BAE to Help DARPA Build Machine Learning Tools for RF Signal Detection

BAE Systems has received a $9.2M contract from the Defense Advanced Research Projects Agency to develop data-based machine learning algorithms for military and commercial users to identify radio frequency signals in different operating environments.

The company said Tuesday it will use cognitive approaches to create signals differentiation tools under the first phase of DARPA’s Radio Frequency Machine Learning System program.

DARPA looks to utilize machine learning to address the challenge of detecting and identifying an adversary’s signal in the field due to the increased number of connected devices such as phones, sensors and drones.

“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,” said John Hogan, director of BAE’s sensor processing and exploitation product line.

Under the contract, the company’s scientists will develop algorithms that rely on machine learning techniques to differentiate enemy and allied signals as well as important and unimportant signals in real-time.