Large Language Models for UAVs: Current State and Pathways to the Future

TL;DR

The paper tackles the problem of enabling autonomous UAVs through Large Language Models (LLMs) by surveying LLM architectures and their suitability for UAV integration, and by outlining state-of-the-art LLM-based UAV architectures and opportunities in spectral sensing. It presents a structured analysis of network architectures, spectrum management, and broad use cases (surveillance, disaster response, delivery, environmental monitoring, and satellite/HAP communications), while identifying key challenges such as computational demands, latency, robustness, and security. The contributions include a detailed comparison of BERT, GPT, T5, XLNet, ERNIE, and BART for UAV tasks, a discussion of modular network designs, and future directions including algorithmic advances, edge computing, RIS/5G/6G integration, and regulatory considerations. The work highlights the practical impact of LLMs in expanding UAV autonomy and responsiveness, particularly in dynamic, spectrum-constrained environments, and provides a roadmap for research and policy to realize reliable, scalable LLM-enabled UAV systems.

Abstract

Unmanned Aerial Vehicles (UAVs) have emerged as a transformative technology across diverse sectors, offering adaptable solutions to complex challenges in both military and civilian domains. Their expanding capabilities present a platform for further advancement by integrating cutting-edge computational tools like Artificial Intelligence (AI) and Machine Learning (ML) algorithms. These advancements have significantly impacted various facets of human life, fostering an era of unparalleled efficiency and convenience. Large Language Models (LLMs), a key component of AI, exhibit remarkable learning and adaptation capabilities within deployed environments, demonstrating an evolving form of intelligence with the potential to approach human-level proficiency. This work explores the significant potential of integrating UAVs and LLMs to propel the development of autonomous systems. We comprehensively review LLM architectures, evaluating their suitability for UAV integration. Additionally, we summarize the state-of-the-art LLM-based UAV architectures and identify novel opportunities for LLM embedding within UAV frameworks. Notably, we focus on leveraging LLMs to refine data analysis and decision-making processes, specifically for enhanced spectral sensing and sharing in UAV applications. Furthermore, we investigate how LLM integration expands the scope of existing UAV applications, enabling autonomous data processing, improved decision-making, and faster response times in emergency scenarios like disaster response and network restoration. Finally, we highlight crucial areas for future research that are critical for facilitating the effective integration of LLMs and UAVs.

Figures (3)

• Figure 1: A general architecture of LLM incorporating input layer, embedding layer, transformer block, and output layer.
• Figure 2: Comprehensive architecture of LLM-integrated UAV systems.
• Figure 3: Applications of LLM-integrated UAVs.