LMPath: Language-Mediated Priors and Path Generation for Aerial Exploration

2026-05-13

AI Summary

This work addresses the inefficiency of conventional unmanned aerial vehicle (UAV) search strategies that rely solely on geometric coverage while ignoring semantic information about targets, particularly in large-scale environments. To overcome this limitation, the authors propose a novel approach that integrates generative language models with vision foundation models to produce semantic exploration priors from natural language prompts describing target characteristics. These priors, combined with segmentation results derived from satellite imagery, guide UAV path planning in a semantically informed manner. This study represents the first effort to incorporate language-guided semantic priors into UAV search tasks, thereby transcending the traditional paradigm of semantics-agnostic trajectory generation. Both real-world and simulated experiments demonstrate that the proposed method significantly outperforms existing approaches in terms of time-to-discovery, probability of detection within limited flight ranges, and reduction of the effective search space.

Abstract

Traditional autonomous UAV search missions rely on geometric coverage patterns that ignore the semantic context of the target, leading to significant time waste in large-scale environments. In this paper we present LMPath, a pipeline for generating language-mediated exploration priors for Unmanned Aerial Vehicle (UAV) search missions that leverages semantics. Given a basic geofence and an object of interest prompt, LMPath uses generative language models to determine what regions of the environment should contain that object and a foundation vision model ran over satellite imagery to segment sub-regions that form the exploration prior. This prior can then be used to generate UAV paths with various objectives, such as minimizing the expected time to locate the object of interest, maximizing the probability that the object is found given a limited travel distance, or narrowing down the search space to sub-regions that are most likely to contain the object. To demonstrate it's capabilities, we used LMPath to generate various UAV paths and ran them using a real UAV over large-scale environments. We also ran simulations to demonstrate how paths generated using LMPath outperform traditional path planning approaches for search missions.

Problem

• UAV search
• semantic context
• exploration prior
• path planning
• large-scale environments

Innovation

• language-mediated priors
• semantic-aware path planning
• foundation vision models
• UAV search missions
• generative language models