The Defense Advanced Research Projects Agency has unveiled a three-year competition that seeks to develop machine-learning platforms designed to allow civilian and military wireless devices to gain access to the electromagnetic spectrum.
DARPA launched the Spectrum Collaboration Challenge at the two-day International Wireless Communications Expo that kicked off Wednesday in Las Vegas, the agency said Wednesday.
SC2 seeks to equip radios with machine-learning and artificial intelligence functions in order for the devices to collaborate with other types of radios in spectrum environments.
“DARPA Challenges have traditionally rewarded teams that dominate their competitors, but when it comes to making the most of the electromagnetic spectrum, the team that shares most intelligently is going to win,” said Paul Tilghman, SC2 program manager at DARPA’s microsystems technology office.
DARPA will start the competition in 2017 and will award a prize of $2 million to the winning team in early 2020.
The agency also plans to build a wireless testbed for the challenge in order to allow researchers to assess spectrum-sharing techniques and algorithms for radio platforms.