Growing use of RF/microwave signals may require machines and robots to keep things straight. For this reason, DARPA awarded BAE Systems a contract worth $9.2 million for its Radio Frequency Machine Learning System (RFMLS) program. DARPA is looking to BAE to develop new data-driven machine-learning algorithms to help decipher the growing number of RF/microwave signals populating an ever-more-crowded frequency spectrum. It’s hoped that practical solutions can be developed to keep track of the many high-frequency wireless signals in use for commercial, industrial, and military applications.
Data-driven machine-learning research has made great strides in image and speech recognition, as well as fostering progress in developing safe autonomous vehicles. Machine-learning techniques are felt to be capable of supporting traditional RF/microwave signal-processing methods to identify and categorize high-frequency signals and separate dangerous rogue signals that could serve as jammers for an increasing number of wireless RF devices.
As the number of RF sensors increases for Internet of Things (IoT) applications as well as for such systems as unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs), data-driven machine learning may provide the means to quickly and effectively process many RF/microwave signals in an operating environment to prevent hacking, spooking, and disruption of desired RF-based services.
DARPA has contracted BAE Systems to develop machine-learning solutions to help sort real from rogue RF signals.
“The inability to uniquely identify signals in an environment creates operational risk due to the lack of situational awareness, inability to target threats, and vulnerability of communications to malicious attack,” says Dr. John Hogan, director of the Sensor Processing and Exploitation product line at BAE Systems. “Our goal for the RFMLS program is to create algorithms that will enable a whole new level of understanding of the RF spectrum, so users can identify and react to any signals that could be putting them in harm’s way.”
Under this Phase 1 contract, BAE Systems’ scientists intend to create machine-learning algorithms based on cognitive approaches that can identify and differentiate signals according to applications. The researchers intend to sort through signals in real time based on relative importance, so that interference and disruption of applications can be avoided.
The RFMLS program involves work on machine learning as well as artificial-intelligence (AI) research. BAE’s research will build on the company’s vast expertise in its autonomy technology portfolio. It adds to previous work involving machine learning and intelligence, including the DARPA Communications Under Extreme RF Spectrum Conditions (CommEX) and Adaptive Radar Countermeasures (ARC) programs. BAE Systems has also advanced to the second round of another major DARPA effort to bring machine learning and AI to the RF domain called the Spectrum Collaboration Challenge (SC2). Work on the RFMLS program will be performed at BAE’s facilities in Burlington, Mass. and Durham, N.C.
