SRI International eyes artificial intelligence (AI) reconfigurable processors for EW and communications

ARLINGTON, Va. – U.S. military researchers needed to develop high-throughput streaming-data processors that reconfigure themselves within 50 nanoseconds for advanced RF applications in radar, communications, and electronic warfare (EW). They found their solution from SRI International in Menlo Park, Calif.

Officials of the U.S. Defense Advanced Projects Agency (DARPA) in Arlington, Va., announced a $14.4 million contract to SRI International last week for the Processor Reconfiguration for Wideband Sensor Systems (PROWESS) project.

SRI International joins the University of Southern California (USC) in Los Angeles on the PROWESS project. USC won a $9 million contract for the project in August.

On the PROWESS contract, SRI International and USC researchers will try to develop reconfigurable processors that provide autonomous RF and microwave systems with situational awareness about complex and uncertain electromagnetic environments.

Related: DARPA to revolutionize high-end IC design for military and aerospace uses

PROWESS aims at RF autonomy, where radios use artificial intelligence (AI) to sense the spectrum and adapt to the environment. RF autonomy can help resist the effects of radio interference and improve the capacity of the spectrum to accommodate an increasing number of transceivers.

Although the preferred processors for today’s autonomous radios are field programmable gate arrays (FPGAs), signal environments can change in nanoseconds, which is far faster than FPGAs can reprogram. What are necessary are new classes of receiver processors.

PROWESS aims to develop high-throughput, streaming-data processors that reconfigure in real time to detect and characterize RF signals. Through processors that self-reconfigure within 50 nanoseconds, PROWESS will enable real-time synthesis of processing pipelines in uncertain environments.

PROWESS will help enable future radio receivers to optimize performance to measured spectrum conditions and the needs of cognitive RF decision logic.

Related: DARPA funds software to coordinate battlefield operations

High-throughput streaming-data processors can enable just-in-time synthesis of receiver processing pipelines in uncertain environments where pre-programmed solutions are likely to fail, DARPA researchers say.

PROWESS is expected to combine emerging high-density reconfigurable processing arrays with embedded real-time schedulers to expose new architectural tradeoffs that deliver fast program switching and high-compute density.

Commercial and military demands on the electromagnetic spectrum (EMS) are driving radio frequency (RF) systems to operate in increasingly congested and complex environments, researchers explain. Spectrum sensing in these conditions drives the demand for edge processing beyond the capacity of today’s devices.

Related: Enabling technologies for image and video processing

The PROWESS project seeks create reconfigurable processors to improve RF autonomy by enhancing spectrum sensing, which enables RF systems to optimize to actual spectrum conditions and react to interference in real time, DARPA researchers say.

These kinds of computer architectures potentially offer significant benefits for spectrum sensing and related applications, particularly when systems must operate in dynamic and sometimes-confusing environments. PROWESS expects to focus on the development of runtime reconfigurable processing hardware and support software.

For more information contact SRI International online at www.sri.com, USC at https://today.usc.edu/tag/research/, or DARPA at www.darpa.mil/news-events/2022-10-06.