Context-Aware RF Electromagnetic Surveying for Exploiting Signals of Opportunity

OUSD (R&E) CRITICAL TECHNOLOGY AREA(S): Trusted AI and Autonomy; Integrated Sensing and Cyber The technology within this topic is restricted under the International Traffic in Arms Regulation (ITAR), 22 CFR Parts 120-130, which controls the export and import of defense-related material and services, including export of sensitive technical data, or the Export Administration Regulation (EAR), 15 CFR Parts 730-774, which controls dual use items. Offerors must disclose any proposed use of foreign nationals (FNs), their country(ies) of origin, the type of visa or work permit possessed, and the statement of work (SOW) tasks intended for accomplishment by the FN(s) in accordance with the Announcement. Offerors are advised foreign nationals proposed to perform on this topic may be restricted due to the technical data under US Export Control Laws. OBJECTIVE: Develop a capability to use 3D environment models and RF propagation patterns to develop low-latency CNNs for RF geolocation and signal-type identification that can be run in parallel on low SWaP RF Electronic Spectrum Monitoring (ESM) antenna arrays for Class I and Class II UAS airframes. DESCRIPTION: Highly realistic and accurate 3D models are available for nearly all locations of our globe. These models often include coarse geometric and visible light (EO) information as textures. This project will develop algorithms that autonomously or semi-autonomously construct detailed 3D RF propagation models using available 3D geometry-and-texture, i.e., skinned, models of real-world locations. The resulting RF models will be used to develop context-specific AI technologies that estimate candidate 3D RF source locations and signal types from a low SWaP Ultra-Wide Band antenna array consisting of 4 antennas or less. Frequency ranges of interest for geolocation include 0.8 GHz - 6 GHz and solutions extending this range without sacrificing SWaP or performance are welcome. Geolocation approaches should be capable of detecting RF sources in complex multi-path environments where the strongest sensed signal may arrive to the sensor via direct-path propagation or propagation paths involving up to 2 bounces. Geolocation capabilities will be part of a larger Electronic Surveillance Monitoring (ESM) algorithm suite which can be deployed as downstream analysis capabilities for the payload. Algorithm suite capabilities can provide search, intercept, collect, classify, geolocate, monitor, copy, and exploit capabilities. PHASE I: Performer shall conduct and report on a feasibility study, survey of relevant technologies, and prototype algorithms that demonstrate an ability to deploy context-specific RF geolocation algorithms inside a 16 hour window that outperform competing approaches in terms of either accuracy and computational complexity or the SWaP of the required payload specifications. Applications should be capable of being run in Zynq Ultrascale+ RFSoC hardware in parallel and deployable as a payload to Class I and Class II UAS. PHASE II: Building upon their Phase I, Performer shall implement a selected algorithm and approach. Deliver a prototype payload that can be integrated with a UAS that demonstrates the conceptual design of Phase I. Evaluate the performance of the prototype for direct-path, single-bounce and double-bounce geolocation contexts and geolocate targets including those that may exist in low-impedance indoor locations, e.g., inside windows. PHASE III DUAL USE APPLICATIONS: Phase III efforts transition the prototype technology of Phase II to a fully-developed technology for use as a commercial or warfighter solution. A viable business model for the developed technology must be demonstrated through the performer or in partnership with other contractors. Transition partners would be in a position to supply this capability and future realizations to the Air Force and other DoD entities. REFERENCES: N211-091 Real-time Simulation of Radio Frequency (RF) Signal Returns from Complex Targets and Backgrounds, Phase I, 2021; Willis, A., Hossain, M., Godwin, J, Hardware-accelerated SAR simulation with NVIDIA-RTX technology, SPIE Defense and Commercial Sensing: Algorithms for Synthetic Aperture Radar Imagery XXVII, 2020; Martian, A. Real-time spectrum sensing using software defined radio platforms. Telecommun Syst 64, 749 761, 2017; Mansfield, T.O., Ghita, B.V. & Ambroze, M.A. Signals of opportunity geolocation methods for urban and indoor environments. Ann. Telecommun. 72, pp. 145 155, 2017; E. Kupershtein, M. Wax, and I. Cohen, Single-site emitter localization via multipath fingerprinting, IEEE Transactions on Signal Processing, vol. 61, no. 1, pp. 10 21, 2013; B. R. Phelan, Location of GSM transmitters in an urban environment via unique multipath characterizations, The Pennsylvania State University, State College, Pa, USA, 2012.; KEYWORDS: Geolocation; RF source models; Electronic Surveillance Monitoring; context-specific RF geolocation