Direct Robust Adaptive Tracking Control of Electric Vehicles Based on Radial Basis Function Neural Networks

This paper proposes a direct robust adaptive tracking control scheme for the longitudinal motion of electric vehicles (EVs) subject to parametric uncertainties, nonlinear dynamics, and external disturbances. The vehicle's longitudinal dynamics are formulated as a second-order nonlinear system with unknown nonlinearities. Instead of identifying the system's unknown functions separately, a radial basis function neural network (RBFNN) is employed to directly approximate the ideal feedback control law, which is derived based on a sliding mode framework and Lyapunov synthesis. To enhance robustness against approximation errors and bounded disturbances, a robust adaptive law incorporating $\sigma$-modification is designed for updating the neural network weights online. The stability of the closed-loop control system is rigorously proved via Lyapunov theory, demonstrating that all signals remain uniformly ultimately bounded (UUB) and the tracking error converges to a small residual set around zero. The controller's performance is independent of the exact knowledge of the vehicle's nonlinear dynamics. Simulation results on a high-fidelity EV model confirm the effectiveness of the proposed controller in achieving accurate velocity tracking under various driving conditions and disturbances.