基于行车风险场的变邻域A^(*)算法车辆路径规划

Vehicle Path Planning Using Variable Neighborhood A^(*)Algorithm Based on Driving Risk Field

随着车辆智能化水平的飞速发展,为了满足智能车辆对全局路径规划的速度、平滑性和安全性要求,提出了一种基于行车风险势场的变邻域改进A*算法。首先对栅格地图的环境建模中加入必要安全空间和冗余安全空间,保留足够的行车安全裕度;为了提升环境适应性,基于车辆当前位置和目标点的位置关系,改进了启发函数的计算方式;同时结合行车风险势场对于车辆产生的合力,改进算法扩展搜索机制,引入了横纵向和斜向增扩策略,提升算法的搜索效率;完整路径规划算法完成后,通过冗余点剔除和动态切点光滑算法对路径进行二次处理,形成最终的平滑车辆路径。最后通过仿真实验进行算法对比,验证了改进算法对于智能车辆路径规划性能和行车安全性的提升。

With the rapid development of vehicle intelligence,a variable neighborhood improved A^(*)algorithm based on the driving risk field is proposed to meet the speed,smoothness,and safety requirements of intelligent vehicles for global path planning.Firstly,necessary safety spaces and redundant safety spaces are added to the environmental modeling of raster maps,while retaining sufficient driving safety margins;In order to improve environmental adaptability,the calculation method of the heuristic function was improved based on the relationship between the current position of the vehicle and the position of the target point;At the same time,combining the combined force of driving risk potential field on vehicles,the algorithm extension search mechanism is improved,and horizontal,vertical,and diagonal expansion strategies are introduced to enhance the search efficiency of the algorithm;After the completion of the complete path planning algorithm,the redundant points are removed and the dynamic tangent smoothing algorithm is used to perform secondary processing on the path,forming the final smooth vehicle path.Finally,algorithm comparison was conducted through simulation experiments to verify the improvement of the algorithm in intelligent vehicle path planning performance and driving safety.