基于全局导向的智能车辆路径规划融合算法研究

Research on Global Oriented Path Planning Fusion Algorithm for Intelligent Vehicles

针对曲线道路的路径规划问题,本文提出一种基于全局导向人工势场法的路径规划融合算法。考虑持续转弯的弯曲道路工况,构建基于变形栅格的栅格地图;考虑道路环境中的行车风险,基于行车风险场理论优化A^(*)算法启发函数从而改进A^(*)算法。改进传统人工势场法的局限性及固有缺陷,在局部路径规划中考虑自车、环境车辆及障碍物的轮廓形状,引入全局导向路径进一步改进人工势场法。以改进A^(*)算法规划路径为全局最优导向路径,设计基于改进人工势场法的路径规划融合算法。仿真结果表明,提出的融合算法可以生成有效的行驶路径,与数据集提取的实车路径接近,且在障碍物环境中规划的路径安全高效,满足车辆的行驶要求。

For the problems of path planning on curved roads,a path planning fusion algorithm based on global oriented artificial potential field method is proposed in this paper.Considering the curved road conditions,a grid map based on deformed grid is constructed.Considering the driving risk in the road environment,the heuristic function of A^(*)algorithm is optimized based on the driving risk field theory.To improve the limitation and inherent defects of the traditional artificial potential field method,in view of the outline shapes of the subject vehicle,environment vehicles and obstacles,the artificial potential field method is improved as the local path planning method by introducing in the globally guided path.Taking the path planned by the improved A^(*)algorithm as the global optimal guided path,the path planning fusion algorithm is designed based on the improved artificial potential field method.The simulation results show that the proposed fusion algorithm can generate effective and reasonable driving path,which is close to the real vehicle path extracted from the dataset.Moreover,the path planned in the environment with obstacles is safe and efficient,meeting the driving requirements of the vehicle.