A formation control method of UAV Based on accelerated neural network
Weiqi Li, Zhaozi Zu, Yifei Pei · 2021 China Automation Congress (CAC) · 2021
This paper studies the cooperative control of multi-UAV formation. Based on the traditional PID algorithm, a cooperative flight control method based on accelerating neural network is proposed. Firstly, aiming at the low efficiency of traditional PID control algorithm, a PID controller based on neural network is proposed to improve the control accuracy and stability of the algorithm. In order to solve the problem of slow convergence speed of neural network, the momentum term and gradient factor are introduced to improve the convergence speed of the network, which significantly improve UAV formation flight dynamic response. The UAV formation simulation results show that the algorithm can improve the convergence efficiency of the original algorithm and also has certain robustness.