DARPA Funding Brings Machine Learning to BAE’s Signals Intelligence Capabilities

HUDSON, N.H.
— BAE Systems has been awarded funding from the Defense Advanced Research
Projects Agency (DARPA) to integrate machine-learning (ML) technology into
platforms that decipher radio frequency signals, the company said in a July 8
release.

Its
Controllable Hardware Integration for Machine-learning Enabled Real-time
Adaptivity (CHIMERA) solution provides a reconfigurable hardware platform for
ML algorithm developers to make sense of radio frequency (RF) signals in
increasingly crowded electromagnetic spectrum environments.

The up-to-$4.7
million contract, dependent on successful completion of milestones, includes
hardware delivery along with integration and demonstration support. CHIMERA’s
hardware platform will enable algorithm developers to decipher the ever-growing
number of RF signals, providing commercial or military users with greater
automated situational awareness of their operating environment. This contract
is adjacent to the previously announced award for the development of data-driven
ML algorithms under the same DARPA program (Radio Frequency Machine Learning
Systems, or RFMLS).

RFMLS
requires a robust, adaptable hardware solution with a multitude of control
surfaces to enable improved discrimination of signals in the evolving dense
spectrum environments of the future.

“CHIMERA
brings the flexibility of a software solution to hardware,” said Dave Logan,
vice president and general manager of Command, Control, Communications,
Computers, Intelligence, Surveillance, and Reconnaissance (C4ISR) Systems at
BAE Systems. “Machine learning is on the verge of revolutionizing signals
intelligence technology, just as it has in other industries.”

In an
evolving threat environment, CHIMERA will enable ML software development to
adapt the hardware’s RF configuration in real time to optimize mission
performance. This capability has never been available in a hardware solution.
The system provides multiple control surfaces for the user, enabling on-the-fly
performance trade-offs that can maximize its sensitivity, selectivity and
scalability depending on mission need. The system’s open architecture
interfaces allow for third party algorithm development, making the system
future-proof and easily upgradable upon deployment.

Other RF functions —
including communications, radar and electronic warfare — also can benefit from
this agile hardware platform, which has a reconfigurable array, front-end, full
transceiver and digital pre-processing stage. Work on these phases of the
program will take place at BAE Systems’ sites in Hudson and Merrimack, New
Hampshire, and Dallas.