ships. SINTEF, 2019.

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

TY - GEN

T1 - Outlook for Navigation - Comparing Human Performance with a Robotic Solution

AU - Blanke, Mogens

AU - Hansen, Søren

AU - Stets, Jonathan Dyssel

AU - Koester, T.

AU - Brøsted, J. E.

AU - Maurin, Adrian Llopart

AU - Nykvist, Nicolai

AU - Bang, J.

PY - 2019

Y1 - 2019

N2 - Considering whether a temporarily unattended bridge could be allowed, Maritime Authorities wish to investigate whether sensor technology is available that, when seconded by sophisticated computer algorithms, is able to provide outlook with the same reliability and safety as that of the average human outlook. This paper reports findings from a comparative study of human versus electronic outlook. Assessment of navigator’s outlook is based on measurements with a wearable eye-tracker and areas of their visual attention are recorded on video. Simultaneously, a set of electro-optical sensors provides image-data as input to computer algorithms that detect and classify objects at sea within visual range. The paper presents the methodology used to deduct, from the observations of fixations, when the navigator turned his attention to a particular object and compares this with the Electronic Outlook. On the technology side, the paper details on how machine learning is used for object detection and classification, an discusses quality attributes, including efficiency and robustness of detection and classification, expressed through statistical measures.

AB - Considering whether a temporarily unattended bridge could be allowed, Maritime Authorities wish to investigate whether sensor technology is available that, when seconded by sophisticated computer algorithms, is able to provide outlook with the same reliability and safety as that of the average human outlook. This paper reports findings from a comparative study of human versus electronic outlook. Assessment of navigator’s outlook is based on measurements with a wearable eye-tracker and areas of their visual attention are recorded on video. Simultaneously, a set of electro-optical sensors provides image-data as input to computer algorithms that detect and classify objects at sea within visual range. The paper presents the methodology used to deduct, from the observations of fixations, when the navigator turned his attention to a particular object and compares this with the Electronic Outlook. On the technology side, the paper details on how machine learning is used for object detection and classification, an discusses quality attributes, including efficiency and robustness of detection and classification, expressed through statistical measures.

KW - Outlook for navigation

KW - Autonomous vessels

KW - Electronic outlook

KW - Human outlook

M3 - Article in proceedings

SN - 978-82-536-1628-5

BT - ICMASS 2018. Proceedings of the 1st International Conference on Maritime Autonomous Surface Ships

PB - SINTEF

ER -

Blanke M, Hansen S, Stets JD, Koester T, Brøsted JE, Maurin AL et al. Outlook for Navigation - Comparing Human Performance with a Robotic Solution. In ICMASS 2018. Proceedings of the 1st International Conference on Maritime Autonomous Surface Ships. SINTEF. 2019