The U.S. Army Combat Capabilities Development Command has worked with the Virginia Polytechnic Institute and State University and the Army Research Laboratory to create an automatic method for military radar systems to function in operational environments that are congested and have limited spectrum.
Researchers applied machine learning to understand interference activity as part of a project to explore spectrum sharing between Department of Defense radars and commercial communications equipment, the military branch said Wednesday.
The research, titled “Deep Reinforcement Learning Control for Radar Detection and Tracking in Congested Spectral Environments,” was published in the IEEE Transactions on Cognitive Communications and Networking journal.
Anthony Martone, an Army researcher, said the approach has the potential to help military personnel use a radar technology to detect targets at an extended range without experiencing interference.
The project is part of a broader DoD initiative to facilitate the autonomous behavior of software-based radars with machine learning and adaptive signal processing algorithms.
