A Multi-Modal Knowledge-Enhanced Framework for Vessel Trajectory Prediction

2025-03-27

AI Summary

To address the trajectory prediction accuracy bottleneck caused by irregular AIS sampling and highly nonlinear vessel motion, this paper proposes MAKER, a multimodal knowledge-enhanced framework. Methodologically, MAKER integrates large language models, knowledge distillation, spatiotemporal graph neural networks, and self-paced learning. Its key contributions are: (1) a novel language-model-guided trajectory knowledge transfer module (LKT), enabling cross-scenario semantic knowledge adaptation; and (2) a kinematics-constrained self-paced learning module (KSL), which explicitly incorporates physical priors into model training. Evaluated on two real-world maritime trajectory datasets, MAKER achieves an average 14.97% reduction in prediction error over state-of-the-art methods. It demonstrates significantly improved generalization—particularly for long-horizon forecasting and high-dynamic scenarios—validating the effectiveness of synergistic multimodal knowledge integration and physics-informed learning.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Machine Learning: Large Multimodal Models (LMMs)
• Humans and AI: Human-Aware Planning and Behavior Prediction

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: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Accurate vessel trajectory prediction facilitates improved navigational safety, routing, and environmental protection. However, existing prediction methods are challenged by the irregular sampling time intervals of the vessel tracking data from the global AIS system and the complexity of vessel movement. These aspects render model learning and generalization difficult. To address these challenges and improve vessel trajectory prediction, we propose the multi-modal knowledge-enhanced framework (MAKER) for vessel trajectory prediction. To contend better with the irregular sampling time intervals, MAKER features a Large language model-guided Knowledge Transfer (LKT) module that leverages pre-trained language models to transfer trajectory-specific contextual knowledge effectively. To enhance the ability to learn complex trajectory patterns, MAKER incorporates a Knowledge-based Self-paced Learning (KSL) module. This module employs kinematic knowledge to progressively integrate complex patterns during training, allowing for adaptive learning and enhanced generalization. Experimental results on two vessel trajectory datasets show that MAKER can improve the prediction accuracy of state-of-the-art methods by 12.08%-17.86%.

Problem

• Address irregular sampling intervals in vessel tracking data
• Improve learning of complex vessel movement patterns
• Enhance generalization in trajectory prediction models

Innovation

• Multi-modal framework for trajectory prediction
• Language model-guided knowledge transfer module
• Knowledge-based self-paced learning module