Deep Learning towards Autonomous Ship Navigation and Possible COLREGs Failures
A structured technology framework to address navigation considerations, including collision avoidance, of autonomous ships is the focus of this study. That consists of adequate maritime technologies to achieve the required level of navigation integrity in ocean autonomy. Since decision-making facili...
Published in: | Journal of Offshore Mechanics and Arctic Engineering |
---|---|
Main Author: | |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
American Society of Mechanical Engineers (ASME)
2019
|
Subjects: | |
Online Access: | https://hdl.handle.net/10037/17949 https://doi.org/10.1115/1.4045372 |
id |
ftunivtroemsoe:oai:munin.uit.no:10037/17949 |
---|---|
record_format |
openpolar |
spelling |
ftunivtroemsoe:oai:munin.uit.no:10037/17949 2023-05-15T14:21:49+02:00 Deep Learning towards Autonomous Ship Navigation and Possible COLREGs Failures Perera, Lokukaluge Prasad 2019-12-17 https://hdl.handle.net/10037/17949 https://doi.org/10.1115/1.4045372 eng eng American Society of Mechanical Engineers (ASME) Journal of Offshore Mechanics and Arctic Engineering Perera, L.P. (2019) Deep Learning towards Autonomous Ship Navigation and Possible COLREGs Failures . Journal of Offshore Mechanics and Arctic Engineering, 2019 FRIDAID 1744894 doi:10.1115/1.4045372 0892-7219 1528-896X https://hdl.handle.net/10037/17949 openAccess Copyright © 2019 by ASME VDP::Technology: 500::Marine technology: 580::Offshore technology: 581 VDP::Teknologi: 500::Marin teknologi: 580::Offshoreteknologi: 581 Journal article Tidsskriftartikkel Peer reviewed acceptedVersion 2019 ftunivtroemsoe https://doi.org/10.1115/1.4045372 2021-06-25T17:57:22Z A structured technology framework to address navigation considerations, including collision avoidance, of autonomous ships is the focus of this study. That consists of adequate maritime technologies to achieve the required level of navigation integrity in ocean autonomy. Since decision-making facilities in future autonomous vessels can play an important role under ocean autonomy, these technologies should consist of adequate system intelligence. Such system intelligence should consider localized decision-making modules to facilitate a distributed intelligence type strategy that supports distinct navigation situations in future vessels as agent-based systems. The main core of this agent consists of deep learning type technology that has presented promising results in other transportation systems, i.e., self-driving cars. Deep learning can capture helmsman behavior; therefore, such system intelligence can be used to navigate future autonomous vessels. Furthermore, an additional decision support layer should also be developed to facilitate deep learning-type technologies, where adequate solutions to distinct navigation situations can be facilitated. Collision avoidance under situation awareness, as one of such distinct navigation situations (i.e., a module of the decision support layer), is extensively discussed. Ship collision avoidance is regulated by the Convention on the International Regulations for Preventing Collisions at Sea (COLREGs) under open sea areas. Hence, a general overview of the COLREGs and its implementation challenges, i.e., possible regulatory failures, under situation awareness of autonomous ships is also presented with the possible solutions. Additional considerations, i.e., performance standards with the applicable limits of liability, terms, expectations, and conditions, toward evaluating ship behavior as an agent-based system in collision avoidance situations are also illustrated. Article in Journal/Newspaper Arctic University of Tromsø: Munin Open Research Archive Journal of Offshore Mechanics and Arctic Engineering 142 3 |
institution |
Open Polar |
collection |
University of Tromsø: Munin Open Research Archive |
op_collection_id |
ftunivtroemsoe |
language |
English |
topic |
VDP::Technology: 500::Marine technology: 580::Offshore technology: 581 VDP::Teknologi: 500::Marin teknologi: 580::Offshoreteknologi: 581 |
spellingShingle |
VDP::Technology: 500::Marine technology: 580::Offshore technology: 581 VDP::Teknologi: 500::Marin teknologi: 580::Offshoreteknologi: 581 Perera, Lokukaluge Prasad Deep Learning towards Autonomous Ship Navigation and Possible COLREGs Failures |
topic_facet |
VDP::Technology: 500::Marine technology: 580::Offshore technology: 581 VDP::Teknologi: 500::Marin teknologi: 580::Offshoreteknologi: 581 |
description |
A structured technology framework to address navigation considerations, including collision avoidance, of autonomous ships is the focus of this study. That consists of adequate maritime technologies to achieve the required level of navigation integrity in ocean autonomy. Since decision-making facilities in future autonomous vessels can play an important role under ocean autonomy, these technologies should consist of adequate system intelligence. Such system intelligence should consider localized decision-making modules to facilitate a distributed intelligence type strategy that supports distinct navigation situations in future vessels as agent-based systems. The main core of this agent consists of deep learning type technology that has presented promising results in other transportation systems, i.e., self-driving cars. Deep learning can capture helmsman behavior; therefore, such system intelligence can be used to navigate future autonomous vessels. Furthermore, an additional decision support layer should also be developed to facilitate deep learning-type technologies, where adequate solutions to distinct navigation situations can be facilitated. Collision avoidance under situation awareness, as one of such distinct navigation situations (i.e., a module of the decision support layer), is extensively discussed. Ship collision avoidance is regulated by the Convention on the International Regulations for Preventing Collisions at Sea (COLREGs) under open sea areas. Hence, a general overview of the COLREGs and its implementation challenges, i.e., possible regulatory failures, under situation awareness of autonomous ships is also presented with the possible solutions. Additional considerations, i.e., performance standards with the applicable limits of liability, terms, expectations, and conditions, toward evaluating ship behavior as an agent-based system in collision avoidance situations are also illustrated. |
format |
Article in Journal/Newspaper |
author |
Perera, Lokukaluge Prasad |
author_facet |
Perera, Lokukaluge Prasad |
author_sort |
Perera, Lokukaluge Prasad |
title |
Deep Learning towards Autonomous Ship Navigation and Possible COLREGs Failures |
title_short |
Deep Learning towards Autonomous Ship Navigation and Possible COLREGs Failures |
title_full |
Deep Learning towards Autonomous Ship Navigation and Possible COLREGs Failures |
title_fullStr |
Deep Learning towards Autonomous Ship Navigation and Possible COLREGs Failures |
title_full_unstemmed |
Deep Learning towards Autonomous Ship Navigation and Possible COLREGs Failures |
title_sort |
deep learning towards autonomous ship navigation and possible colregs failures |
publisher |
American Society of Mechanical Engineers (ASME) |
publishDate |
2019 |
url |
https://hdl.handle.net/10037/17949 https://doi.org/10.1115/1.4045372 |
genre |
Arctic |
genre_facet |
Arctic |
op_relation |
Journal of Offshore Mechanics and Arctic Engineering Perera, L.P. (2019) Deep Learning towards Autonomous Ship Navigation and Possible COLREGs Failures . Journal of Offshore Mechanics and Arctic Engineering, 2019 FRIDAID 1744894 doi:10.1115/1.4045372 0892-7219 1528-896X https://hdl.handle.net/10037/17949 |
op_rights |
openAccess Copyright © 2019 by ASME |
op_doi |
https://doi.org/10.1115/1.4045372 |
container_title |
Journal of Offshore Mechanics and Arctic Engineering |
container_volume |
142 |
container_issue |
3 |
_version_ |
1766294522943242240 |