DARPA Spectrum Challenges

The team of four current and former researchers of the Institute for Software Integrated Systems of Vanderbilt have worked together since 2016 to create an embedded AI-based radio system that can manage the wireless spectrum, finding unused slices in its rigid bands to jump to for more bandwidth—collaboratively with other users—in complex scenarios created to test the teams’ systems. Our team, MarmotE, won $1.5 million in preliminary rounds, taking the top prize in 2017 and second place in 2018, and 2nd place in the SC2 Final event in 2019 bringing their total winnings to $2.5 million. These challenges were looking for autonomous strategies for utilizing the RF spectrum, using novel radio waveforms, information coding and flow control. Successful participation in these competitions required in-depth understanding of digital communication and signal processing, software-defined radio platforms, networking and artificial intelligence.

List of ranking in DARPA Spectrum Challenge (SC) and Spectrum Collaboration Challenge (SC2) competitions:

• 1st place: SC Preliminary Event Competitive Track, 2013.
• 3rd place: SC Final Event Cooperative Track, 2014.
• 1st place: SC2 Preliminary Event 1, 2017.
• 2nd place: SC2 Preliminary Event 2, 2018.
• 2nd place: SC2 Final Event, 2019.

Press Releases:

• Vanderbilt team wins $1m in Darpa Spectrum Challenge finale
• Vanderbilt team wins $750K with AI to manage RF spectrum Jan. 29, 2019