Method for Collision Avoidance by USV Based on Improved Genetic Algorithm

Abstract

This paper proposes a method for collision avoidance by unmanned surface vehicle (USV) based on improved genetic algorithm. For the complex marine environment in which static and dynamic obstacles are densely covered, we establish models of the USV system. When the USV encounters dynamic obstacles, we divide scenarios involving encounters and design corresponding collision avoidance strategies; and calculate the motion parameters and risk of collision to determine whether to start collision avoidance. Following this, we improve the genetic algorithm through retention, deletion, and replacement, use the analytic hierarchy process to build the fitness, iteratively optimize the acceleration and yaw rate, and calculate the optimal path for collision avoidance for USV. Finally, we built a simulation platform for USV collision avoidance to verify the proposed method. The results show that the proposed method can be used for the safe operation of USV.