Research on Ship Collision Avoidance Decision-Making Based on AVOA-SA and COLREGs

With the rapid development of the shipping industry, the collision risk among ships in open waters has been steadily increasing, making effective multi-ship collision avoidance decision-making a critical issue for ensuring navigational safety. This paper proposes a multi-ship collision avoidance decision-making method based on the COLREGs. First, a fuzzy comprehensive evaluation method is used to construct a collision risk index model. Then, considering navigational safety, COLREG compliance, turning amplitude, and path economy, an objective function for ship collision avoidance is formulated. Next, the AVOA is improved by incorporating SA to simulate the foraging and navigation behavior of vultures. The Metropolis acceptance criterion is applied to help the algorithm escape local optima and enhance global search capabilities. Experiments conducted in the VSC simulation environment show that the proposed method significantly improves decision-making performance in multi-ship encounter scenarios compared to the standard AVOA.