Multi-swarm drones to quell forest fires

These AI-driven swarms can be helpful during other natural disasters such as floods and earthquakes, locating survivors, delivering essential supplies, and improving communication.
Representational image: Indian Institute of Science (IISC) in Bengaluru.
Representational image: Indian Institute of Science (IISC) in Bengaluru. (File photo| EPS)

BENGALURU: More than 2,12,000 forest fires were reported in the country between November 2022 and June 2023, data from the Forest Survey of India has revealed. To curb the catastrophic impact of these fires that are accelerated due to climate change, researchers at the Indian Institute of Science (IISc) have presented a new solution, using a swarm of drones.

These AI-driven swarms can be helpful during other natural disasters such as floods and earthquakes, locating survivors, delivering essential supplies, and improving communication. Suresh Sundaram, Professor in the Department of Aerospace Engineering, IISc, and his team proposed the use of coordinated multi-swarm drones flying in to quell forest fires.

“By the time somebody identifies and reports a fire, it would have started spreading and cannot be put out with one drone. You need to have a swarm of drones that can communicate with each other,” Sundaram added. The study was published in IEEE Transactions on Systems, Man, and Cybernetics: Systems.

Researchers designed a special algorithm that would allow decentralised decision-making based on real-time data, aimed at maximum efficiency through direct communication between the drones. “When an alarm is raised about a potential fire, the swarms can be sent in, each drone armed with cameras, thermal and infrared sensors, and temperature detectors, to spot the fires. Once the fire is discovered, the drone closest to it becomes the centre of the swarm. Each drone also has autonomy to calculate the size, and potential spread of fire, and decide how many drones are needed to quench the fire,” read the release.

The drones will also figure out which fire cluster will spread fast, and make timely decisions on moving from one fire spot to the other. This solution was inspired by the behaviour of a marine predator, a flagellum called Oxyrrhis marina. “When foraging, it first takes longer to explore the area. Once it feels it’s closer to the food source, it reduces the step length and starts exploring the area in detail,” said Josy John, PhD student at the Department of Aerospace Engineering.

Related Stories

No stories found.
The New Indian Express
www.newindianexpress.com