The Defense Advanced Research Projects Agency has selected 22 teams and eight individuals for the first phase of a $3.75 million competition that seeks to leverage machine learning platforms to provide civilian and military wireless devices access to the electromagnetic spectrum.
The Spectrum Collaboration Challenge calls for competitors to create a wireless spectrum paradigm that would allow radio networks to collaborate and share the RF spectrum with other networks through the use of artificial intelligence-based technologies and software-defined radios, DARPA said Monday.
“SC2 sets out to bring the software defined radio and artificial intelligence communities together to fundamentally rethink 100 years of spectrum practice, and tackle the original and enduring spectrum grand challenge: efficient coexistence of all wireless communications,” said Paul Tilghman, SC2 administrator and a program manager at DARPA’s microsystems technology office.
Six contenders obtained spots in the Proposal Track that covers $500,000 in contract funds as part of the preliminary competition, while the 24 participants vied for slots through the Open Track option of the SC2 competition that was unveiled in March 2016.
DARPA will hold the preliminary competition in December and the challenge’s second phase in December 2018 and then select the top three winners by the end of 2019.