Aero-LLM: A Distributed Framework for Secure UAV Communication and Intelligent Decision-Making

2025-02-05

AI Summary

To address security and real-time decision-making challenges in critical UAV–ground control station (GCS) communications, this paper proposes a distributed multi-large language model (LLM) collaboration framework structured as an onboard–edge–cloud tri-level agent architecture. The method introduces a specialized LLM division-of-labor mechanism to overcome performance bottlenecks of monolithic LLMs under resource constraints, ultra-low latency requirements, and high-security demands. It integrates lightweight LLM deployment, distributed inference, anomaly-detection LLMs, time-series prediction LLMs, and a multi-layer encrypted communication protocol. Experimental evaluation demonstrates that the system withstands 98.7% of typical network attacks, achieves millisecond-scale threat response and zero-trust closed-loop decision-making over real-world UAV–GCS links, and significantly improves both task accuracy and response speed.

Technology Category

Machine Learning: Large Multimodal Models (LMMs)Multiagent Systems: Agent CommunicationPlanning, Routing, and Scheduling: Planning with Language Models

Application Category

User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendationEconomics, Online Markets and Human Computation: Cost models of using LLMs in production systemsSemantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Increased utilization of unmanned aerial vehicles (UAVs) in critical operations necessitates secure and reliable communication with Ground Control Stations (GCS). This paper introduces Aero-LLM, a framework integrating multiple Large Language Models (LLMs) to enhance UAV mission security and operational efficiency. Unlike conventional singular LLMs, Aero-LLM leverages multiple specialized LLMs for various tasks, such as inferencing, anomaly detection, and forecasting, deployed across onboard systems, edge, and cloud servers. This dynamic, distributed architecture reduces performance bottleneck and increases security capabilities. Aero-LLM's evaluation demonstrates outstanding task-specific metrics and robust defense against cyber threats, significantly enhancing UAV decision-making and operational capabilities and security resilience against cyber attacks, setting a new standard for secure, intelligent UAV operations.

Problem

• Enhances UAV communication security
• Improves UAV operational efficiency
• Distributes LLMs for intelligent decision-making

Innovation

• Distributed Large Language Models
• Onboard-edge-cloud deployment
• Enhanced UAV cyber security