A sliding mode control strategy based on RBF neural network was designed in order to solve the problem that the on-road firing of a vehicle-mounted machine gun would be affected by a series of nonlinear factors. Based on the strong robustness of sliding mode control, a real-time disturbance observer is used to accurately observe the disturbance, and the unique advantage of RBF neural network in nonlinear function approximation is used to approximate the uncertainties of the system, and an adaptive law is designed to ensure the asymptotic stability of the system. The switching gain is dynamically adjusted by RBF neural network to further suppress the chattering problem and the influence of nonlinear factors such as parameter change and external disturbance. The simulation results show that compared with the conventional sliding mode control, the proposed control strategy can effectively improve the stability control precision of the vehicle-mounted gun system.