Answers are grounded in this paper and cite their sources.
Numerical simulations and experiments demonstrate improved path tracking accuracy in autonomous vehicles using adaptive control.
The uncertainty of the steer-by-wire (SbW) system and external disturbance during path tracking may lead to lateral position deviation of the vehicle, making it challenging to realize high-precision path tracking control. Therefore, this paper proposes an adaptive neural network controller with an integrated SbW system. Firstly, the SbW system model and vehicle dynamics model are integrated into a strict feedback model. Then, an adaptive neural network approximator and a disturbance observer are designed to estimate the nonlinear friction and the unknown disturbance. Next, based on the backstepping control, a barrier Lyapunov function is introduced to constrain the tracking error, thereby improve the tracking accuracy. Finally, a rigorous stability analysis based on Lyapunov stability theory is carried out to ensure that all signals of the closed-loop system are bounded. The results of numerical simulations, hardware-in-the-loop (HIL) experiments and, real-vehicle experiment show that the proposed method has good control performance. The proposed method achieves a good control effect, with the maximum lateral position error is reduced to 0.18 m in the real-vehicle experiment. The scheme can provide theoretical reference for the control practice of autonomous vehicles.
No takes yet. Share an insight, caveat, or question.
Ye et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: