Cooperative forest fire surveillance using a team of small unmanned air vehicles

TLDR

The paper investigates the feasibility of using multiple low‑altitude, short‑endurance UAVs to cooperatively monitor and track large forest fires. A real‑time infrared‑sensor algorithm tracks fire perimeters, coordinating a decentralized UAV team with limited communication and sensing, validated in simulation with a six‑degree‑of‑freedom UAV model and a numerical fire propagation model. The approach enables continuous monitoring of a changing fire perimeter, dynamic addition and removal of UAVs, and delivery of time‑critical information to firefighters. Keywords: forest fire surveillance, unmanned air vehicles; funded by NASA STTR, AFOSR, and NSF.

Abstract

Abstract The objective of this paper is to explore the feasibility of using multiple low-altitude, short endurance (LASE) unmanned air vehicles (UAVs) to cooperatively monitor and track the propagation of large forest fires. A real-time algorithm is described for tracking the perimeter of fires with an on-board infrared sensor. Using this algorithm, we develop a decentralized multiple-UAV approach to monitoring the perimeter of a fire. The UAVs are assumed to have limited communication and sensing range. The effectiveness of the approach is demonstrated in simulation using a six degree-of-freedom dynamic model for the UAV and a numerical propagation model for the forest fire. Salient features of the approach include the ability to monitor a changing fire perimeter, the ability to systematically add and remove UAVs from the team, and the ability to supply time-critical information to fire fighters. Keywords: Forest fireSurveillanceUnmanned air vehicles Acknowledgments We would like to thank Chad Frost, Francis Enomoto, and Scott Poll at NASA Ames Research Center for initiating this research problem and pointing out related work in the area. This research was supported by NASA under STTR contract No. NNA04AA19C to Scientific Systems Company, Inc (SSCI) and Brigham Young University (BYU), by AFOSR grants F49620-01-1-0091 and F49620-02-C-0094 and by the National Science Foundation under Information Technology Research Grant CCR-0313056.