LMPath: Language-Mediated Priors and Path Generation for Aerial Exploration
Jonathan A. Diller, Fernando Cladera, Camillo J. Taylor, Vijay Kumar
TLDR
LMPath uses language models and satellite imagery to generate semantic priors for UAV search paths, significantly improving efficiency over traditional methods.
Key contributions
- Introduces LMPath, a pipeline using generative language models for semantic UAV exploration priors.
- Leverages foundation vision models on satellite imagery to segment object-likely sub-regions.
- Generates UAV paths optimized for objectives like minimizing search time or maximizing find probability.
- Demonstrated improved search efficiency in real UAV flights and simulations compared to traditional methods.
Why it matters
This paper addresses the inefficiency of traditional UAV search by integrating semantic understanding. By using language and vision models, LMPath creates intelligent search priors, drastically reducing search time. This advancement is crucial for large-scale autonomous exploration and emergency response.
Original 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.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.