不同车速下自适应变化的路径跟踪控制研究

Research on path tracking control of adaptive changes at different vehicle velocities

路径跟踪是自动驾驶汽车的核心技术,许多控制算法已被广泛应用于路径跟踪任务。为了提高路径跟踪在不同速度下的自适应能力,提出了一种结合预测轨迹和模糊控制的自适应Stanley路径跟踪控制器。参考人类驾驶员经验,模糊控制器根据车辆的横纵向速度实时调整预瞄距离,预测轨迹根据纵向速度实时调整预测时间进行提前控制。最后设计了自适应邻域的粒子群算法来对控制器参数进行优化。通过Simulink-CarSim的联合仿真验证,证明自适应Stanley控制器可以显著提高对不同速度的适应性和跟踪性能。

Path tracking is the core technology of autonomous vehicles,and many control algorithms have been widely used in path tracking tasks.In order to improve the adaptive ability of path tracking at different speeds,an adaptive Stanley path tracking controller that combines predictive trajectory and fuzzy control is proposed.Referring to the experience of human drivers,the fuzzy controller adjusts the preview distance in real time according to the horizontal and vertical speed of the vehicle,and the predicted trajectory adjusts the predicted time in real time according to the longitudinal speed to perform advance control.Finally,an adaptive neighborhood particle swarm optimization algorithm is designed to optimize the controller parameters.Through the co-simulation verification of Simulink-CarSim,it is proved that the adaptive Stanley controller can significantly improve the adaptability and tracking performance to different velocity.