Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Yang Zhan, Yunhao Li, Zhang Chao, Yuxu Lu, Yan Li

TL;DR

The proposed ShipTraj-R1 is a novel LLM-based framework that reformulates ship trajectory prediction as a text-to-text generation problem and achieves the least error compared with state-of-the-art deep learning and LLM-based baselines.

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.

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

TL;DR

The proposed ShipTraj-R1 is a novel LLM-based framework that reformulates ship trajectory prediction as a text-to-text generation problem and achieves the least error compared with state-of-the-art deep learning and LLM-based baselines.

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.
Paper Structure (15 sections, 6 equations, 3 figures, 4 tables)

This paper contains 15 sections, 6 equations, 3 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Ship Trajectory Prediction
  4. LLM-based Trajectory Prediction
  5. Methodology
  6. Problem Definition
  7. ShipTraj-R1 Model
  8. Rule-based Reward Function
  9. Reinforcement Fine-Tuning
  10. Experiment
  11. Experimental Settings
  12. Comparison with State-of-art Methods
  13. Ablation Studies
  14. Conclusion

Figures (3)

  • Figure 1: Overview of our proposed ShipTraj-R1 framework.
  • Figure 2: Qualitative examples of our ShipTraj-R1 on the CSJP dataset. In this case, the ShipTraj-R1 adaptively generates CoT reasoning by itself based on the user prompt.
  • Figure 3: Illustration of predicted ship trajectories from the CSJP and CFDP datasets.