Recognizing the specific complexities of vessel traffic flow, this comprehensive survey exclusively addresses the predictive modeling in maritime transportation, tracing the evolution from conventional statistical approaches to modern artificial intelligence (AI) techniques. The survey examines a broad range of predictive targets, including vessel volume, trajectories, velocities, destinations, and traffic patterns. Through bibliometric analysis utilizing Citespace, the central research themes and technological trends characterizing the vessel traffic flow prediction (VTFP) domain have been identified and discussed. Our analysis indicates a clear trend towards AI-based models, highlighting their increasing dominance in enhancing predictive accuracy and efficiency. Additionally, we highlight persistent challenges, such as the integration of large datasets with traffic flow models and the critical need for real-time data analytics. The survey concludes with insights into the future of VTFP research, emphasizing the potential of hybrid models that combine deep learning with statistical learning that enable more sophisticated predictive analytics to be performed. This review aims to serve as a guide for both academics and practitioners looking to maximize the use of predictive modeling in the maritime traffic sector.

Multi-AUV cooperative hunting requires autonomous underwater vehicles (AUVs) to strategize the encirclement of evaders while navigating around obstacles and other AUVs. Despite the promise of multi-agent reinforcement learning (MARL) in continuous control problems, its low sample efficiency poses a challenge in unknown environments and complex control scenarios. To overcome these limitations, we present a Knowledge-Guided Reinforcement Learning (KG-RL) approach, which integrates an Artificial Potential Field (APF) to enhance sample efficiency and operational safety. Our methodology is bifurcated into pre-training and fine-tuning phases. During the pre-training phase, an APF is employed to generate a concise set of demonstration trajectories that provide agents with foundational knowledge. Subsequently, the fine-tuning phase leverages real-time APF knowledge to direct the learning process, encouraging agents to balance following demonstrated actions with seeking out more optimal solutions. We assess the efficacy of our method through extensive simulations across diverse tasks, demonstrating its ability to expedite the learning process and yield more strategic decision-making. Our approach achieves superior results compared to traditional MARL benchmarks, particularly in learning efficiency, decision quality, and overall performance.