Multi-vessel Interaction-Aware Trajectory Prediction and Collision Risk Assessment

2025-09-01

AI Summary

Existing single-vessel trajectory prediction models neglect vessel interactions, navigational regulations (e.g., COLREGs), and explicit collision-risk modeling, limiting their applicability to multi-vessel collaborative situation awareness. To address this, we propose a novel Transformer-based framework explicitly designed for multi-vessel interaction modeling, enabling joint trajectory prediction of the target vessel and neighboring vessels alongside synchronous, quantitative collision-risk assessment. Our approach innovatively integrates causal convolution (to capture local dynamics), spatial transformation (to encode relative positional relationships), hybrid positional encoding (to jointly model absolute and relative spatiotemporal dependencies), and physics-informed feature encoding (to embed COLREGs-compliant constraints), forming an end-to-end, interaction-aware prediction-and-risk-evaluation architecture. Evaluated on large-scale real-world AIS data, our method achieves statistically significant improvements over state-of-the-art baselines in both multi-vessel joint trajectory prediction accuracy and collision-risk identification precision, thereby enhancing intelligent maritime decision support capabilities.

Technology Category

• Computer Vision: Multi-modal Vision
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Planning, Routing, and Scheduling: Model-Based Reasoning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Accurate vessel trajectory prediction is essential for enhancing situational awareness and preventing collisions. Still, existing data-driven models are constrained mainly to single-vessel forecasting, overlooking vessel interactions, navigation rules, and explicit collision risk assessment. We present a transformer-based framework for multi-vessel trajectory prediction with integrated collision risk analysis. For a given target vessel, the framework identifies nearby vessels. It jointly predicts their future trajectories through parallel streams encoding kinematic and derived physical features, causal convolutions for temporal locality, spatial transformations for positional encoding, and hybrid positional embeddings that capture both local motion patterns and long-range dependencies. Evaluated on large-scale real-world AIS data using joint multi-vessel metrics, the model demonstrates superior forecasting capabilities beyond traditional single-vessel displacement errors. By simulating interactions among predicted trajectories, the framework further quantifies potential collision risks, offering actionable insights to strengthen maritime safety and decision support.

Problem

• Predicts multi-vessel trajectories with interaction awareness
• Integrates collision risk assessment for maritime safety
• Overcomes limitations of single-vessel forecasting models

Innovation

• Transformer-based multi-vessel trajectory prediction
• Hybrid positional embeddings capturing motion patterns
• Integrated collision risk analysis through trajectory simulation