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.

Ship path planning is one of the key technologies for ship automation. Establishing a cooperative collision avoidance (CA) path for multi-ship encounters is of great value to maritime intelligent transportation. This study aims to solve the problem of multi-ship collaborative collision avoidance based on the algorithm of Conflict Search (CS) and Space-Time Hybrid A-star (STHA). First, a static CA path is searched for each ship by using the space-time Hybrid A-star algorithm, and the conflict risk area is determined according to the ship safety distance constraint and fuzzy Collision Risk Index (CRI). Secondly, the space-time conflict constraint is introduced into the multi-ship cooperative CA scheme, and the binary tree is used to search for an optimal navigation path with no conflict and low cost. In addition, the optimal path is smoothed by using cubic interpolation to make the path consistent with actual navigation practice and ship maneuvering characteristics. Finally, considering the constraints of the International Regulations for Preventing Collisions at Sea (COLREGs), the typical two-ship and multi-ship encounter scenarios are designed and simulated to verify the effectiveness of the proposed method. Furthermore, a comparative analysis of actual encounters and encounters based on CS-STHA is also carried out. The results indicate that the proposed algorithm in the study can obtain an optimal CA path effectively and provide a reference of CA decision-making for autonomous ships.

An uncertainty analysis is required to be carried out in formal safety assessment (FSA) by the International Maritime Organization. The purpose of this article is to introduce the uncertainty analysis technique into the FSA process. Based on the uncertainty identification of input parameters, probability and possibility distributions are used to model the aleatory and epistemic uncertainties, respectively. An approach which combines the Monte Carlo random sampling of probability distribution functions with the a-cuts for fuzzy calculus is proposed to propagate the uncertainties. One output of the FSA process is societal risk (SR), which can be evaluated in the two-dimensional frequency–fatality (FN) diagram. Thus, the confidence-level-based SR is presented to represent the uncertainty of SR in two dimensions. In addition, a method for time window selection is proposed to estimate the magnitude of uncertainties, which is an important aspect of modeling uncertainties. Finally, a case study is carried out on an FSA study on cruise ships. The results show that the uncertainty analysis of SR generates a two-dimensional area for a certain degree of confidence in the FN diagram rather than a single FN curve, which provides more information to authorities to produce effective risk control measures.

With the increasing volume of ship traffic, maritime traffic safety is facing a great challenge because the traffic in port becomes more and more crowded and complicated, which will make ship collisions more likely to happen. As a special water area of the port, the anchorage is also threatened by collision risk all the time. For accurately assessing the collision risk in anchorage and its adjacent waters in real time, this paper proposed an analytic model based on Automatic Identification System (AIS) data. The proposed anchorage collision risk model was established in microscopic, macroscopic, and complexity aspects, which considered ship relative motion, anchorage characteristics, and ship traffic complexity, respectively. For validation, the AIS data of the anchorages near the Shandong Peninsular were used to carry out a series of experiments. The results show that the proposed model can identify the anchorage collision risk effectively and has an advantage in dealing with complicated scenarios. The proposed anchorage collision risk model can help maritime surveillance better monitor and organize the ship traffic near the port and provide mariners with a reference about the collision risk situation of the anchorage on their route, which are important to improving maritime traffic safety.

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.