Research Repository

Autonomous Ship Collision Avoidance Navigation Concepts, Technologies and Techniques

Statheros, Thomas and Howells, Gareth and McDonald-Maier, Klaus (2008) 'Autonomous Ship Collision Avoidance Navigation Concepts, Technologies and Techniques.' Journal of Navigation, 61 (01). pp. 129-142. ISSN 0373-4633

Full text not available from this repository.

Abstract

This study provides both a spherical understanding about autonomous ship navigation for collision avoidance (CA) and a theoretical background of the reviewed work. Additionally, the human cognitive abilities and the collision avoidance regulations (COLREGs) for ship navigation are examined together with water based collision avoidance algorithms. The requirements for autonomous ship navigation are addressed in conjunction with the factors influencing ship collision avoidance. Humans are able to appreciate these factors and also perform ship navigation at a satisfactory level, but their critical decisions are highly subjective and can lead to error and potentially, to ship collision. The research for autonomous ship navigation may be grouped into the classical and soft computing based categories. Classical techniques are based on mathematical models and algorithms while soft-computing techniques are based on Artificial Intelligence (AI). The areas of AI for autonomous ship collision avoidance are examined in this paper are evolutionary algorithms, fuzzy logic, expert systems, and neural networks (NN), as well as a combination of them (hybrid system).

Item Type: Article
Uncontrolled Keywords: Autonomous ship; collision avoidance; navigation factors; COLREGs
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Faculty of Science and Health
Faculty of Science and Health > Computer Science and Electronic Engineering, School of
SWORD Depositor: Elements
Depositing User: Elements
Date Deposited: 18 Sep 2013 19:47
Last Modified: 15 Jan 2022 00:54
URI: http://repository.essex.ac.uk/id/eprint/6872

Actions (login required)

View Item View Item