Ship's trajectory planning for collision avoidance at sea based on modified artificial potential field

Abstract

This paper presents an autonomous trajectory planning algorithm for ships or unmanned surface vehicles (USVs) to navigate safely in dynamic environments based on the modified artificial potential field (APF). The algorithm not only addresses collision avoidance (CA) for stationary and moving hazards, but also applies the International Regulations for Preventing Collisions at Sea (known as COLREGS, for COLlision REGulationS). Furthermore, the algorithm is still effective for the USV to prevent a collision once other ships disregard their responsibility under COLREGS. Assumptions, a concise description of the method developed and results of simulated navigational situations are included. The developed solution can be applied in decision support systems on board a ship or in an intelligent Obstacle Detection and Avoidance system.