Outlook for Navigation - Comparing Human Performance with a Robotic Solution

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedings – Annual report year: 2019Researchpeer-review

Documents

View graph of relations

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

    Research areas

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

Download statistics

No data available

ID: 179154452