Model Reference Adaptive Control and Neural Network Based Control of Altitude of Unmanned Aerial Vehicles

The objective is to develop a new control strategy for quadrotor types of unmanned aerial systems that assist in closing the existing research gaps between the undesired uncertainties and current control systems. This paper investigates two modeling systems and the accuracy of error elimination and adaptation in the change of the plant/system's output. The Model Reference Adaptive Controller is a high order of adaptive control. This common fixed parameter has a proportional-integral-derivative for aircraft pitch attitude control. The Model Reference Neural Network Controller is used to the aircraft height altitude control. A disturbance in the system is introduced to test and evaluate the response performance by using the Model Reference Adaptive Controller to observe high-performance tracking in the presence of uncertainties. MATLAB System Identification Tool is used to attain the height altitude model, without disturbance, for the Unmanned Aerial Vehicle. System identification uses a neural network to capture the behavior of system dynamics, which assists the neural network to train itself to act as a controller. Moreover, the performance of the controllers were tested using simulations to demonstrate and to improve the speed and stability of the response for the two dynamic systems.