Unmanned surface vessel (USV) autonomous navigation on the open sea involving real-time path planning and collision avoidance is still one of the essential problems to ensure the USV’s safe and efficient navigation. Especially in a congested and uncertain marine traffic environment, not only will static obstacles be taken into account but other target vessels in motion should also be considered. Also, the general requirement of the Convention on the International Regulations for Preventing Collisions at Sea (COLREGs) should be satisfied. Hence, an improved A-star algorithm for USV path planning and improved dynamic window approach (IDWA) for collision avoidance were proposed. First, considering the requirement of COLREGs, the velocity search space was filtered again, and the quantity of USV trajectories was reduced. Then, the improved A-star algorithm was introduced to let the USV avoid static obstacles and reach its destination without trapping in local optimization. Moreover the Deep Q-network method was utilized to train weight coefficients of the IDWA objective function. Thereby, the improved algorithm-generated path during the process of collision avoidance was more reasonable and safer. To verify feasibility of the proposed path-planning algorithm, a comparison experiment with the traditional DWA method was carried out. The results showed that whether it was for a single USV to a single target or for multiple USVs to multiple targets, path planning, the proposed method, could work effectively to avoid obstacles safely and reach the destination quickly. The improved algorithm will be expected to provide a reference for USV path planning and collision avoidance as well as contribute to the implementation of autonomous ship navigation.

The congestion of waterways can easily lead to traffic hazards. Moreover, according to the data, the majority of sea collisions are caused by human error and the failure to comply with the Convention on the International Regulation for the preventing Collision at Sea (COLREGs). To avoid this situation, ship automatic collision avoidance has become one of the most important research issues in the field of marine engineering. In this study, an efficient method is proposed to solve multi-ship collision avoidance problems based on the multi-agent reinforcement learning (MARL) algorithm. Firstly, the COLREGs and ship maneuverability are considered for achieving multi-ship collision avoidance. Subsequently, the Optimal Reciprocal Collision Avoidance (ORCA) algorithm is utilized to detect and reduce the risk of collision. Ships can operate at the safe velocity computed by the ORCA algorithm to avoid collisions. Finally, the Nomoto three-degrees-of-freedom (3-DOF) model is used to simulate the maneuvers of ships. According to the above information and algorithms, this study designs and improves the state space, action space and reward function. For validating the effectiveness of the method, this study designs various simulation scenarios with thorough performance evaluations. The simulation results indicate that the proposed method is flexible and scalable in solving multi-ship collision avoidance, complying with COLREGs in various scenarios.

The China–Australia Route, which serves as the southern economic corridor of the ‘21st Century Maritime Silk Road’, bears great importance in safeguarding maritime transportation operations. This route plays a crucial role in ensuring the security and efficiency of such activities. To pre-assess the risks of this route, this paper presents a two-stage analytical framework that combines fault tree analysis and Bayesian network for evaluating the occurrence likelihood of risk of transporting liquefied natural gas (LNG) on the China–Australia Route. In the first stage, our study involved the identification of 22 risk influencing factors drawn from a comprehensive review of pertinent literature and an in-depth analysis of accident reports. These identified factors were then utilized as basic events to construct a fault tree. Later, we applied an expert comprehensive evaluation method and fuzzy set theory, and by introducing voting mechanism into expert opinions, the prior probability of basic events was calculated. In the second stage, a fault tree was transformed into a Bayesian network, which overcame the deficiency that the structure and conditional probability table of the Bayesian network find difficult to determine. Consequently, the employment of the Bayesian network architecture was applied to forecast the likelihood of LNG maritime transport along the China–Australia shipping pathway. The probability importance and critical importance of each basic event was calculated through an importance analysis. The development of a risk matrix was achieved by considering the two primary dimensions of frequency and impact, which were subsequently utilized to categorize all relevant risk factors into high, moderate, or low risk categories. This allowed for effective risk mitigation and prevention strategies to be implemented. Finally, assuming that the final risk occurs, we calculated the posterior probability of the basic event to diagnose the risk. The research findings indicate that the primary reasons for the risk of transporting LNG on the China–Australia Route are the impact of natural forces and epidemics, piracy and terrorist attacks, and the risk of LNG explosions. In the final section, we provide suggestions and risk control measures based on the research results to reduce the occurrence of risks.