​The University of California, Riverside (UC Riverside) will develop artificial intelligence (AI) for UAS, using a $1 million grant from the National Science Foundation.

AI in UAS would one day allow the robots to conduct “far-reaching reconnaissance missions”— such as search and rescue missions, and environmental and security monitoring—without direct human control.

Amit Roy-Chowdhury, professor of electrical and computer engineering, and the principal investigator in the grant, would like to create programs that allow UAS to act on their own, such as by zooming in on a certain object.

“The problem with drones is that the travel path is usually set beforehand. Our project will look into how we can let drones dynamically re-plan, depending on what data is sensed,” explains Roy-Chowdhury.

“There might be a need to get higher resolution data, like if you see a person in a remote area.”

As Roy-Chowdhury points out, UAS are usually set on a pre-determined path to collect data, but it is difficult for humans to analyze the data in real-time, and control the UAS, either because of the volume of data collected, or because of limited reception.

To address this issue, Roy-Chowdhury and his group plan to pre-program UAS with AI that allows them to “strategically determine what kind of data and images are important enough to collect.”

Over the next two years, the research and experimentations under this grant will take place in mountainous areas in Inland Southern California, near the UC Riverside campus.