Signal Classification using Novel RF machine learning of PNT Interference in Contested spectrum Environments (SCORPION)

AiRANACULUS proposes Signal Classification using Novel RF machine learning of PNT Interference in Contested spectrum Environments  (SCORPION), which will meet and exceed the requirements of the Novel Position Navigation and Timing (PNT) Signal Classification Techniques project. SCORPION provides a generic and extensible antenna system architecture consisting of a complete hardware and software solution which provides a robust and resilient PNT operation by using state-of-the-art statistical signal processing and AI/ML assisted interference / spoofer detection and characterization. SCORPION provides highly effective interference detection and characterization tool that helps GNSS receivers to tactically choose the best configuration to minimize and mitigate various types of interferences.Performance of the interference detection and characterization is dependent upon interference types. Unintentional interferences, e.g., due to harmonics from malfunctioning transmitters, can generate out-of-band interference into GNSS bands disrupting extremely low received incident power of GNSS signals at or near -155 dBm. Intentional interferences include CW tones and narrowband interferers, typically used against GNSS modes available for commercial use and wideband interferers that disrupt military and commercial GNSS modes. Other interferer modulation formats include noise-modulated, tonal, chirp, PSK/FSK interferers, and so on. GNSS spoofers, in which GNSS-like signals are generated with timing and frequency offsets that trick the GNSS receiver into providing a false positioning. Spoofers can only target GNSS modes available for commercial use as the signal format is entirely known to the spoofer. Spoofers are known to have been deployed to record false locations in GNSS logs to hide locations of users engaging in illegal activities such as fishing in restricted waters. Lastly, GNSS meaconing attacks, in which true GNSS signals are recorded and transmitted with delays and/or frequency offsets that disrupt GNSS receivers or trick them into providing a false positioning/timing solution. Unlike spoofers, meaconing attacks can be deployed against military and commercial GNSS modes. To combat these diverse types of interferences, AiRANACULUS proposes a modular solution that consists of A. RF Front-end (RFFE) consisting of  B. Blind Source Separation and Interference / Spoofer Detection and Characterization (IDC), C. Interference Mitigation Techniques Selection (IMTS), D. Interference Mitigation (IM). SCORPION uses a hybrid and adaptive approach consisting of the best of both, statistical signal processing and machine learning to detect and characterize interference / spoofing. It is the classic Observe Orient Decide Act (OODA) loop, where IDC Module provides its decisions to the IMTS Module, which in turn orchestrates interference mitigation techniques (e. g., Adaptive Beamforming, Multi-tone Cancellation, Adaptive Filter-based Interference Excision).