RF Spectrum Operations Enhanced with Distributed AI-Assisted Sharing of Knowledge Sharing (RF-DASK)

STTR topic DAF27TZ02-DV005 (U.S. Department of Defense – Air Force), Phase I and II. Open to U.S. small businesses; STTR projects partner with a U.S. research institution. Opens: December 2, 2026. Closes: January 6, 2027. Current ES systems are designed to detect enemy electronic signals by extracting Pulse Descriptor Words (PDWs) from these signals. Modern radar systems used by adversaries increasingly employ Artificial Intelligence (AI) and it is becoming increasingly difficult to identify, characterize, and represent their waveforms using PDWs alone. To deploy effective Electronic Countermeasures (ECM), there is a need to develop novel methods, including machine learning (ML) [1,2] to enable dynamic and scalable data representation and compression methods that represent complex waveforms, which can be efficiently shared with other nodes in the network. The main goal of this project is to develop advanced techniques for dynamic and scalable signal representation to describe complex waveforms in a compressed format for radio frequency (RF) spectrum knowledge sharing and support network level information dissemination for emitter detection, classification and geolocation representative of activity segmentation [3]. Operational size, weight and power (SWaP) constraints should be determined to implement the proposed algorithms on hardware platforms and the developed techniques should be evaluated and demonstrated with hardware-in-the-loop experiments in relevant spectrum environments. Official solicitation: https://www.dodsbirsttr.mil/topics-app/