Ship collisions often result in huge losses of life, cargo and ships, as well as serious pollution of the water environment. Meanwhile, it is estimated that between 75% and 86% of maritime accidents are related to human factors. Thus, it is necessary to enhance the intelligence of ships to partially or fully replace the traditional piloting mode and eventually achieve autonomous collision avoidance to reduce the influence of human factors. In this paper, we propose a multi-ship automatic collision avoidance method based on a double deep Q network (DDQN) with prioritized experience replay. Firstly, we vectorize the predicted hazardous areas as the observation states of the agent so that similar ship encounter scenarios can be clustered and the input dimension of the neural network can be fixed. The reward function is designed based on the International Regulations for Preventing Collision at Sea (COLREGs) and human experience. Different from the architecture of previous collision avoidance methods based on deep reinforcement learning (DRL), in this paper, the interaction between the agent and the environment occurs only in the collision avoidance decision-making phase, which greatly reduces the number of state transitions in the Markov decision process (MDP). The prioritized experience replay method is also used to make the model converge more quickly. Finally, 19 single-vessel collision avoidance scenarios were constructed based on the encounter situations classified by the COLREGs, which were arranged and combined as the training set for the agent. The effectiveness of the proposed method in close-quarters situation was verified using the Imazu problem. The simulation results show that the method can achieve multi-ship collision avoidance in crowded waters, and the decisions generated by this method conform to the COLREGs and are close to the level of human ship handling.

Ship collision avoidance has always been one of the classic topics in the field of marine research. In traditional encounter situations, officers on watch (OOWs) usually use a very high frequency (VHF) radio to coordinate each other. In recent years, with the continuous development of autonomous ships, there will be a mixed situation where ships of different levels of autonomy coexist at the same time. Under such a scenario, different decision makers have different perceptions of the current scene and different decision-making logic, so conventional collision avoidance methods may not be applicable. Therefore, this paper proposes a collaborative collision avoidance strategy for multi-ship collision avoidance under mixed scenarios. It builds a multi-ship cooperative network to determine cooperative objects and timing, at the same time. Based on a cooperative game model, a global collision avoidance responsibility distribution that satisfies group rationality and individual rationality is realised, and finally achieves a collaborative strategy according to the generalised reciprocal velocity obstacle (GRVO) algorithm. Case studies show that the strategy proposed in this paper can make all ships pass each other clearly and safely.

To identify and screen the risk scenarios for the navigation risk of intelligent ships, the analysis and evaluation of navigational risks were performed in this study. Risk scenarios were developed and evaluated by mapping the hierarchical holographic modeling (HHM) into risk filtering, ranking and management (RFRM). In detail, considering the insignificant influences of some factors on navigational activities, risk factors were filtered and ranked using the RFRM model. Seven final factors were successfully determined, including traffic flow, navigation environment understanding, ship–shore interaction capabilities, target recognition capabilities, communication equipment reliabilities, professional skills, and situation judgments. The results indicated that cargo security can be guaranteed by following navigational risk identification and screening steps, and thus our findings provide theoretical guidance for the dynamic management of maritime organizations and ship companies. In addition, the proposed methodology is desirable for making predictions on maritime traffic risks.

Large ships are typically with large inertia and longtime delay in motion, in prevailing collision avoidance methods, their maneuverability is generally neglected, there could be a dangerous situation if the system fails to control the ship course as ordered in a timely manner. This paper proposes a coordination system which consists of two algorithms for avoiding risk and then returning to scheduled waypoint. The avoiding risk algorithm are based on VO (velocity obstacle) method, the returning algorithm is derived from LOS (light of sight) guidance. For better performance, the ship model for simulation is a nonlinear Norrbin Model, with the controller improved by CGSA (closed loop gain shaping algorithm) method from traditional PID control, COLREGS (Convention on the International Regulations for Preventing Collisions at Sea) constrains are considered. To test the effectiveness of the proposed system, a series of complex scenarios including Imazu problem are applied.

An autonomous ship refers to a ship that achieves autonomous operation in ship navigation, management, maintenance, cargo transportation and other aspects. Due to the uncertainty in the risks posed by autonomous ship navigation, its risk assessment attracts great attention from researchers. By analyzing the historical accident statistics, this paper gives a comprehensive analysis from the perspective of “Man-Ship-Environment-Management”. In addition, a quantitative evaluation method based on the Entropy–TOPSIS–Coupling coordination model is proposed, which presents a comprehensive assessment of the risks of autonomous ship navigation safety. Furthermore, scientific forecasts and suggestions for improvement are put forward according to the evaluation results.