Distributed Wildfire Surveillance with Autonomous Aircraft using Deep Reinforcement Learning

TL;DR

This paper introduces two deep reinforcement learning methods for autonomous aircraft to effectively monitor wildfires, handling high uncertainty and coordination challenges, and outperforming traditional control strategies in simulations.

Contribution

It presents novel decentralized deep reinforcement learning controllers that enable autonomous aircraft to coordinate and adapt to wildfire dynamics, improving coverage and scalability.

Findings

Both approaches accurately track wildfire expansion.

The methods outperform receding horizon controllers.

The approaches scale with different aircraft numbers and wildfire shapes.

Abstract

Teams of autonomous unmanned aircraft can be used to monitor wildfires, enabling firefighters to make informed decisions. However, controlling multiple autonomous fixed-wing aircraft to maximize forest fire coverage is a complex problem. The state space is high dimensional, the fire propagates stochastically, the sensor information is imperfect, and the aircraft must coordinate with each other to accomplish their mission. This work presents two deep reinforcement learning approaches for training decentralized controllers that accommodate the high dimensionality and uncertainty inherent in the problem. The first approach controls the aircraft using immediate observations of the individual aircraft. The second approach allows aircraft to collaborate on a map of the wildfire's state and maintain a time history of locations visited, which are used as inputs to the controller. Simulation results show that both approaches allow the aircraft to accurately track wildfire expansions and outperform an online receding horizon controller. Additional simulations demonstrate that the approach scales with different numbers of aircraft and generalizes to different wildfire shapes.