第16卷第2期 智能系统学报 Vol.16 No.2 2021年3月 CAAI Transactions on Intelligent Systems Mar.2021 D0:10.11992tis.202004011 网络出版地址：https:/ns.cnki.net/kcms/detail/23.1538.TP.20200716.1146.004html 基于变步长蚁群算法的移动机器人路径规划 徐玉琼123，娄柯2中，李志锟2 (1.广州大学松田学院电气与汽车工程系，广东广州511370：2.高端装备先进感知与智能控制教育部重，点实 验室，安徽芜湖241000,3.安徽工程大学安徽省电气传动与控制重点实验室，安徽芜湖241000) 摘要：针对传统蚁群算法以及双层蚁群算法在路径规划中存在搜索效率低、收敛性较慢以及成本较高的问 题，本文提出了变步长蚁群算法。该算法扩大蚁群可移动位置的集合，通过对跳点的选择以达到变步长策略， 有效缩短移动机器人路径长度：初始化信息素采用不均匀分布，加强起点至终点直线所涉及到栅格的信息素浓 度平行地向外衰减：改进启发式信息矩阵，调整移动机器人当前位置到终点位置的启发函数计算方法。试验结 果表明：变步长蚁群算法在路径长度及收敛速度两方面均优于双层蚁群算法及传统蚁群算法，验证了变步长蚁 群算法的有效性和优越性，是解决移动机器人路径规划问题的有效算法。 关键词：传统蚁群算法；双层蚁群算法；路径规划；变步长；信息素；启发函数；收敛；移动机器人 中图分类号：TP242.6文献标志码：A文章编号：1673-4785(2021)02-0330-08 中文引用格式：徐玉琼，娄柯，李志锟.基于变步长蚊群算法的移动机器人路径规划川.智能系统学报，2021,16(2)： 330-337. 英文引用格式：XU Yuqiong,.LOU Ke,,LI Zhikun..Mobile robot path planning based on variable--step ant colony algorithm. CAAI transactions on intelligent systems,2021,16(2):330-337. Mobile robot path planning based on variable-step ant colony algorithm XU Yuqiong"23,LOU Ke23,LI Zhikun2 (1.Department of Electrical and Automotive Engineering,Songtian College,Guangzhou University,Guangzhou 511370,China;2.Key Laboratory of Advanced Perception and Intelligent Control ofHigh-End Equipment,Ministry of Education,Wuhu 241000,China,3.An- hui Provincial Key Laboratory of Electric Transmission and Control,Anhui Polytechnic University,Wuhu 241000,China) Abstract:To address the problems of the traditional and double-layer ant colony algorithms,such as their low search ef- ficiency,slow convergence,and high path-planning cost,in this paper we propose a variable-step ant colony algorithm. The proposed algorithm expands the set of mobile locations of the ant colony,and uses the variable-step strategy of se- lecting the hopping points,thus effectively shortening the path length of the mobile robot.The initialization pheromone adopts an uneven distribution,which increases the pheromone concentration of the grid in a straight line from the start to end points,with the pheromone decaying outward in parallel.The heuristic information matrix is improved and the method used to calculate the heuristic function of the mobile robot from the current to the end positions is adjusted.The experimental results show that the performance of the variable-step ant colony algorithm is superior to those of the double-layer and traditional ant colony algorithms with respect to path length and convergence speed,which proves its eff- ectiveness and superiority.Thus,the proposed algorithm is effective in solving the path-planning problem of mobile robots. Keywords:traditional ant colony algorithm;double-layer ant colony algorithm;path planning;variable-step;pher- omone;heuristic function;convergence;mobile robot 在移动机器人领域，路径规划技术一直都是 收稿日期：2020-04-10.网络出版日期：2020-07-16 重要研究内容，其任务是在地图环境中为移动机 基金项目：国家自然科学基金项目(61572032)：安徽省高校自 然科学研究重点项目(KJ2019A0151.KJ20I9A0150): 器人从起点至终点避开障碍物而规划出的最优路 2018年度皖江高端装备制造协同创新中心开放基 金项目(GCKJ2018009). 径。目前国内外学者针对路径规划技术做了诸多 通信作者：徐玉琼.E-mail:xuyuqiong0104@163.com 研究，并取得相应成果，常用的传统路径规划算DOI: 10.11992/tis.202004011 网络出版地址: https://kns.cnki.net/kcms/detail/23.1538.TP.20200716.1146.004.html 基于变步长蚁群算法的移动机器人路径规划 徐玉琼1,2,3，娄柯2,3，李志锟2,3 （1. 