Abstract

2019 Innovations in Intelligent Systems and Applications Conference, ASYU 2019 -- 31 October 2019 through 2 November 2019 -- -- 156545 Navigators expect to feel comfortable while passing a ship and an obstacle at sea. This feeling has led to reveal the concept of ship domain. The ship domain is one of the criteria for navigational risk assessment and one of the parameters used in collision avoidance planning and traffic engineering at sea. Generally, navigators determine the domain size by experience, and they form it as a circle in practice. This is because it is called a fully subjective and imprecise value. Although elliptical and circle ship domains are mostly proposed, there have been some complex ship domains such as hexagonal, polygonal, etc. The methods and models to form a ship domain in the related literature are mainly based on analytical, statistical and artificial intelligence methods. In this study, a novel fuzzy rule-based approach has been proposed to determine an asymmetrical polygonal ship domain. The proposed domain is assumed to be around the own ship and its size and shape depend on the directions according to various parameters such as ship length, ship speed, maneuverability, traffic state, navigator experience, day time (daylight or night), sea state, visibility and relative bearing of the target ship (TS). A C# application based on fuzzy inference system (FIS) with Mamdani model has been implemented to form the size and shape of the domain. The logical implication rules used by navigators define the fuzzy domain. In conclusion, it is thought that the proposed model will undoubtedly contribute to the path planning, collision avoidance optimization, ship traffic engineering, and ship motion control. © 2019 IEEE.

Abstract