In the current epoch of intelligent transportation, achieving high-precision tracking control for autonomous vehicles is a crucial challenge due to the presence of system nonlinearities, uncertainties, and communication constraints. Traditional continuous control methods often lead to excessive communication traffic, while existing adaptive control techniques struggle to ensure asymptotic tracking accuracy under these constraints. To address these issues, this paper investigates the problem of high-precision tracking control for intelligent vehicles by designing an event-triggered asymptotic composite neural tracking control scheme. In the proposed framework, radial basis function neural networks are employed to compensate for system nonlinearities and uncertainties. By introducing integral-bounded functions into both the control laws and adaptive laws, the asymptotic convergence of positional tracking errors is ensured through the adaptive backstepping approach. To reduce communication traffic, an event-triggered control strategy is implemented in the controller-to-actuator channel, where variable threshold-based triggering conditions are designed. Furthermore, to enhance the approximation capability of neural networks, composite learning is incorporated into the control design. A novel serial-parallel estimation model is established to generate prediction errors while simultaneously ensuring asymptotic stability. The stability of the overall system is rigorously analyzed using Lyapunov’s direct method and the Barbalat lemma. Finally, numerical simulations are conducted to validate the effectiveness and superiority of the proposed control scheme.