Method for anti-collision path planning using velocity obstacle and A* algorithms for maritime autonomous surface ship

Abstract

With the increasing size of ships and increasing demand for autonomous navigation, ensuring ship safety is not the only concern; the efficiency of anti-collision technology should be enhanced. In this paper, we propose a novel hybrid anti-collision path planning method called VO-PATH. This method combines the advantages of the velocity obstacle (VO) algorithm, which guarantees anti-collision for autonomous ships, with the A* algorithm, which is known for its capacity to optimize paths. To assess the effectiveness of the proposed method, we conducted anti-collision simulations for both single- and multiple-encounter scenarios, all of which adhered to COLREGs-defined avoidance obligations. Furthermore, we evaluated the performance of the proposed method by comparing its results with those obtained using conventional VO and A* algorithms. The findings indicate that the proposed method is superior to the A* algorithm in terms of steering away from collisions in complex multiple-encounter scenarios. Additionally, the proposed method significantly reduces the distance traveled by the ship to avoid potential collisions, with improvements of up to approximately 6.6% compared with alternative algorithms. We expect that this reduction will enhance safety and provide a more efficient anti-collision path.

Topics & Concepts