Adaptive neuro fuzzy inference systems (ANFIS) approach for autonomous flight control of unmanned aerial vehicles

Abstract

This thesis concentrates on an ANFIS based, autonomous flight controller that has generalization capability, for UAVs (Unmanned Aerial Vehicle). Three different ANFIS modules are developed in order to control of the altitude, the speed and the roll angle through which the altitude and the latitude-longitude of the air vehicle is controlled. Then all these responses are compared to the responses of other two alternative control mechanisms called conventional PID and PID type fuzzy controllers. The implementation framework utilizes MATLAB’s standard configuration and the Aerosim Aeronautical Simulation Block Set which provides a complete set of tools for rapid development of detailed 6 degree-of-freedom nonlinear generic unmanned aerial vehicle models. The Aerosonde UAV model is used in the simulations in order to demonstrate the performance and the potential of the controllers. The simulated test flights indicate the capability of the approaches in achieving the desired performances but proposed ANFIS architecture shows a better performance than the other two methods.