Researchers at the University of Arizona (UA) received a USD 750,000 grant from the US Air Force Office of Scientific Research to build an autonomous surveillance system for land and aerial vehicles monitoring the country's border with Mexico.
They are building a framework for border surveillance that uses artificial intelligence, based on realistic computer simulations, to integrate data from different sources and respond in real time.
"Our goal is to devise a system to most effectively, efficiently and safely deploy border patrol resources," said Young-Jun Son, professor at UA.
The research will help the United States Department of Homeland Security's Customs and Border Protection unit to gain a clearer picture of border activities for swifter, better- coordinated responses.
Homeland Security has used unmanned aerial vehicles equipped with cameras and radar for border surveillance since 2005, researchers said.
The challenge is to choose the right combination of aerial and ground vehicles, given different terrain and weather conditions, and activates them at just the right time.
"A major task of unmanned vehicles in patrol missions is to detect and find their targets' locations in real time," said Sara Minaeian, doctoral candidate at UA.
They have also been analysing and testing different wireless network technologies for drones to communicate and cooperate over varied distances.
Establishing when and where to send unmanned aerial vehicles versus personnel on foot or in trucks is a delicate balancing act.
"Once we have detected, located and identified our targets of interest, we must decide which vehicles to deploy, and how many of each, to best meet objectives while considering trade-offs of performance, cost and safety," Son said.
The team will add aerostats, increasingly used to track drug traffickers' low-flying drones and intercept traffickers.
They have also developed an algorithm that will allow drones to accurately predict crowd behaviour.