AURA: Autonomous Urban Reconnaissance Array for Post-Earthquake Emergency Communication Networks

Abstract

This paper presents AURA (Autonomous Urban Reconnaissance Array), a ROS 2-based drone swarm system designed to restore emergency WiFi communication in post-earthquake disaster zones. The system deploys five coordinated UAVs that autonomously establish a selfhealing mesh network. The architecture integrates PX4SITL with Gazebo Classic, a log-distance path loss simulator calibrated to ITU-R P.1411 urban parameters, and two complementary positioning strategies: a deterministicHungarian-assignment baseline achieving 96–99% grid coverage under static conditions, and a PPO reinforcement learning policy trained with dead zone awareness thatpreserves full mesh connectivity (all relay links intact) under dynamic signal obstructions at the cost of reduced spatial coverage. A context-dependent switchingmechanism transitions between controllers based on environmental conditions. Experimental evaluation across static, dynamic, and fault-tolerance scenarios demonstrates114.7 Mbps aggregate throughput, 6 ms latency, and graceful degradation to 80% coverage under singledrone failure within a 450 m×260 m disaster environment containing 17 collapsed structures.