ShipTraj-R1: Reinforcing Ship Trajectory Prediction in Large Language Models via Group Relative Policy Optimization

2026-03-03

AI Summary

This work addresses the limited reasoning capability and accuracy of existing methods in vessel trajectory prediction under complex maritime scenarios by proposing a novel approach that reformulates the task as a text-to-text generation problem using the large language model Qwen3. The method introduces dynamic prompting to guide adaptive chain-of-thought reasoning, integrates a comprehensive reward function grounded in maritime navigation rules, and employs Group Relative Policy Optimization (GRPO) for reinforcement fine-tuning. By innovatively combining domain-specific prompts, rule-driven rewards, and the GRPO algorithm, the proposed framework significantly outperforms current deep learning and LLM-based baselines on two real-world, complex maritime datasets, achieving the lowest prediction error reported to date.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Recent advancements in reinforcement fine-tuning have significantly improved the reasoning ability of large language models (LLMs). In particular, methods such as group relative policy optimization (GRPO) have demonstrated strong capabilities across various fields. However, applying LLMs to ship trajectory prediction remains largely unexplored. In this paper, we propose ShipTraj-R1, a novel LLM-based framework that reformulates ship trajectory prediction as a text-to-text generation problem. (1) We design a dynamic prompt containing trajectory information about conflicting ships to guide the model to achieve adaptive chain-of-thought (CoT) reasoning. (2) We introduce a comprehensive rule-based reward mechanism to incentivize the reasoning format and prediction accuracy of the model. (3) Our ShipTraj-R1 is reinforced through the GRPO mechanism guided by domain-specific prompts and rewards, and utilizes the Qwen3 as the model backbone. Extensive experimental results on two complex and real-world maritime datasets show that the proposed ShipTraj-R1 achieves the least error compared with state-of-the-art deep learning and LLM-based baselines.

Problem

• ship trajectory prediction
• large language models
• reinforcement fine-tuning
• maritime datasets

Innovation

• ShipTraj-R1
• group relative policy optimization
• trajectory prediction
• large language models
• chain-of-thought reasoning