A Modified RL-IGWO Algorithm for Dynamic Weapon-Target Assignment in Frigate Defensing UAV Swarms

Abstract

Unmanned aerial vehicle (UAV) swarms have significant advantages in terms of cost, number, and intelligence, constituting a serious threat to traditional frigate air defense systems. Ship-borne short-range anti-air weapons undertake terminal defense tasks against UAV swarms. In traditional air defense fire control systems, a dynamic weapon-target assignment (DWTA) is disassembled into several static weapon target assignments (SWTAs), but the relationship between DWTAs and SWTAs is not supported by effective analytical proof. Based on the combat scenario between a frigate and UAV swarms, a model-based reinforcement learning framework was established, and a DWAT problem was disassembled into several static combination optimization (SCO) problems by means of the dynamic programming method. In addition, several variable neighborhood search (VNS) operators and an opposition-based learning (OBL) operator were designed to enhance the global search ability of the original Grey Wolf Optimizer (GWO), thereby solving SCO problems. An improved grey wolf algorithm based on reinforcement learning (RL-IGWO) was established for solving DWTA problems in the defense of frigates against UAV swarms. The experimental results show that RL-IGWO had obvious advantages in both the decision making time and solution quality.