Optimization of ANFIS controllers using improved ant colony to control an UAV trajectory tracking task

摘要

Development of unmanned aerial vehicles (UAVs) has become the most important research areas in the field of autonomousaeronautical control. This paper proposes a robust and intelligent controller based on adaptive-network-basedfuzzy inference system (ANFIS) and improved ant colony optimization (IACO) to govern the behavior of a three degreeof freedom quadrotor UAV. The quadrotor was chosen due to its simple mechanical structure; nevertheless, these typesof aircraft are highly nonlinear. Intelligent control such as fuzzy logic is a suitable choice for controlling nonlinear systems.The ANFIS controller is used to reproduce the desired trajectory of the quadrotor in 2D Vertical plane and theIACO algorithm aims is to facilitate convergence to the ANFIS’s optimal parameters in order to reduce learning errorsand improve the quality of the controller. To evaluate the performance of the proposed IACO tuned ANFIS controller, acomparison between the proposed ANFIS-IACO controller and other controller’s performance such us ANFIS only andproportional–integral–derivative controllers is illustrated using the same system. As expected, the hybrid ANFIS-IACOcontroller gives very satisfactory results than the others methods already developed in the same study.