Award

Rapid Emitter Geolocation with Adaptive Learning (REGAL) introduces a transformative approach to radio frequency (RF) signal identification and emitter geolocation in urban settings, utilizing local 3D models of buildings and terrain to train context-specific neural networks that calculate emitter position based on multi-path effects of the received signal. These neural networks are designed for low-latency and rapid deployment on Group 1 and Group 2 unmanned aircraft system (UAS), and are trained through extensive RF simulations that leverage NVIDIA ray-tracing techniques for highly detailed signal trajectories and multi-bounce effects within the physical environment. As the cornerstone of a comprehensive Electronic Surveillance Monitoring (ESM) suite, REGAL's capabilities extend to searching, intercepting, collecting, classifying, monitoring, copying, and exploiting RF signals. Optimized for dense urban landscapes, REGAL stands to significantly enhance operations in surveillance, emergency response, law enforcement, and urban infrastructure management. During this Phase II activity we will: (1) develop a containerized software application for gathering offline 3D models, performing RF simulation, and training the geolocation neural network, (2) develop a run-time optimized RF processor for use on low size, weight, and power (SWaP) platforms, and (3) physically construct a REGAL payload and evaluate it via flight testing on a Group II UAS platform.