Exploitation of Self Organization in UAV Swarms for Optimization in Combat Environments

This investigation focuses primarily on the development of effective target engagement for unmanned aerial vehicle (UAV) swarms using autonomous selforganized cooperative control. This development required the design of a new abstract UAV swarm control model which flows from an abstract Markov structure, a Partially Observable Markov Decision Process. Self-organization features, bio-inspired attack concepts, evolutionary computation (multi-objective genetic algorithms, differential evolution), and feedback from environmental awareness are instantiated within this model. The associated decomposition technique focuses on the iterative deconstruction of the problem domain state and dynamically building-up of self organizational rules as related to the problem domain environment. Resulting emergent behaviors provide the appropriate but different dynamic activity of each UAV agent for statistically accomplishing the required multi-agent temporal attack task. The current application implementing this architecture involves both UAV flight formation behaviors and UAVs attacking targets in hostile environments. This temporal application has been quite successful in computational simulation (animation) with supporting statistical analysis.