A study on path optimization method of an unmanned surface vehicle under environmental loads using genetic algorithm

Setting a path is essential for reaching a target point and avoiding obstacles in the autonomous navigation system for an unmanned surface vehicle (USV). Accordingly, a decision algorithm for determining an optimized path, considering ocean environmental loads, is necessary. In this study, a genetic algorithm was used to determine the optimized path with the minimum travel time for a USV under environmental loads. The optimized paths were determined using numerical simulations. First, the path of the vessel under environmental loads was expressed using chromosomes consisting of the turning angle of the vessel per unit time. In the configuration of the decision algorithm, the following three objective functions were derived: avoiding obstacles, reaching a target point, and minimizing travel time. By integrating the three objective functions, a new fitness function was proposed. In addition, to determine the optimized path, the fitness evaluation of each chromosome was repeated for all generations using the fitness function. Using the proposed algorithm, the optimized paths were determined considering environmental loads and the allowed minimum distance of approach to an obstacle, and validated using numerical simulations.