# Wildfire Monitoring in Remote Areas using Autonomous Unmanned Aerial Vehicles

## TL;DR

This paper presents an autonomous drone system for rapid wildfire monitoring in remote areas, using coalition formation to efficiently cover fire zones with minimal human intervention and energy use.

## Contribution

It introduces a distributed leader-follower coalition model enabling fully autonomous wildfire monitoring with optimized drone coverage and energy efficiency.

## Key findings

- Simulation shows near-optimal coverage without inter-coalition communication.
- System reduces monitoring time compared to traditional methods.
- Minimizes human risk and energy consumption during wildfire surveillance.

## Abstract

In this paper, we propose a drone-based wildfire monitoring system for remote and hard-to-reach areas. This system utilizes autonomous unmanned aerial vehicles (UAVs) with the main advantage of providing on-demand monitoring service faster than the current approaches of using satellite images, manned aircraft and remotely controlled drones. Furthermore, using autonomous drones facilitates minimizing human intervention in risky wildfire zones. In particular, to develop a fully autonomous system, we propose a distributed leader-follower coalition formation model to cluster a set of drones into multiple coalitions that collectively cover the designated monitoring field. The coalition leader is a drone %with longer communication range that employs observer drones potentially with different sensing and imaging %actuation capabilities to hover in circular paths and collect imagery information from the impacted areas. The objectives of the proposed system include i) to cover the entire fire zone with a minimum number of drones, and ii) to minimize the energy consumption and latency of the available drones to fly to the fire zone. Simulation results confirm that the performance of the proposed system -- without the need for inter-coalition communications -- approaches that of a centrally-optimized system.