Combined MPC and Dynamic Neural Network-Based UAVs Trajectory Tracking Control

Abstract

This paper focuses on the trajectory tracking problem of unmanned aerial vehicles (UAVs) under external disturbances, and a trajectory tracking method that combines model predictive control with dynamic neural networks was proposed. Firstly, the trajectory tracking problem is transformed into a constrained quadratic programming problem using the idea of model predictive control. Then, the kinematic constraints are taken into account, and control increment constraints and relaxation factors are designed in the objective function. A dynamic neural network is introduced to solve this quadratic programming problem in real-time. In addition, a disturbance compensation observer is designed to overcome external disturbances. Finally, numerical simulations are conducted to verify that the proposed tracking strategy reduces computational

Keywords

• External disturbances
• trajectory tracking
• dynamic neural networks
• model predictive control