UAV Adaptive Control Laws Using Non-Linear Dynamic Inversion Augmented with an Immunity-based Mechanism

In this paper, a novel adaptive flight control system is presented, designed to handle failures and malfunctions of aircraft sub-systems as well as general environmental upset conditions. The proposed control laws use a non-linear dynamic inversion approach augmented with an artificial immune system mechanism that relies on a direct compensation inspired primarily by the biological immune system response. This work is an extension of a recently developed artificial immune system-based architecture which implements negative and positive selection algorithms for aircraft fault detection, identification, and evaluation within a hierarchical multi-self scheme. The effectiveness of the approach is demonstrated through simulation examples within the West Virginia University unmanned aerial vehicle simulation environment. The performance of the control laws is evaluated in terms of trajectory tracking errors and control activity during autonomous flight in the presence of atmospheric disturbances and actuator failures. The results show that the proposed fault tolerant adaptive control laws significantly improve the tracking performance of the vehicle at nominal conditions and under a variety of abnormal flight conditions.