Jeff Child, Editor-in-Chief, COTS Journal

For anyone who has followed this column over the years, I’ve always been keenly interested in the various DARPA “Challenge” events. Beginning over 10 years back with the DARPA Grand Challenge, Congress has continued to authorized DARPA to award cash prizes to further DARPA’s mission to sponsor revolutionary, high-payoff research that bridges the gap between fundamental discoveries and military use. The initial DARPA Grand Challenge was created to spur the development of technologies needed to create the first fully autonomous ground vehicles capable of completing a substantial off-road course within a limited time. Over the years there’s been a number of challenges addressing technology areas like cyber security and robotics.

Over the next couple years another DARPA challenge is underway that very much is in line with the advanced electronics technologies of interest to COTS Journal readers: the DARPA Spectrum Collaboration Challenge (SC2). This is the first-of-its-kind collaborative machine-learning competition to overcome scarcity in the radio frequency (RF) spectrum. A little background: spectrum today is managed by dividing it into rigid, exclusively licensed bands. But this human-driven process is not adaptive to the dynamics of supply and demand, and thus cannot exploit the full potential capacity of the spectrum.

The team whose radio design most reliably achieves successful communication in the presence of other competing radios could win as much as $3,500,000. Competitors will reimagine spectrum access strategies and develop a new wireless paradigm in which radio networks will autonomously collaborate and reason about how to share the RF spectrum, avoiding interference and jointly exploiting opportunities to achieve the most efficient use of the available spectrum. SC2 teams will develop these breakthrough capabilities by taking advantage of recent advances in artificial intelligence (AI) and machine learning, and the expanding capacities of software-defined radios.

According to DARPA this competition aims not only to challenge innovators in academia and business to produce breakthroughs in collaborative AI, but also to catalyze a new spectrum paradigm that can help usher in an era of spectrum abundance. In October the SC2 Open Track Hurdles page went providing an overview of the process to follow to successfully complete the three Phase 1 hurdles. Teams wishing to participate in the Spectrum Collaboration Challenge, must complete 3 entrance hurdles.

The competition will unfold in three year-long phases beginning in 2017 and finishing, for those teams that survive the two Preliminary Events, in a high-profile Championship Event in late 2019. The team whose advanced, software-defined radios collaborate most effectively with a diversity of simultaneously operating radios in a manner that optimizes spectrum usage for the entire communicating ensemble will walk away with a grand prize of $2 million. The teams that rank as the second and third best collaborators will take home $1 million and $750,000, respectively.

A leading player in our industry National Instruments has stepped up to serve a major role in the Spectrum Collaboration Challenge. NI has begun a collaboration with DARPA to supply core infrastructure for a path-breaking channel emulation testbed, called Colosseum. NI will provide USRP software defined radios (SDRs) that support a wide variety of open source and proprietary tool flows including GNU Radio, RFNoC and LabVIEW system design software.

The Colosseum channel emulation testbed supports up to 256-by-256-channel, real-time channel emulation, calculating more than 65,000 channel interactions at up to 80 MHz of real-time bandwidth per channel. The testbed, based on the USRP X310 software defined radio and NI ATCA-3671 high-performance FPGA processing system, will be housed at the Johns Hopkins University Applied Physics Laboratory in Laurel, Md., and will be accessible remotely for next-generation wireless research. The testbed will provide a level playing field for the three-year competition.

Ettus Research, a subsidiary of NI, provides a key piece of hardware: the USRP X310 scalable software defined radio (SDR) platform. The hardware architecture combines two extended-bandwidth daughterboard slots covering DC to 6 GHz with up to 160 MHz of baseband bandwidth, multiple high-speed interface options (PCIe, dual 10 GigE, dual 1 GigE), and a large user-programmable Kintex-7 FPGA in a convenient desktop or rack-mountable half-wide 1U form factor.  In addition to providing best-in-class hardware performance, the open source software architecture of X310 provides cross-platform UHD driver support making it compatible with a large number of supported development frameworks, reference architectures, and open source projects.

Like all of DARPA’s other challenge “events, the SC2 shows much wisdom on the part of the DoD in not simply looking inward for technology innovation, but rather to cast as wide a net as possible to leverage all the thinking power of academia and industry. I look forward to following the progress of this challenge over the next couple years.

Information on the DARPA Spectrum Collaboration Challenge is available at (Click Here)