广州大学松田学院 电气与汽车工程系，广东 广州 511370; 2. 高端装备先进感知与智能控制教育部重点实 验室，安徽 芜湖 241000; 3. 安徽工程大学 安徽省电气传动与控制重点实验室，安徽 芜湖 241000） 摘 要：针对传统蚁群算法以及双层蚁群算法在路径规划中存在搜索效率低、收敛性较慢以及成本较高的问 题，本文提出了变步长蚁群算法。该算法扩大蚁群可移动位置的集合，通过对跳点的选择以达到变步长策略， 有效缩短移动机器人路径长度；初始化信息素采用不均匀分布，加强起点至终点直线所涉及到栅格的信息素浓 度平行地向外衰减；改进启发式信息矩阵，调整移动机器人当前位置到终点位置的启发函数计算方法。试验结 果表明：变步长蚁群算法在路径长度及收敛速度两方面均优于双层蚁群算法及传统蚁群算法，验证了变步长蚁 群算法的有效性和优越性，是解决移动机器人路径规划问题的有效算法。 关键词：传统蚁群算法；双层蚁群算法；路径规划；变步长；信息素；启发函数；收敛；移动机器人 中图分类号：TP242.6 文献标志码：A 文章编号：1673−4785(2021)02−0330−08 中文引用格式：徐玉琼, 娄柯, 李志锟. 基于变步长蚁群算法的移动机器人路径规划 [J]. 智能系统学报, 2021, 16(2): 330–337. 英文引用格式：XU Yuqiong, LOU Ke, LI Zhikun. Mobile robot path planning based on variable-step ant colony algorithm[J]. CAAI transactions on intelligent systems, 2021, 16(2): 330–337. Mobile robot path planning based on variable-step ant colony algorithm XU Yuqiong1,2,3 ，LOU Ke2,3 ，LI Zhikun2,3 (1. Department of Electrical and Automotive Engineering, Songtian College, Guangzhou University, Guangzhou 511370, China; 2. Key Laboratory of Advanced Perception and Intelligent Control of High-End Equipment, Ministry of Education, Wuhu 241000, China; 3. An￾hui Provincial Key Laboratory of Electric Transmission and Control, Anhui Polytechnic University, Wuhu 241000, China) Abstract: To address the problems of the traditional and double-layer ant colony algorithms, such as their low search ef￾ficiency, slow convergence, and high path–planning cost, in this paper we propose a variable-step ant colony algorithm. The proposed algorithm expands the set of mobile locations of the ant colony, and uses the variable-step strategy of se￾lecting the hopping points, thus effectively shortening the path length of the mobile robot. The initialization pheromone adopts an uneven distribution, which increases the pheromone concentration of the grid in a straight line from the start to end points, with the pheromone decaying outward in parallel. The heuristic information matrix is improved and the method used to calculate the heuristic function of the mobile robot from the current to the end positions is adjusted. The experimental results show that the performance of the variable-step ant colony algorithm is superior to those of the double-layer and traditional ant colony algorithms with respect to path length and convergence speed, which proves its eff￾ectiveness and superiority. Thus, the proposed algorithm is effective in solving the path-planning problem of mobile robots. Keywords: traditional ant colony algorithm; double-layer ant colony algorithm; path planning; variable-step; pher￾omone; heuristic function; convergence; mobile robot 在移动机器人领域，路径规划技术一直都是 重要研究内容，其任务是在地图环境中为移动机 器人从起点至终点避开障碍物而规划出的最优路 径。目前国内外学者针对路径规划技术做了诸多 研究，并取得相应成果，常用的传统路径规划算 收稿日期：2020−04−10. 网络出版日期：2020−07−16. 基金项目：国家自然科学基金项目 (61572032)；安徽省高校自 然科学研究重点项目 (KJ2019A0151，KJ2019A0150)； 2018 年度皖江高端装备制造协同创新中心开放基 金项目 (GCKJ2018009). 通信作者：徐玉琼. E-mail: xuyuqiong0104@163.com. 第 16 卷第 2 期 智 能 系 统 学 报 Vol.16 No.2 2021 年 3 月 CAAI Transactions on Intelligent Systems Mar. 2021