Vanderbilt Wins Top Prize In First Round Of DARPA Spectrum Collaboration Challenge

In two years, the world may see a revolutionary solution to the century-old approach of allocating bands for specific use on the radio frequency spectrum. Vanderbilt may help solve the problem.

A Vanderbilt team of researchers and alumni – dubbed MarmotE – won the Round 1 in mid-December of the U.S. Defense Advanced Research Projects Agency’s Spectrum Collaboration Challenge (SC2), leading the top 10 teams, each awarded $750,000 in prize money. This was the first event of the three-year long tournament. Round 2 is set for December 2018. The ultimate SC2 winners will walk away in 2019 with $2 million in prize money.

The win is especially significant for Peter Volgyesi, a research scientist and Miklos Maroti, a research associate professor at Vanderbilt’s Institute for Software Integrated Systems. More than a year ago, the ISIS team qualified for SC2 but was not one of the five teams funded by DARPA for the competition. Volgyesi and Maroti worked only in their spare time, across months of development and hundreds of scrimmage hours.

“This win means a great deal to us,” Volgyesi said. “The competitors – both funded and unfunded – represent the best defense contractors, private companies and academic groups in mobile networking globally.” BAE Systems came in second. Northrop Grumman, eighth. Other university teams came from Berkeley, Purdue, Ghent and Antwerp, University of Florida, Northeastern, and Texas A&M.

For the preliminary event, 475 fully autonomous matches were run with the 19 qualified teams’ radio designs in SC2’s custom testbed environment, known as Colosseum. The final matches for the first event were carried out across six different communications scenarios designed to mirror real-world congested environments, but with more complexity than existing commercial radios are equipped to handle.

The competing teams faced fluctuating bandwidths and interference from other competitors as well as DARPA designed bots that tested and challenged their radio designs. Each team’s radio performance was scored based on its collaborative spectrum sharing abilities.

Vanderbilt’s MarmotE built on its experiences from the first DARPA Spectrum Challenge in 2013-2014 for this event.

“These kinds of very ‘hands-on’ challenges force us, and other teams with very deep theoretical backgrounds, to put their ideas into practice,” said Volgyesi. “That’s a very important step to measure and prove novel approaches and make them useful in the long term for real-life applications. That’s why I like this challenge—it drives professors, graduate students, and engineers to work together towards a common goal.”

Managing the spectrum — automatically

Globally, the wireless revolution is fueling a voracious demand for access to RF spectrum. Smartphones to wearable fitness devices to smart kitchen appliances are competing for bandwidth. In the military, there is a growing reliance on unmanned platforms, from underwater sensors to satellites. Managing demand of the RF spectrum is a serious problem.

DARPA wants to solve the problem in the most efficient way possible, using machine intelligence. SC2 is the first-of-its-kind collaborative machine-learning competition to overcome scarcity in the RF spectrum.

Today’s approach, which is almost a century old, isolates wireless systems by dividing the spectrum into rigid licensed bands that are allocated over large, geographically defined regions. This approach rations access to the spectrum in exchange for the guarantee of interference-free communication. However, at any given time many allocated bands are unused by licensees while other bands are overwhelmed.

In SC2, competitors will reimagine a new, more efficient wireless paradigm where radio networks automatically collaborate to determine how the spectrum should be used moment to moment.

“Central management of the spectrum is simply not scalable and pretty wasteful, but ad-hoc sharing as implemented in WiFi is not working either,” said Maroti. “The best solution to spectrum management would be a combination of distributed cooperation and adaptation driven by the latest advances of machine learning.”

The Round 1 competition found that when two radio networks were asked to share the spectrum, the top performing teams were successful at adapting their spectrum usage so that both networks could successfully transmit with minimal interference.

Fully autonomous sharing of the spectrum with three simultaneous wireless technologies however, remains a difficult challenge. When three different technologies attempt to coexist simultaneously there is a smaller set of overlapping strategies that will fulfill each individual radio network’s needs. This causes conflict and requires a higher degree of agility and reasoning, which will be required to be successful in the next phase.

The next preliminary event will further challenge competitors with an interference environment beyond what existing commercial and military radios can handle—upping the number of simultaneous wireless network types from three to five, and raising the total number of radios from 15 to 50.

SC2 teams will take advantage of recent advances in artificial intelligence and machine learning and the expanding capacities of software-defined radios to develop breakthrough capabilities that can help bring about spectrum abundance.