The attribution of anomalous vessel behaviors is crucial for maritime traffic supervision and safety decision-making. However, existing approaches often lack the capability to systematically interpret multidimensional anomaly features and reveal their underlying behavioral mechanisms, limiting the transparency and practical value of anomaly attribution. To address these challenges, we propose a multidimensional anomalous vessel behavior attribution and decision-support framework based on large language models (LLMs). Specifically, the framework first employs Behavioral Anomaly Semantic Mapping (BASM) to transform multidimensional anomaly features into structured semantic units governed by logical constraints; it then leverages knowledge-guided reasoning (KGRP-PCoT) with LLMs to perform multi-step inference, enabling systematic attribution from low-level anomaly observations to high-level behavioral mechanisms. Experiments conducted on AIS data from the Wusongkou waters demonstrate that the proposed framework significantly outperforms traditional methods. Quantitative evaluations show that the framework achieves a BLEU-4 score of 0.91 and a BERTScore of 0.98 when integrated with advanced LLMs like DeepSeek. Furthermore, the ablation study confirms that the proposed BASM and KGRP-PCoT mechanisms improve the BERTScore from approximately 0.86 to 0.98. It not only reveals the causal mechanisms underlying anomalous behaviors more accurately but also improves logical consistency and regulatory compliance, confirming its practical utility and decision-support value.
Yongfeng Suo, Fangfang Luo, Tao Zhang· Journal of Marine Science an...· 0 citations
Ship path planning is a central challenge in autonomous navigation for unmanned surface vehicles and maritime autonomous surface ships. It is not simply a shortest-path problem, but a constrained sequential decision process that must reconcile collision risk, route efficiency, COLREGs compliance, vessel dynamics, and environmental uncertainty. Here we review the field through a unified framework based on planning scope, decision basis, and deployment requirements. We examine search- and sampling-based, geometric and rule-based, optimization-based, learning-driven, and hybrid methods, with particular emphasis on deep reinforcement learning for discrete decisions, continuous maneuvering, multi-vessel interaction, and safety-oriented control. Representative studies are compared across objective and reward design, state representation, exploration and policy optimization, rule integration, disturbance modeling, simulation platforms, and operational validation. The synthesis identifies persistent barriers, including ambiguous rule formalization, partial observability, strategic coupling among vessels, inconsistent benchmarks, limited cross-scenario generalization, and insufficient full-scale validation. We further discuss priority directions in explicit safety constraints, digital twins, transfer and meta-learning, world models, scalable multi-agent coordination, and large-model-assisted mission reasoning. We argue that progress will depend less on further algorithmic proliferation than on integrated, verifiable architectures that combine data-driven adaptation with model-based structure, standardized evaluation, and staged real-world assurance.
Weijun Wang, Mingjie Li, Bushuo Wang et al.· Journal of Marine Science an...· 0 citations
