Scenario-based Testing of a Ship Collision Avoidance System

Ivan Porres; Sepinoud Azimi; Johan Lilius

doi:10.1109/SEAA51224.2020.00090

Scenario-based Testing of a Ship Collision Avoidance System

Ivan Porres, Sepinoud Azimi, Johan Lilius

Research output: Chapter in Book/Conference proceeding › Conference contribution › Scientific › peer-review

16 Citations (Scopus)

Abstract

We propose a method for scenario-based testing of maritime collision avoidance systems. The goal is to test an autonomous agent in scenarios that can lead to an unacceptable risk of collision or may clearly not comply with the International Regulations for Preventing Collisions at Sea (COLREGs).Our method is based on the use of a discriminating artificial neural network that is trained online while performing the testing of the agents. Our experimental results show that the proposed algorithm generates test suits composed mostly of challenging scenarios. This allows us to validate quickly if the agent under test can perform the collision avoidance maneuvers safely while abiding the COLREGs.

Original language	English
Title of host publication	2020 46th Euromicro Conference on Software Engineering and Advanced Applications (SEAA)
Publisher	IEEE
Pages	545-552
ISBN (Electronic)	978-1-7281-9532-2
ISBN (Print)	978-1-7281-9533-9
DOIs	https://doi.org/10.1109/SEAA51224.2020.00090
Publication status	Published - 2020
MoE publication type	A4 Article in a conference publication
Event	Euromicro Conference on Software Engineering and Advanced Applications - Duration: 26 Aug 2020 → …

Conference

Conference	Euromicro Conference on Software Engineering and Advanced Applications
Abbreviated title	SEAA
Period	26/08/20 → …

Access to Document

10.1109/SEAA51224.2020.00090

Cite this

@inproceedings{22ce800ea4da483f99bd2d85355c1620,

title = "Scenario-based Testing of a Ship Collision Avoidance System",

abstract = "We propose a method for scenario-based testing of maritime collision avoidance systems. The goal is to test an autonomous agent in scenarios that can lead to an unacceptable risk of collision or may clearly not comply with the International Regulations for Preventing Collisions at Sea (COLREGs).Our method is based on the use of a discriminating artificial neural network that is trained online while performing the testing of the agents. Our experimental results show that the proposed algorithm generates test suits composed mostly of challenging scenarios. This allows us to validate quickly if the agent under test can perform the collision avoidance maneuvers safely while abiding the COLREGs.",

author = "Ivan Porres and Sepinoud Azimi and Johan Lilius",

note = "DBLP's bibliographic metadata records provided through http://dblp.org/search/publ/api are distributed under a Creative Commons CC0 1.0 Universal Public Domain Dedication. Although the bibliographic metadata records are provided consistent with CC0 1.0 Dedication, the content described by the metadata records is not. Content may be subject to copyright, rights of privacy, rights of publicity and other restrictions.; Euromicro Conference on Software Engineering and Advanced Applications , SEAA ; Conference date: 26-08-2020",

year = "2020",

doi = "10.1109/SEAA51224.2020.00090",

language = "English",

isbn = "978-1-7281-9533-9",

pages = "545--552",

booktitle = "2020 46th Euromicro Conference on Software Engineering and Advanced Applications (SEAA)",

publisher = "IEEE",

}

TY - GEN

T1 - Scenario-based Testing of a Ship Collision Avoidance System

AU - Porres, Ivan

AU - Azimi, Sepinoud

AU - Lilius, Johan

N1 - DBLP's bibliographic metadata records provided through http://dblp.org/search/publ/api are distributed under a Creative Commons CC0 1.0 Universal Public Domain Dedication. Although the bibliographic metadata records are provided consistent with CC0 1.0 Dedication, the content described by the metadata records is not. Content may be subject to copyright, rights of privacy, rights of publicity and other restrictions.

PY - 2020

Y1 - 2020

N2 - We propose a method for scenario-based testing of maritime collision avoidance systems. The goal is to test an autonomous agent in scenarios that can lead to an unacceptable risk of collision or may clearly not comply with the International Regulations for Preventing Collisions at Sea (COLREGs).Our method is based on the use of a discriminating artificial neural network that is trained online while performing the testing of the agents. Our experimental results show that the proposed algorithm generates test suits composed mostly of challenging scenarios. This allows us to validate quickly if the agent under test can perform the collision avoidance maneuvers safely while abiding the COLREGs.

AB - We propose a method for scenario-based testing of maritime collision avoidance systems. The goal is to test an autonomous agent in scenarios that can lead to an unacceptable risk of collision or may clearly not comply with the International Regulations for Preventing Collisions at Sea (COLREGs).Our method is based on the use of a discriminating artificial neural network that is trained online while performing the testing of the agents. Our experimental results show that the proposed algorithm generates test suits composed mostly of challenging scenarios. This allows us to validate quickly if the agent under test can perform the collision avoidance maneuvers safely while abiding the COLREGs.

U2 - 10.1109/SEAA51224.2020.00090

DO - 10.1109/SEAA51224.2020.00090

M3 - Conference contribution

SN - 978-1-7281-9533-9

SP - 545

EP - 552

BT - 2020 46th Euromicro Conference on Software Engineering and Advanced Applications (SEAA)

PB - IEEE

T2 - Euromicro Conference on Software Engineering and Advanced Applications

Y2 - 26 August 2020

ER -

Scenario-based Testing of a Ship Collision Avoidance System

Abstract

Conference

Access to Document

Fingerprint

Cite this