Maritime Mission Planning for Unmanned Surface Vessel using Large Language Model

2025-03-15

AI Summary

Unmanned Surface Vehicles (USVs) struggle to adapt to sudden disturbances in dynamic maritime environments, and conventional static task planning lacks robustness. Method: This paper proposes a symbolic autonomous planning framework deeply integrated with large language models (LLMs), embedding GPT-4 into the high-level symbolic planning loop of USVs for the first time. The framework enables natural-language instruction interpretation, environment-perception-driven real-time replanning, and co-optimization with low-level control feedback. It integrates a natural-language interface, a symbolic reasoning engine, and a maritime simulation environment. Contribution/Results: The system achieves millisecond-scale replanning under dynamic disruptions such as sudden obstacle appearance and sea-state variations. Experiments demonstrate significant improvements in mission success rate and environmental adaptability, substantial reduction in operational complexity, and end-to-end deployment of high-level goals without manual programming.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Multiagent Systems: Multiagent Planning
• Humans and AI: Planning and Decision Support for Human-Machine Teams

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

Unmanned Surface Vessels (USVs) are essential for various maritime operations. USV mission planning approach offers autonomous solutions for monitoring, surveillance, and logistics. Existing approaches, which are based on static methods, struggle to adapt to dynamic environments, leading to suboptimal performance, higher costs, and increased risk of failure. This paper introduces a novel mission planning framework that uses Large Language Models (LLMs), such as GPT-4, to address these challenges. LLMs are proficient at understanding natural language commands, executing symbolic reasoning, and flexibly adjusting to changing situations. Our approach integrates LLMs into maritime mission planning to bridge the gap between high-level human instructions and executable plans, allowing real-time adaptation to environmental changes and unforeseen obstacles. In addition, feedback from low-level controllers is utilized to refine symbolic mission plans, ensuring robustness and adaptability. This framework improves the robustness and effectiveness of USV operations by integrating the power of symbolic planning with the reasoning abilities of LLMs. In addition, it simplifies the mission specification, allowing operators to focus on high-level objectives without requiring complex programming. The simulation results validate the proposed approach, demonstrating its ability to optimize mission execution while seamlessly adapting to dynamic maritime conditions.

Problem

• Adapt USV mission planning to dynamic maritime environments.
• Integrate LLMs for real-time adaptation and obstacle handling.
• Simplify mission specification using natural language commands.

Innovation

• Uses Large Language Models for maritime mission planning
• Integrates LLMs to adapt to dynamic environments
• Simplifies mission specification with natural language commands