LLM-Powered Obstacle Map Generation for UAV Path Planning in Complex Weather Conditions

When executing missions under complex weather conditions, Unmanned Aerial Vehicles (UAVs) face numerous challenges. The highly dynamic and complex nature of weather conditions makes it an urgent challenge to accurately and efficiently construct maps for path planning. In this work, we propose a novel method for obstacle map generation and path planning using Large Language Models (LLMs) to address the challenges of UAV navigation in complex weather conditions. We collect real-time meteorological data from multiple sources and process through fine-tuned LLMs to generate threat values. These threat values are then used to construct obstacle maps with a convex hull algorithm. Then convex optimization-based UAV path planning is deployed on the map. Simulation experiments validate the effectiveness of our approach. The results demonstrate that our approach achieves high accuracy and real-time performance, providing reliable obstacle maps to ensure safe UAV flight in complex weather environments.