Adaptive neuro-fuzzy inference system based autonomous flight control of unmanned air vehicles

In this paper, an ANFIS (adaptive neuro-fuzzy inference system) based autonomous flight controller for UAVs (unmanned aerial vehicles) is described. To control the position of the UAV in three dimensional space as altitude and longitude–latitude location, three fuzzy logic modules are developed. These adjust the pitch angle, the roll angle and the throttle position of the UAV so that its altitude, the heading and the speed are controlled together. 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 six degree-of-freedom nonlinear generic manned/unmanned aerial vehicle models. To demonstrate the performance and potential of the controllers, the Aerosonde UAV model is used. Flight Gear open source flight simulator and Gauges Block Set are deployed in order to get visual outputs that aid the designer in the evaluation of the controllers. Steep turn maneuvers which are used for basic training of pilots are applied to test the performance of the fuzzy logic controllers. Despite the simple design procedure, the simulated test flights indicate the capability of the approach in achieving the desired performance.