Intent inference of ship maneuvering for automatic ship collision avoidance

Abstract

This study addresses the intent inference of ship maneuvering with the consideration of the international regulations on marine traffic for preventing collisions at sea and its application to automatic ship collision avoidance. By assuming that the surrounding ship may or may not always follow the rules, the proposed method provides a decision-making procedure for safe navigation by predicting the maneuvering intent of traffic ships. A probabilistic approach based on a graphical model consisting of the maneuvering intent and evolution of system states is formulated and presented. To demonstrate and verify the feasibility of the proposed approach as an application of automatic ship collision avoidance, ship traffic simulations were conducted and the obtained results are provided and discussed.