Neural Network-based Adaptive Backstepping Controller for UAV Quadrotor system

The aim of this paper is to design a neural network based adaptive backstepping controller (NN-ABC) for altitude and attitude control of a quadrotor system under uncertainties and disturbances. A radial basis function neural network (RBFNN) used as an approximator of nonlinear functions is included in classical backstepping control (BC) to solve the unknown dynamics problem. Also, a robust control term is added to improve the performances in tracking a reference signal when parametric uncertainties and disturbances exist. Design and stability of the closed-loop system is realized by Lyapunov method in a step by step procedure. Simulation results of the proposed NN-ABC are compared with those of the classical proportional-integral-derivative (PID) controller and backstepping controller (BC). The proposed NN-ABC achieves good tracking performance and robust control law to deal with parametric uncertainties and disturbances than the classical PID and BC controllers.

• quadrotor
• adaptive backstepping control
• neural network control
• radial basis function neural network
• altitude control
• attitude control
• parameter uncertainty
• disturbance rejection
• robust control
• Lyapunov stability
• tracking performance

• Adaptive Control of Nonlinear Systems
• Control and Dynamics of Mobile Robots
• Advanced Control and Stabilization in Aerospace Systems
• quadrotor
• adaptive backstepping control
• neural network control
• radial basis function neural network
• altitude control
• attitude control
• parameter uncertainty
• disturbance rejection
• Control and Systems Engineering
• Aerospace Engineering
• Engineering