AI-Informed Algorithms Combined with Differential Game Theory to Support Swarm-on-Swarm Engagements

Swarms are becoming a threat to warfighters across all operating domains due to their non-traditional, unpredictable tactics and the advantage of mass and decentralization. Counter-swarm tactics are an emerging field, and missile defense systems must evolve to respond to potential threats from swarms operating in the hypersonic regime. Developing algorithms, methods, and concepts to guide assets in swarm-on-swarm engagements is essential to defend targets from incoming hypersonic swarm threats. By utilizing artificial intelligence and machine learning (AI/ML) algorithms, Infinity Labs, in partnership with University of Cincinnati, propose a method that will enable large-scale swarm and counter-swarm defensive strategies. Phase I efforts include a feasibility study with MS&A of proposed algorithms that combine target-attacker-defender DGT optimal control strategies with nature-inspired optimization and deep learning classification for weapon target assignments (WTA). Approved for Public Release | 24-MDA-11673 (8 Jan 24)