Context-Informed Ship Trajectory Prediction via Conditional Attention

2026-07-29

AI Summary

This work addresses the limitations of existing vessel trajectory prediction methods, which often neglect the directional physical influence of environmental factors and suffer significant performance degradation under sensor outages. To overcome these issues, the authors propose a Transformer-based conditional generative framework that explicitly models the unidirectional modulation of vessel dynamics by environmental conditions through a conditional attention mechanism. Furthermore, a modality masking training strategy is introduced to enhance robustness against unreliable or missing sensor inputs. By integrating Automatic Identification System (AIS) data with ERA5 meteorological reanalysis, the proposed method achieves a 15.4% improvement in prediction accuracy when environmental context is available and reduces fallback error by nearly an order of magnitude during sensor failures.

Abstract

Long-term ship trajectory prediction is a fundamental capability for maritime safety and autonomous navigation. While recent Transformer-based architectures have improved forecasting horizons, they predominantly rely on historical kinematic states, treating vessel motion as an isolated system. In reality, maritime navigation is profoundly modulated by extrinsic factors like weather and constrained by static vessel characteristics. Existing multimodal approaches fundamentally model the joint distribution over states and contexts, treating environmental variables as peer features rather than encoding the directional physical dependence of vessel dynamics on environmental conditions. In this work, we propose the Conditional Informer, a novel encoder-decoder architecture that formulates trajectory prediction as a conditional generation task. We employ a dedicated Conditional Attention mechanism where the vessel state explicitly queries environmental contexts through cross-attention, encoding the physical prior that weather modulates - but is not generated by - vessel dynamics. Furthermore, to address the intermittency of real-world data, we introduce a Modality Masking training strategy to prevent catastrophic degradation during sensor fallback. Extensive experiments on AIS and ERA5 data demonstrate that our approach outperforms kinematic and concatenation-based baselines by 15.4% in prediction accuracy when context is available. Crucially, Modality Masking prevents shortcut learning, reducing fallback error by nearly an order of magnitude compared to unconstrained models.

Problem

• ship trajectory prediction
• context-aware modeling
• environmental modulation
• multimodal learning
• maritime navigation

Innovation

• Conditional Attention
• Trajectory Prediction
• Multimodal Learning
• Modality Masking
• Maritime Navigation