基于逆问题求解的汽车操纵性能优化

OPTIMIZATION OF VEHICLE MANEUVERABILITY BASED ON SOLUTION TO INVERSE PROBLEMS

给出一种基于逆问题求解的人-车-路闭环系统操纵性能优化的方法。利用径向基函数神经网络建立了汽车侧向位移与方向盘转角及其它响应之间的映射关系,由跟踪路径反求出方向盘转角及汽车的其它响应,进而计算闭环系统的操纵性能评价指标并进行优化。该方法是在不同汽车方案具有相同实际行驶路径的基础上对操纵性能进行分析并优化,从而得到的最优汽车方案在跟踪某一典型路径时具有最好的操纵性能。

Based on solution to inverse problems,an optimization approach is proposed for the purpose of improving maneuverability of a driver-vehicle-road closed-loop system.The mapping relationship between the vehicle lateral displacement and the steering wheel angle as well as other responses can be found utilizing radial basis function(RBF) neural networks.One prescribed path is taken as input of the trained RBF neural network,then the steering wheel angle and other vehicle responses can be identified and the maneuverability index of the closed-loop system can be obtained and optimized.It can be seen that based on the inversion solution study,different vehicle configurations have the inherent ability to follow the same prescribed path,and therefore the optimal vehicle configuration has the best maneuverability among all vehicle configurations when they follow some typical path.