Design and Evaluation of a Multi-Agent Perception System for Autonomous Flying Networks

TL;DR

This paper introduces MAPS, a multi-agent perception system for autonomous flying networks that uses multimodal AI to interpret sensor data, enabling zero-touch operation by accurately detecting users and their demands.

Contribution

The paper presents a novel, scalable perception system leveraging multimodal large language models and AI agents for autonomous UAV-based network management.

Findings

User detection accuracy above 70%

Service Level Specifications generated within 130 seconds in 90% of cases

Multimodal data improves user detection performance

Abstract

Autonomous Flying Networks (FNs) are emerging as a key enabler of on-demand connectivity in dynamic and infrastructure-limited environments. However, current approaches mainly focus on UAV placement, routing, and resource management, neglecting the autonomous perception of users and their service demands - a critical capability for zero-touch network operation. This paper presents the Multi-Agent Perception System (MAPS), a modular and scalable system that leverages multi-modal large language models (MM-LLMs) and agentic Artificial Intelligence (AI) to interpret visual and audio data collected by UAVs and generate Service Level Specifications (SLSs) describing user count, spatial distribution, and traffic demand. MAPS is evaluated using a synthetic multimodal emergency dataset, achieving user detection accuracies above 70% and SLS generation under 130 seconds in 90% of cases. Results demonstrate that combining audio and visual modalities enhances user detection and show that MAPS provides the perception layer required for autonomous, zero-touch FNs.