基于机器学习的智能新能源汽车路径规划算法研究  

Research on Intelligent New Energy Vehicle Path Planning Algorithm

作　　者：潘丽 PAN Li(School of Electrical and Automation,Wuhu Institute of Technology,Wuhu Anhui 241000,China)

机构地区：[1]芜湖职业技术学院电气与自动化学院,安徽芜湖241000

出　　处：《佳木斯大学学报（自然科学版）》2024年第5期156-159,共4页Journal of Jiamusi University：Natural Science Edition

基　　金：安徽省高校自然科学研究重点项目(2023AH052386);芜湖职业技术学院智能控制教师教学创新团队(2023jxtd04)。

摘　　要：在网络技术飞速发展的今天,汽车行业发生了巨大的变化。自动驾驶技术已经成为当前的一个热门话题,在无人驾驶系统中,路径规划和避障是其中最为关键的技术部分。研究提出一种基于粒子群算法改进A*算法的路径规划技术,以便于解决乡村和城市道路中复杂的车辆路径规划问题。研究结果表明,该系统在采用改进的A*算法后,使用MATLAB试验经过21 ms后,改进的A*算法就到达预期的10-4的误差,又在市区复杂路段和农村复杂路段分别进行仿真试验,结果表明,改进的A*算法在节点选取方面比A*算法有显著提高,其拐点数量、路径平滑度等性能指标也均有明显改善作用,改进后的A*算法在搜索面积上有了很大的下降。综上可知,改进的A*算法更加适用于复杂路段的路径规划,能够有效提高车辆的避障性能。With the rapid development of network technology today,the automotive industry has undergone tremendous changes.Autonomous driving technology has become a hot topic at present,and path planning and obstacle avoidance are the most critical technical parts in unmanned systems.The study proposes a path planning technique based on particle swarm algorithm to improve the A*algorithm in order to facilitate the solution of complex vehicle path planning problems in rural and urban roads.The results of the study show that the system reaches the expected error of 10-4 after 21ms using Matlab tests with the improved A*algorithm,and simulations are carried out on complex urban and rural roads respectively,and the results show that the improved A*algorithm has a significant improvement over the A*algorithm in terms of node selection,and its number of inflection points,path smoothness and other.The improved A*algorithm has a significant improvement in node selection,the number of inflection points,path smoothness and other performance indexes,and the improved A*algorithm has a significant decrease in search area.In summary,the improved A*algorithm is more suitable for path planning of complex road sections and can effectively improve the obstacle avoidance performance of vehicles.

关 键 词：新能源汽车 路径规划 A*算法 粒子群算法 复杂路段 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]