In response to the US Navys solicitation for an Unmanned Air Vehicle (UAV) support capability to assists Manned-Unmanned Teaming to challenge and/or negate enemy radar and radar networks, we propose RANGER: Robust Autonomy for NeGation of Enemy Radar, a modular software solution designed to increase mission efficiency and survivability by adapting negation techniques on-the-fly in response to agile enemy waveforms and dynamic enemy radar behavior. RANGER agents are equipped with a multi-task learning based counter-radar intelligence module that provides agents with a common electromagnetic operating picture and an intelligent radar defeat engine that computes both single agent and coordinated defeat methods tailored to the specific threat. Operating in conjunction with the two previous modules is RANGERs federated learning technique, enabling fast adaptation and behavior change to varying mission conditions, which provides the framework with the requisite battlefield agility to defeat the dynamic radar networks of the future.
Benefit: RANGER offers the Navy a generalizable and modular electronic warfare autonomy solution for UAV support of MUM-T operations. RANGER, by design, is applicable to many MUM-T operations requiring the negation of enemy radar and radar networks. RANGERs improved learning and radar defeat architecture will allow for dynamic and robust UAV radar negation in the field, allowing for faster adaptation to dynamic threats and mission scenarios by continuously learning to enhance and customize defeat methods throughout the mission. Further, on-the-fly learning will allow for reuse of the RANGER framework across many different types of missions, eschewing the need to swap out pre-determined swarm plays that may fail when presented with a new scenario. RANGER is also anticipated to make beneficial impacts in non-military industries, including the infrastructure, insurance, first responder, and public safety industries. For the infrastructure and insurance industries, a team of UAVs can provide surveillance and progress/damage assessments on assets, leading to reductions in building costs, improved claim assessment, and proactive damage mitigation. Importantly, RANGERs solution will allow for deployment even in contested electromagnetic environments. For the public safety and first responder industries, RANGER could be used to negate civilian radar threats used in an adversarial manner against first responders. RANGER technology would provide the means to defeat such threats that emerge in densely populated areas with congested electromagnetic environments. Lastly, RANGER agents could be used in a more general, 6G swarm technology, delivering service to users through aerial base stations, all while adapting network topology and behavior to provide optimal quality of service.
Keywords: Radar Negation, Radar Negation, Reinforcement Learning, multi-task learning, Federated Learning
