Modeling on Self-Learning Driver Model under Extreme Driving Conditions

Ensuring the safe and stable operation of autonomous vehicles under extreme driving conditions requires the capability to approach the vehicle’s dynamic limits. Inspired by the adaptability and trial and error learning ability of expert human drivers, this study proposes a Self-Learning Driver Model (SLDM) that integrates trajectory planning and path tracking control. The framework consists of two core modules: In the trajectory planning stage, an iterative trajectory planning method based on vehicle dynamics constraints is employed to generate dynamically feasible limit trajectories while reducing sensitivity to initial conditions; In the control stage, a neural network enhanced nonlinear model predictive controller (NN-NMPC) is designed, which incorporates a self-learning mechanism to continuously update the internal vehicle model using trial-and-error data on top of mechanistic physical constraints, thereby improving predictive accuracy and path-tracking performance. By combining mechanistic modeling with data-driven learning, SLDM reduces dependence on precise parameter calibration and progressively approaches the vehicle’s dynamic limits. Simulation results demonstrate that in high-speed double lane-change scenarios, SLDM achieves stable operation at speeds up to 130 km/h and significantly outperforms conventional Pacejka based NMPC in terms of path-tracking accuracy and robustness. These findings validate SLDM as a universal and adaptive high-performance driver model capable of achieving accurate and stable control under extreme conditions.