Robust neuroadaptive trajectory tracking for quadrotor UAV based on non-singular terminal sliding mode control

The quadrotor UAV is an underactuated, strongly coupled, and highly unstable nonlinear system. In order to address the issue of external interference during the actual flight of the quadrotor UAV and enhance the accurate trajectory tracking effect under system parameter perturbations, a trajectory tracking algorithm based on neural networks and terminal sliding mode control is designed. A non-singular neural network is utilized to approximate the unknown terms in the system. A low-pass filter is introduced to avoid differential operations and filter noise in the parameters. To ensure the robustness of the system, a terminal sliding mode controller is designed, and an adaptive parameter estimation method is developed to mitigate the system’s chattering phenomenon. Consequently, the system state can track a given desired signal more accurately. The stability of the designed controller is proven using the Lyapunov stability theorem. Taking a quadrotor UAV as an example, the validity and reliability of the proposed method are verified through computer simulations.