Adaptive Sliding Mode Control for Attitude and Altitude System of a Quadcopter UAV via Neural Network

In this article, a sliding mode control based on neural networks is proposed for attitude and altitude system of quadcopter under external disturbances. First, the dynamic model of the quadcopter is considered under external disturbances. Sliding mode controllers are then integrated with neural network algorithm to achieve the time-varying sliding surface; their coefficients in sliding surface are adjusted through backpropagation law. The disturbance observer is also combined with sliding mode controllers to estimate and handle the external disturbances. Finally, the Lyapunov theory is applied to validate the stability of suggested control method. The performance of proposed sliding mode control has been evaluated using a numerical simulation. The results show that the attitude and altitude controller based on suggested algorithm has a better tracking performance and disturbance rejection.

Automated summary

In this article, a sliding mode control based on neural networks is proposed for attitude and altitude system of quadcopter under external disturbances. By integrating sliding mode controllers with neural network algorithm and combining disturbance observer, the suggested control method shows better tracking performance and disturbance rejection in numerical simulations, indicating an improved stability of the quadcopter system.