改进A*算法融合DWA算法的自动驾驶路径规划  

PathPlanning of Automatic Driving Improved A* Algorithm Fused DWA Algorithm

作　　者：刘茜[1] 邱官升[1] 曾召余 LIU Qia;QIU Guansheng;ZENG Zhaoyu(Shaanxi communications vocational and Technical College,Xi’an 710018,China;Li Auto Inc,Beijing 101399,China)

机构地区：[1]陕西交通职业技术学院,西安710018 [2]理想汽车,北京101399

出　　处：《自动化与仪器仪表》2023年第2期32-36,41,共6页Automation & Instrumentation

基　　金：《“一心双环多点”模式下高职院校劳动教育研究与实践》(21GZ021)。

摘　　要：针对传统家用车自动驾驶时路径规划效果不佳的问题,提出基于改进A*算法融合DWA算法的自动驾驶路径规划算法,通过此算法,在道路拥挤状况下,能快速准确找到最佳路径。仿真结果表明,提出的改进7*7的A*算法在0.038 s时可找出一条距离为37.85 mm的最佳路径,相较于改进前的A*算法和改进5*5的A*算法,本算法的平滑性最好,可在最短时间内找出最短路径。对比于传统A*算法和改进7*7的A*算法,提出的融合算法规划路径最短为38.61 mm,所用时间最短。综合分析可知,融合算法可提高路径规划准确性、平滑性,路径规划效果更好,可在家用车领域进行应用。In view of the problem of poor path planning effect of traditional family vehicles, the automatic driving path planning algorithm based on improved A*algorithm and DWA algorithm is proposed. Through this algorithm can quickly and accurately find the best path under the condition of road congestion. Simulation results show that the proposed A*algorithm of 7*7 can find the best path with a distance of 37.85 mm at 0.038 s. Compared with the improved A*algorithm and the 5*5 algorithm, the algorithm has the best smoothness and can find the shortest path in the shortest time. Compared with the traditional A*algorithm and the improved 7*7 A*algorithm, the proposed fusion algorithm has the shortest planning path of 38.61 mm and the shortest time used. Comprehensive analysis shows that the fusion algorithm can improve the accuracy of path planning, smoothness and path planning effect, and can be applied in the field of family car.

关 键 词：深度学习 A*算法 DWA算法 自动驾驶 路径规划 

分 类 号：TP392[自动化与计算机技术—计算机应用技术]