Autonomous decision-making for ships to avoid collision is core to the autonomous navigation of intelligent ships. In recent years, related research has shown explosive growth. However, owing to the complex constraints of navigation environments, the Convention of the International Regulations for Preventing Collisions at Sea, 1972 (COLREGs), and the underactuated characteristics of ships, it is extremely challenging to design a decision-making algorithm for autonomous collision avoidance (CA) that is practically useful. Based on the investigation of many studies, current decision-making algorithms can be attributed to three strategies: alteration of course alone, alteration of speed alone, and alteration of both course and speed. This study discusses the implementation methods of each strategy in detail and compares the specific ways, applicable scenes, and limiting conditions of these methods to achieve alteration of course and/or speed to avoid collision, especially their advantages and disadvantages. Additionally, this study quantitatively analyzes the coupling mechanisms of alterations of course and speed for autonomous CA decision-making under different encounter situations, supplementing and optimizing the decision-making theory for ship autonomous CA. Finally, several feasible algorithms and improvement schemes for autonomous CA decision-making, combined with course and speed alterations, are discussed.

Accurate detection of sea-surface objects is vital for the safe navigation of autonomous ships. With the continuous development of artificial intelligence, electro-optical (EO) sensors such as video cameras are used to supplement marine radar to improve the detection of objects that produce weak radar signals and small sizes. In this study, we propose an enhanced convolutional neural network (CNN) named VarifocalNet * that improves object detection in harsh maritime environments. Specifically, the feature representation and learning ability of the VarifocalNet model are improved by using a deformable convolution module, redesigning the loss function, introducing a soft non-maximum suppression algorithm, and incorporating multi-scale prediction methods. These strategies improve the accuracy and reliability of our CNN-based detection results under complex sea conditions, such as in turbulent waves, sea fog, and water reflection. Experimental results under different maritime conditions show that our method significantly outperforms similar methods (such as SSD, YOLOv3, RetinaNet, Faster R-CNN, Cascade R-CNN) in terms of the detection accuracy and robustness for small objects. The maritime obstacle detection results were obtained under harsh imaging conditions to demonstrate the performance of our network model.

A two-fluid, phase transition-based multiphase flow model is employed to simulate the dynamics of phase transition between liquid and vapor phases during shock wave and rarefaction wave propagation in underwater explosions. The aim is to understand the influence of a rigid wall on the cavitation evolution process and the cavitation collapse load, considering various charge quantities and water depths. The evolution of crucial physical qualities, such as the density, pressure, and the cavitation domain, within the flow field are analyzed and summarized. The presence of a rigid wall is found to significantly impact the cavitation evolution process in underwater explosions. It affects the shape, size, and dynamics of the cavitation domain, as well as the interaction between the explosion and the surrounding fluid. Specifically, the reflected wave on the wall influences the cavitation collapse load, leading to notable differences in the collapse time and collapse pressure compared to free-field conditions. Under different operating conditions, the size and position of the cavitation domain exhibit distinct changes. The proximity of the rigid wall results in unique patterns of cavitation domain evolution, which in turn lead to variations in the pressure distribution and the emergence of new cavitation regions. The findings of this study provide valuable insights into the behavior of cavitation and atomization induced by underwater explosions near the free surface. The understanding gained from these investigations can contribute to the development of effective safety measures and protective strategies in marine and underwater engineering applications. By accurately predicting and mitigating the effects of cavitation, it is possible to enhance the design and operation of underwater structures, ensuring their integrity and minimizing the potential risks associated with underwater explosions.