DARPA funds earmarked for integration of machine-learning technology

The Defense Advanced Research Projects Agency (DARPA) has awarded a contract of up to $4.7 million to BAE Systems to integrate machine learning (ML) into platforms deciphering radio frequency signals.

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

“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.”

CHIMERA will enable ML software development to adapt the hardware’s Radio Frequency (RF) configuration in real-time to optimize mission performance, officials said, adding the capability has never before been available in a hardware solution, with the system providing multiple control surfaces for the user, enabling on-the-fly performance trade-offs maximizing 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.

BAE Systems officials said other RF functions within the realm of communications, radar, and electronic warfare can also benefit from the hardware platform, which has a reconfigurable array, front-end, full transceiver, and digital pre-processing stage.