A Coordinated Air Defense Learning System Based on Immunized Classifier Systems

Autonomous (unmanned) combat systems will become an integral part of modern defense systems. However, limited operational capabilities, the need for coordination, and dynamic battlefield environments with requirement timeless in decision-making are peculiar difficulties to be solved order realize intelligent control. In this paper, we explore application Learning Classifier System Artificial Immune models coordinated self-learning air particular, paper presents a scheme that implements autonomous cooperative threat evaluation weapon assignment learning approach. Taking into account uncertainties successful interception, target characteristics, type closed-loop behaviors, adopt hierarchical multi-agent approach coordinate multiple platforms achieve optimal performance. Based on combined strengths classifier system artificial immune-based algorithms, proposed consists two categories agents; strategy generation agent inspired by system, coordination mechanisms. An experiment realistic environment shows adopted hybrid can used learn weapon-target unmanned successfully defend against attacks. The presented results show potential approaches enabling adaptable collaborative