Research on Intelligent Vehicle Path Planning Based on Improved Artificial Potential Field Method

In this paper, the path planning algorithm and motion control technology of intelligent vehicles are studied. The artificial potential field method is selected for research. The distance parameter between the vehicle and the target point is introduced to solve the problem of target unreachability in the traditional potential field method. The boundary repulsion potential field is established to limit the range of vehicle motion. The repulsion potential field function of obstacles is optimized to solve the problem of target unreachability in the traditional potential field method. Considering the dynamic characteristics of the vehicle during driving, the vehicle dynamics model is taken as the control object, and the vehicle monorail model is combined with the tire cornering model. In an environment where obstacle information is unknown, to ensure the safety of vehicle driving, the decision-making layer needs to plan a safe collision free path. In order to ensure the stability of trajectory tracking, a vehicle motion controller based on model predictive control theory is designed. Finally, the performance of the motion controller under different working conditions is analyzed in the Simulink/CarSim joint simulation environment. The results show that the controller has good adaptability and robustness for tracking reference trajectory under different road adhesion conditions and different vehicle speeds. In order to further prove the effectiveness of the established model predictive control theory based autonomous steering controller, this paper compares another commonly used PID controller, and compares their tracking effects on the double lane change trajectory under the same working conditions. The research results show that the model predictive controller designed in this paper can control the driving stability and riding comfort of vehicles better.