Automatic collision avoidance decision making for vessels is a critical challenge in the development of autonomous ships and has become a central point of research in the maritime safety domain. Effective and systematic collision avoidance strategies significantly reduce the risk of vessel collisions, ensuring safe navigation. This study develops a multi-vessel automatic collision avoidance decision-making method based on deep reinforcement learning (DRL) and establishes a vessel behavior decision model. When designing the reward function for continuous action spaces, the criteria of the “Convention on the International Regulations for Preventing Collisions at Sea” (COLREGs) were adhered to, taking into account the vessel’s collision risk under various encounter situations, real-world navigation practices, and navigational complexities. Furthermore, to enable the algorithm to precisely differentiate between collision avoidance and the navigation resumption phase in varied vessel encounter situations, this paper incorporated “collision avoidance decision making” and “course recovery decision making” as state parameters in the state set design, from which the respective objective functions were defined. To further enhance the algorithm’s performance, techniques such as behavior cloning, residual networks, and CPU-GPU dual-core parallel processing modules were integrated. Through simulation experiments in the enhanced Imazu training environment, the practicality of the method, taking into account the effects of wind and ocean currents, was corroborated. The results demonstrate that the proposed algorithm can perform effective collision avoidance decision making in a range of vessel encounter situations, indicating its efficiency and robust generalization capabilities.

The exploration of ship collision avoidance behavior characteristics can provide a theoretical basis for ship collision risk assessment and collision avoidance decision-making, which is significant for ensuring maritime navigation safety and the development of intelligent ships. In order to scientifically and effectively analyze the characteristics of ship collision-avoidance behavior and to seek the intrinsic connections among ship collision-avoidance behavior feature parameters(CABFPS), this study proposes a method that combines the Apriori algorithm and complex network theory to mine ship collision-avoidance behavior characteristics from massive AIS spatiotemporal data. Based on obtaining ship encounter samples and CABFPS from AIS data, the Apriori algorithm is used to mine the association rules of motion parameters, and the maximum mutual information coefficient is employed to represent the correlation between parameters. Complex networks of CABFPS for different encounter situations are constructed, and network topological indicators are analyzed. Mutual information theory is applied to identify key parameters affecting ship collision- avoidance behavior under different situations. The analysis using actual AIS data indicates that during navigation, the relationships among various parameters are closely linked and prone to mutual influence. The impact of CABFPS on ship collision-avoidance actions varies under different encounter scenarios, with relative distance and DCPA having the greatest influence on ship collision-avoidance actions. This method can comprehensively and accurately mine the correlations between CABFPS and the influence mechanism of parameters on collision-avoidance actions, providing a reference for intelligent ship navigation and the formulation of collision-avoidance decisions.