Originally posted by: Forbes
DARPA, the government agency responsible for much of the technology we hold near and dear today such as the Internet, GPS and voice recognition, issued a challenge today. Dubbed the Spectrum Collaboration Challenge (SC2), the infamous agency is soliciting a solution to the increasingly-overcrowded electromagnetic spectrum.
The newest of their Grand Challenges, the aim is to ensure that the exponentially-increasing range of both military and civilian wireless devices will have access to the electromagnetic spectrum by developing “smart systems that collaboratively, rather than competitively, adapt in real time to today’s fast-changing, congested spectrum environment—redefining the conventional spectrum management roles of humans and machines in order to maximize the flow of radio frequency (RF) signals.”
Currently, these devices operate on fixed ranges such as a 2.4 GHz or a 5.8 GHz phone, the latter spectrum being less crowded and thus operating more effectively. However, the problem is that as the number of devices increases, the likelihood for interference and decreased accessibility by both government and civilian devices will continue to grow at an alarming rate. Considering that the spectrum is fixed, the agency is soliciting the public’s help with the incentive of a $2 million prize.
The contest, set to begin in 2017 and end in 2020, aims to award the winner that develops the best and most collaborative machine-learning solutions to the electromagnetic spectrum. It was announced to an audience of 8000 engineers and professionals in the communications industry at the International Wireless Communications Expo (IWCE) in Las Vegas.
In the past, the agency has issued other challenges that would award teams in a competitive environment, such as the DARPA Robotics Challenge, which aimed to develop semi-autonomous robots that could complete “complex tasks in dangerous, degraded, human-engineered environments.” The challenge ran from 2012 through 2015 and pitted teams based on eight separate objectives.
SC2’s inherent aim is to award the team that can develop the best collaborative system rather than competitive. The goal is to use the machine-learning technology in wireless devices to autonomously change their frequency based on congestion and spectrum availability, making the devices dynamic rather than fixed-range.
“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,” states Paul Tilghman from DARPA’s Microsystems Technology Office (MTO).
The challenge is partially born from the military’s need for access to the wireless spectrum, which is increasingly becoming less and less accessible to not only coordinate critical missions and execute them, but also in assessing the tactical environment in the early-planning stages. With the likelihood for congestion, interference, and inaccessibility by the military rising, it’s no surprise that they’ve turned to DARPA to help institute a solution that will involve machine-learning technologies.
Eventually, in the 2020’s, we’ll see this technology prebuilt into all types of wireless devices, whatever those might like like in the coming decade. Devices will learn to move dynamically across the wireless spectrum based on load and accessibility, paving the way for the exponential wave of devices coming onto the market today and into the future.