基于改进人工势场法的避障路径规划研究  

Research on obstacle avoidance path planning based on improved artificial potential field method

作　　者：纪苏宁 曹景胜[1] 刘世江 李刚[1] JI Suning;CAO Jingsheng;LIU Shijiang;LI Gang(College of Automobile and Traffic Engineering,Liaoning University of Technology,Jinzhou 121001,China)

机构地区：[1]辽宁工业大学汽车与交通工程学院,辽宁锦州121001

出　　处：《现代电子技术》2025年第1期117-122,共6页Modern Electronics Technique

基　　金：国家自然科学基金项目(51675257);国家自然科学基金青年基金项目(51305190);辽宁省教育厅基本科研项目面上项目(LJKMZ20220976);辽宁省自然科学基金指导计划项目(20180550020)。

摘　　要：传统的人工势场法(APF)在路径规划领域因其简单性和高效性而被广泛采用,然而,这种方法往往会遇到局部最小值的问题,并且在动态环境中的适应性有限。为了解决这些问题,文中提出一种基于模拟退火算法(SA)改进的人工势场法。该改进方法结合人工势场法的实时避障能力和模拟退火法的全局优化特性,在所提出的改进方法中,通过在局部极小值附近添加随机目标点,使用模拟退火算法进行优化,从而有助于跳出局部最小值,并逐渐逼近全局最优或近似最优解。通过一系列的仿真实验表明,与传统人工势场法相比,基于模拟退火法的改进方法能够显著减少陷入局部最小值的情况,并在多种动态场景中表现出更强的鲁棒性和更优的路径规划效果。此外,该方法还展现了良好的实时性和适应性,能够满足车辆在复杂动态环境中进行避障和路径规划的需求。The traditional artificial potential field(APF)method has been widely adopted in the field of path planning be-cause of its simplicity and efficiency.However,the application of this method often generates local minima.In addition,this method has limited adaptability in dynamic environments.Therefore,an improved APF method based on the simulated annealing(SA)algorithm is proposed to eliminate the above problems.The improved method combines the real-time obstacle avoidance ca-pability of the APF method and the global optimization property of the SA method.The improved method is optimized with the SA algorithm by adding a random object point near the local minima,so as to help the improved method jump out of the local minima and gradually approach the global optimum or near-optimum solution.A series of simulation experiments show that the improved method based on SA significantly reduces the cases of falling into local minima and exhibits stronger robustness and better path planning results in a variety of dynamic scenarios in comparison with the traditional APF method.In addition,the pro-posed method demonstrates good real-time performance and adaptability,so it can meet the needs of vehicles for obstacle avoidance and path planning in complex dynamic environments.

关 键 词：车辆路径规划 人工势场法 模拟退火算法 动态避障 局部极小值 随机目标点 

分 类 号：TN911-34[电子电信—通信与信息系统] TP242[电子电信—信息与通信工程]