Augmented Antenna Designs using AI/ML of Spectral and Spatial Degrees of Freedom, Smart Materials, and SWaP-C Constraints

We propose to use Artificial Intelligence/Machine Learning (AI/ML) to build augmented antenna systems to enable Picatinny fire control systems to respond to adverse electromagnetic (EM) environments.  AI/ML will be applied in the spectral domain to mitigate EM interference and optimize signal agility methods derived from techniques such as space-time adaptive processing (STAP) and cognitive radio.  AI/ML will also be applied in the spatial domain to find the source and signal strength of jammers and interference, using optimization techniques such as Particle Swarm Optimization (PSO), for a wide range of transmitter and receiver configurations.  Our antenna simulations include novel materials that protect antennas from EM interference and enable tunability in the antenna system, using existing research results available to us from the Army’s extensive previous investment in this research area, which gives our research a head start in optimizing material designs.  We propose to design and build lab prototypes during Phase 1 research that optimize Size, Weight, Power, and Cost (SWaP-C) constraints.  Our design uses a modular open systems architecture that can be integrated with Army ground vehicles and other assets.