Constructing reliable trajectories for ship targets in busy waterways involves associating tracks from various sensor sources. This poses challenges due to the incoherence in sensor data precision and acquisition frequency, the high density of targets, and the intertwined correlation scenarios involving trajectory interruptions and multi-source (also known as multi-sensor) observations. Utilizing the intuitive idea that a ship's motion pattern is influenced by its geographic location, we integrate geographic and dynamic information to enhance trajectory accuracy in dense scenes. The proposed approach employs self-supervised contrastive learning to extract relevant features, accompanied by a dual-level augmentation strategy tailored to two association scenarios. Additionally, a specialized feature enhancement module is introduced to enable a comprehensive representation of trajectories. When tested on a large dataset and compared with established methods, our method demonstrates superior capabilities in extracting trajectory features and excels in a variety of association contexts.

Collision avoidance algorithms play a crucial role in ensuring the safety and effectiveness of autonomous ships, which require comprehensive testing in realistic multi-ship encounter scenarios. However, existing scenario generation methods often inadequately represent the spatiotemporal complexity and dynamic risk interactions of real-world encounters, leading to biased evaluations. To bridge this gap, this paper proposes a combinatorial-testing-based scenario generation framework integrated with spatiotemporal complexity optimisation. First, a full-process scenario representation model is developed by abstracting real-world navigation features into a discretised parameter space. Subsequently, a combinatorial-testing-based scenario generation method is adopted to cover the parameter space, generating a high-coverage scenario set. Finally, spatiotemporal complexity is introduced to filter out oversimplified scenarios and extremely dangerous scenarios. Experiments demonstrated that 13.7% of generated scenarios were eliminated as unrealistic or trivial, while high-risk encounter scenarios and multi-ship interaction scenarios were amplified by 7.96 times and 5.84 times, respectively. Compared to conventional methods, the optimised scenario set exhibited superior alignment with real-world complexity, including dynamic risk escalation and multi-ship coordination challenges. The proposed framework not only advances scenario generation methodology through its integration of combinatorial testing and complexity-driven optimisation, but also provides a practical tool for rigorously validating autonomous ship safety systems.

With the development of the shipbuilding industry, nonparametric prediction has become the mainstream method for predicting ship maneuvering motion. However, the lack of transparency and interpretability make the output process of the prediction results challenging to track and understand. An interpretable deep learning framework based on the NbeatsX model is presented for nonparametric ship maneuvering motion prediction. Its three-tier fully connected architecture incorporates trend, seasonal, and exogenous constraints to decompose motion data, enhancing temporal and contextual learning while rendering the prediction process transparent. On the KVLCC2 zig-zag maneuver dataset, NbeatsX achieves NRMSEs of 0.01872, 0.01234, and 0.01661 for surge speed, sway speed, and yaw rate, with SMAPEs of 9.21%, 6.40%, and 7.66% and R² values all above 0.995, yielding a more than 20% average error reduction compared with LS-SVM, LSTM, and LSTM–Attention and reducing total training time by about 15%. This method unifies high-fidelity forecasting with transparent decision tracing. It is an effective aid for ship maneuvering, offering more credible support for maritime navigation and safety decision-making, and it has substantial practical application potential.