Preliminary Event #2 Recap

Competitors from around the world came together this month for the Preliminary Event #2 (PE2) of DARPA’s Spectrum Collaboration Challenge (SC2) at Johns Hopkins University Applied Physics Laboratory (APL) in Laurel, MD. This was the second event of the three-year long tournament designed to generate new wireless paradigms and access strategies in which radio networks enhanced with artificial intelligence will autonomously collaborate and reason about how to share the increasingly congested electromagnetic spectrum. Months of development and hundreds of scrimmage hours paid off for either teams who each walked away from the December 12 event with $750,000 in prize money. The winning teams’ demonstrated software defined radio (SDR) designs that were most effective at collaborating with competing radio designs to jointly optimize spectrum usage.

Competitors from around the world came together on December 12, 2018 for Preliminary Event #2 (PE2) at Johns Hopkins University AppliedPhysics Laboratory (APL) in Laurel, MD. Fifteen teams represented by members from across the academic, commercial and defense landscape, pit theirSC2 radio designs against each other in this round-robin competition. At the event’s conclusion, the following teams walked away with $750,000 each in prize money:

  • Zylinium, a team of independent researchers
  • MarmotE from Vanderbilt University
  • Sprite from Northeastern University
  • Erebus, a team of independent researchers
  • Gator Wings from University of Florida
  • SCATTER from IDLab, an imec research group at Ghent University and University of Antwerp, and Rutgers University

Starting in early December, each team’s radio participated in 105 matches against competitors in the Colosseum, a massive RF testbed that was developed specifically for SC2. The matches were held in a round-robin fashion where each radio network – working in groups of threes, fours or fives – had multiple opportunities to compete against every other radio design in the competition. Roughly 400 matches were held in total to determine the final team rankings and the prize recipients.

During the PE2 matches, teams’ were put through six different RF scenarios designed to mimic the challenges that collaborative, autonomous radios will face in the real world. These scenarios challenged the radios to collaboratively mitigate interfering with an incumbent radio system, sense and adapt to the spectrum demands of high-traffic environments, handle the data demands of the connected soldier of the future, and beyond. Each scenario was designed to pressure test various elements of the teams’ approaches and, in particular, their ability to successfully collaborate with the other radios operating within the same environment.  

To aid with decision making, teams applied AI and machine learning technologies in various ways. Some leveraged the current generation of AI technologies like deep learning, while others used more conventional optimization approaches. There were also a few teams that used first wave, rule-based AI technologies.  While not all competitors received interim prizes, all 15 teams have an opportunity to move on to the next stage and compete in the 2019 Spectrum Collaboration Challenge Championship Event.