Autonomous ship collision avoidance navigation concepts, technologies and techniques

Thomas Statheros, Gareth Howells, Klaus McDonald-Maier

Research output: Contribution to journalArticlepeer-review

234 Citations (Scopus)


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).

Original languageEnglish
Pages (from-to)129-142
Number of pages14
JournalJournal of Navigation
Issue number1
Early online date10 Dec 2007
Publication statusPublished - 1 Jan 2008
Externally publishedYes


  • Autonomous ship
  • Collision avoidance
  • Navigation factors

ASJC Scopus subject areas

  • Oceanography
  • Ocean Engineering


Dive into the research topics of 'Autonomous ship collision avoidance navigation concepts, technologies and techniques'. Together they form a unique fingerprint.

Cite this