Robust Multi-objective Optimization Based on NSGA-II for UCAV Weapon Delivery

Abstract

The problem of generating robust optimal air-to-ground weapon delivery planning (WDP) for UCAVs is studied. In order to deal with the uncertainties in combat operation, such as disturbing in battlefield, model imprecise, operating errors and so on, a strategy based on robust multi-objective optimization (RMO) approach is proposed. In this paper, several constraints include flight capability constraint, weapon constraint and battlefield constraint, are considered. And some robust optimal cost functions are built, using Monte Carlo method simulating criteria of weapon delivery, and then the weapon delivery planning problem is transformed into a robust multi-objective optimization problem. In order to improve the convergence performance, a combining robust multi-objective optimization algorithm based on an improved NSGA-II and Monte Carlo simulation is designed, and then a tactical basic flight maneuver (BFM) is presented to generate weapon delivery trajectory. The proposed approach is demonstrated on a typical air-to-ground attack mission scenario. The simulated results show that the proposed approach is capable of generating the robust and optimal weapon delivery trajectories efficiently.