Path tracking control cannot effectively satisfy the stability requirements of intelligent vehicles under large curvature conditions. To solve this problem, an adaptive preview distance path tracking controller with a hierarchical structure is proposed in this study. The vehicle centroid lateral acceleration and lateral error of the preview point are taken as the inputs of the upper controller, and the optimal preview distance is obtained based on fuzzy inference. To eliminate the subjective influence of the membership function and fuzzy rule selection in the fuzzy controller design, a genetic algorithm is used for optimization. The lower controller is a sliding mode controller that aims to achieve intelligent vehicle self-tracking. Moreover, a radial basis function neural network is adopted to combine with the sliding mode controller to eliminate output chattering. However, adaptive adjustment of the preview distance deteriorates the vehicle directional tracking error, which makes controlling the vehicle at the road curvature switching point difficult. Thus, a directional error compensation controller is designed based on the iterative learning theory to compensate the front wheel steering angle. Simulations under two standard conditions are carried out to verify the control effect. The results show that, in a double lane change test, the peak centroid acceleration and coaxial load transfer rates decreased by 26.91% and 19.83% at low velocity, respectively, and the improvements at high velocity were 42.71% and 39.22%, respectively. In the pylon course slalom test, all three performance indicators decreased by more than 30%, which indicates the modified adaptive preview distance path tracking controller with a hierarchical structure can effectively improve the vehicle handling performance and roll stability and can ensure the tracking accuracy.