DARPA $2M contest looks to bring AI to wireless spectrum provisioning

Credit: Reuters

DARPA wants strategies that enhance optimization of the wireless spectrum

Getting mobile devices to more intelligently access and use the ever-tightening wireless spectrum will be the goal of a new public competition from the Defense Advanced Research Projects Agency.

The defense research agency recently announced a $2 million Grand Challenge called the Spectrum Collaboration Challenge (SC2) and said the primary goal of the contest was to infuse radios with “advanced machine-learning capabilities so they can collectively develop strategies that optimize use of the wireless spectrum in ways not possible with today’s intrinsically inefficient approach of pre-allocating exclusive access to designated frequencies.”

DARPA said the current practice of assigning fixed frequencies for various uses irrespective of actual, moment-to-moment demand is simply too inefficient to keep up with actual demand and threatens to undermine wireless reliability in the military as well as civilian applications, DARPA stated.

+More on Network World: What are grand technology and scientific challenges for the 21st century?+

The challenge is expected to take advantage of recent significant progress in the fields of artificial intelligence and machine learning and also spur new developments in those research domains, with potential applications in other fields where collaborative decision-making is critical,” DARPA stated.

“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 SC2 program manager Paul Tilghman of DARPA’s Microsystems Technology Office in a statement. “We want to radically accelerate the development of machine-learning technologies and strategies that will allow on-the-fly sharing of spectrum at machine timescales.”

+More on Network World: The most momentous tech events of the past 30 years+

DARPA said it will build what it called the largest-of-its-kind wireless test bed – “the Colosseum” -- which will serve during and after the SC2 as a national asset for evaluating spectrum-sharing strategies, tactics, and algorithms for next-generation radio systems. The “Colosseum” will let researchers remotely conduct large-scale experiments with intelligent radio systems in realistic, user-defined RF environments, such as the wireless conditions of a busy city neighborhood or battle setting.

The actual SC2 include three, year-long phases beginning in 2017 and finish in early 2020 with a live competition of finalists who have survived the two preliminary contests. The team whose radios collaborate most effectively with various types of other radios to dynamically optimize spectrum usage will win a grand prize of $2 million, DARPA stated.

DARPA has been sponsoring Grand Challenge competitions for years. The idea typically is to get the nation's best and brightest in a particular area to focus on revolutionary research. In the past the agency has developed autonomous cars as well as security and space technology in this fashion.  NASA and other agencies have mimicked DARPA's success in running these events.

Check out these other hot stories:

NASA competition could net you $1.5M for next great airship

FBI grows “Cyber Most Wanted” list with Syrian Electronic Army members

IRS: Top 10 2015 identity theft busts

FBI warning puts car hacking on bigger radar screen

NASA’s IG tells space agency to bolster space network security

Air Force faces challenges managing drone force

DARPA: Show us how to weaponize benign technologies

Boeing’s self-cleaning aircraft bathroom lets you use loo without touching anything (mostly)

US national lab advances wireless charging for electric cars

DARPA moves ahead with radical vertical takeoff aircraft

Must read: Hidden Cause of Slow Internet and how to fix it
View Comments
Join the discussion
Be the first to comment on this article. Our Commenting Policies