Intelligent active disturbance rejection controller based on adaptive neuro fuzzy inference system for the quadrotor system

Abstract Quadrotor systems, a key type of Unmanned Aerial Vehicle (UAV), are renowned for their agility and versatility, making them invaluable in both civilian and military applications. Despite these advantages, the high coupling, under-actuation, and nonlinearity of their dynamics present significant challenges in accurate modeling and control. Among the critical control tasks, attitude stabilization—controlling the roll, pitch, and yaw angles—is the fundamental prerequisite for ensuring the overall stability and maneuverability of a quadrotor. Active Disturbance Rejection Control (ADRC) provides a robust framework by using an Extended State Observer (ESO) to estimate and compensate for uncertainties and external disturbances in real-time. However, traditional nonlinear ADRC (NLADRC) requires extensive parameter tuning, and while Linear ADRC (LADRC) simplifies implementation, it often struggles in highly nonlinear environments. This paper proposes an Intelligent Active Disturbance Rejection Control (IADRC) approach that combines the simplicity of the linear ESO with the adaptive, nonlinear capabilities of an Adaptive Neuro-Fuzzy Inference System (ANFIS) as the state error feedback controller. The proposed method retains the simplicity of LADRC while enhancing robustness and adaptability, significantly reducing the need for manual parameter tuning. Simulation results demonstrate that the proposed IADRC framework achieves substantial improvements in stabilizing the quadrotor’s attitude dynamics, providing a critical advancement for UAV control systems.