Attitude control using an extended calssifier system algorithm for offline auto-tuning of a PID controller

Studies in air vehicles modeling and control have been increased rapidly recently. This paper presents the modeling and attitude control of a four rotor vertical take-off and landing (VTOL). The modeling of this vehicle will be described by using Euler-Newton equations. In order to stabilize VTOL vehicle and control the attitude of that, an intelligent technique based on eXtended Classifier System (XCS) algorithm that adjusts the PID controller gains, have been designed. The performance of this method is evaluated with Ziegler-Nichols method for tuning the PID controller Gains which is the most popular method for adjusting the PID parameters. Matlab Simulink has been used to test, analyze and compare the performance of the controllers in simulations. This study shows that although, both of the classical PID and the XCS auto-tuning PID controllers, can control the system properly, the second controller performed better than the classical PID controller. The designed control algorithm then are optimized for implementation in the microcontroller, taking the limitation of the hardware into account. The control algorithm are implemented in the test platform and evaluated.