Lane Changing Control of Autonomous Vehicle With Integrated Trajectory Planning Based on Stackelberg Game

Lane changing present a significant challenge for autonomous vehicles, as they must maintain safe driving and optimize time efficiency. This process is strongly affected by traffic environment and driver characteristics. This paper proposed a lane changing control method based on Stackelberg game theory, integrating lane changing decision and trajectory planning while comprehensively considering the driver’s characteristics and the traffic environment. Firstly, considering the common characteristics of lane changing decision and trajectory planning, the two stages are integrated using the leader-follower game theory, enhancing the accuracy of lane changing decisions. Secondly, the cooperative game theory model is employed to design an adaptive weight adjustment strategy for the trajectory tracking controller. The weight coefficients for vehicle stability and path tracking accuracy are dynamically adjusted within the model predictive control method to adapt to the vehicle’s stability state. Simulation results indicate a 24% improvement in decision-making accuracy with the proposed leader-follower game decision method over the rule-based lane changing model. The average relative error in lateral displacement, comparing the vehicle’s actual trajectory to the planned one, is reduced by 6%. Additionally, the variable-weight trajectory tracking control enhances overall tracking performance by over 30% in scenarios involving high speeds and low adhesion. These findings verify the proposed vehicle lane changing method notably improves lane changing safety, stability, and precision.