Path Tracking Control of Fixed-Wing Unmanned Aerial Vehicle Based on Modified Supertwisting Algorithm

This paper focuses on the issues of low path tracking precision and weak disturbance rejection capability in fixed-wing unmanned aerial vehicle (UAV). This study designs a path tracking controller that combines the radial basis function (RBF) neural network and the supertwisting sliding mode control (STSMC) algorithm. The theoretical stability of the proposed controller is proved by using the Lyapunov theory. The research begins by establishing the motion model of the fixed-wing UAV. The designed controller, integrating the RBF neural network and STSMC, is implemented to enable the UAV to focus on accurately tracking the desired path. The RBF neural network is utilized to estimate and compensate for external disturbances within the model. Validation of the proposed approach is conducted through semiphysical simulation experiments, demonstrating that the designed control method can effectively enhance anti-interference ability and suppress chattering.