Flight Control System Design Optimisation via Genetic Programming

This chapter presents a methodology which is developed to design a controller that satisfies the objectives of shipboard recovery of a fixed-wing UAV. The methodology itself is comprehensive and should be readily applicable for different types of UAVs and various task objectives. With appropriate modification of control law representation, the methodology can be applied to a broad range of control problems. Development of the recovery controller for the UAV Ariel is a design example to support the methodology. This chapter focuses on adaptation of Evolutionary Algorithms for aircraft control problems. It starts from analysis of typical control laws and control design techniques. Then, the structure of the UAV controller and the representation of the control laws suitable for evolutionary design are developed. This is followed by the development of the general evolutionary design algorithm, which is then applied to the UAV recovery problem. Finally the presented results demonstrate robust properties of the developed control system.