一种改进蚁群算法的移动机器人路径规划
|
摘要
路径规划是移动机器人运动控制中的关键问题。针对传统蚁群算法在机器人全局路径规划中存在收敛速度慢、易陷入局部最优等缺点,提出一种改进型蚁群路径规划算法。首先,通过栅格法建立机器人运动环境模型,然后在传统蚁群算法基础上引入A*搜索算法的估价函数思想,改进蚁群算法的启发函数,增加目标节点与可选行进节点数对启发函数的影响。其次,在信息素更新公式中,通过引入Logistic增长函数对信息素挥发因子作自适应调整,提高算法速度与精度。最后,通过Matlab仿真实验证明,改进蚁群算法比传统算法在路径搜索速度和精度上都有较大提升。
Path planning is a key problem in motion control of mobile robot. An improved ant colony path planning algorithm is pro?posed to solve the problems of slow convergence rate and getting stuck in the local optimum easily. First robot movement environment model is established by the grid method,and then on the basis of traditional ant colony algorithm,the evaluation function of A*search algorithm is produced to improve ant colony algorithm function,increase the target node and optional node number's influence on the heuristic function. Secondly,in the update formula of pheromones,the speed and accuracy of the algorithm are improved by introduc?ing logistic growth function to adjust the volatility factor of pheromones. Finally,through the Matlab simulation experiment,it is veri?fied that the improved ant colony algorithm has greatly improved the speed and precision of the path search compared with the tradition?al algorithm.
Path planning is a key problem in motion control of mobile robot. An improved ant colony path planning algorithm is pro?posed to solve the problems of slow convergence rate and getting stuck in the local optimum easily. First robot movement environment model is established by the grid method,and then on the basis of traditional ant colony algorithm,the evaluation function of A*search algorithm is produced to improve ant colony algorithm function,increase the target node and optional node number's influence on the heuristic function. Secondly,in the update formula of pheromones,the speed and accuracy of the algorithm are improved by introduc?ing logistic growth function to adjust the volatility factor of pheromones. Finally,through the Matlab simulation experiment,it is veri?fied that the improved ant colony algorithm has greatly improved the speed and precision of the path search compared with the tradition?al algorithm.
引文
[1]任玉洁,付丽霞,张勇,等.基于平滑A*人工势场法的机器人动态路径规划[J].软件导刊,2018,17(1):8-10.
[2]高涵,高柏军.移动机器人路径规划方法研究[J].现代仪器与医疗,2015,21(5):14-17.
[3]王殿君.基于改进A*算法的室内移动机器人路径规划[J].清华大学学报:自然科学版,2012,52(8):1085-1089.
[4] FAKOOR M,KOSARI A,JAFARZADEH M. Humanoid robot pathplanning with fuzzy Markov decision processes[J]. Journal of AppliedResearch&Technology,2016,14(5):300-310.
[5]周文卷.复杂环境下自主移动机器人路径规划方法的研究[D].长春:吉林大学,2014.
[6] MEHD I,FATEH M,FATEH S. A precise robust fuzzy control of ro?bots using voltage control strategy[J]. International Journal of Automa?tion and Computing,2013,10(1):64-72.
[7]施磊磊,施化吉,束长波,等.改进的模糊控制算法在机器人路径规划中的应用[J].软件导刊,2014,13(11):46-48.
[8]彭玉青,李木,张媛媛.基于改进模糊算法的移动机器人避障[J].计算机应用,2015,35(8):2256-2260.
[9]李奕铭.基于人工势场法的移动机器人避障研究[D].合肥:合肥工业大学,2013.
[10]张殿富,刘福.基于人工势场法的路径规划方法研究及展望[J].计算机工程与科学,2013,35(6):88-95.
[11]史恩秀,陈敏敏,李俊,等.基于蚁群算法的移动机器人全局路径规划方法研究[J].农业机械学报,2014,45(6):53-57.
[12] ZHANG K,YUAN C M,GAO X S. A greedy algorithm for feedrateplanning of CNC machines along curved tool paths with confined jerk[J]. Robotics and Computer Integrated Manufacturing,2012,28(4):472-483.
[13]夏小云,周育人.蚁群优化算法的理论研究进展[J].智能系统学报,2016,11(1):27-36.
[14]李明磊,赵杰,李戈.面向方形节点拓扑地图下的移动机器人路径规划算法研究[J].机械与电子,2015(10):67-70.
[15]陈超,唐坚,靳祖光.一种基于可视图法导盲机器人路径规划的研究[J].机械科学与技术,2014,33(4):490-495.
[16]李士勇,陈勇强,李研.蚁群算法及其应用[M].哈尔滨:哈尔滨出版社,2004.
[17]万晓凤,胡伟,方武义,等.基于改进蚁群算法的机器人路径规划研究[J].计算机工程与应用,2014,50(18):63-66.
[18]侯欣蕾,于莲芝.基于改进蚁群算法的移动机器人路径规划[J].软件导刊,2017,16(12):162-164.
[19] MOHAMMAD S M,SAEED D A,FARSHID E,et al.An ant colony al?gorithm(ACA)for solving the new integrated model of job shopscheduling and conflictfree routing of AGVs[J]. Computers and In?dustrial Engineering,2015,86(C):2-13.
[20]王沛栋.改进蚁群算法及在路径规划问题的应用研究[D].青岛:中国海洋大学,2012.
[21]梁嘉俊,曾碧,何元烈.基于改进势场栅格法的清洁机器人路径规划算法研究[J].广东工业大学学报,2016,33(4):30-36.
[2]高涵,高柏军.移动机器人路径规划方法研究[J].现代仪器与医疗,2015,21(5):14-17.
[3]王殿君.基于改进A*算法的室内移动机器人路径规划[J].清华大学学报:自然科学版,2012,52(8):1085-1089.
[4] FAKOOR M,KOSARI A,JAFARZADEH M. Humanoid robot pathplanning with fuzzy Markov decision processes[J]. Journal of AppliedResearch&Technology,2016,14(5):300-310.
[5]周文卷.复杂环境下自主移动机器人路径规划方法的研究[D].长春:吉林大学,2014.
[6] MEHD I,FATEH M,FATEH S. A precise robust fuzzy control of ro?bots using voltage control strategy[J]. International Journal of Automa?tion and Computing,2013,10(1):64-72.
[7]施磊磊,施化吉,束长波,等.改进的模糊控制算法在机器人路径规划中的应用[J].软件导刊,2014,13(11):46-48.
[8]彭玉青,李木,张媛媛.基于改进模糊算法的移动机器人避障[J].计算机应用,2015,35(8):2256-2260.
[9]李奕铭.基于人工势场法的移动机器人避障研究[D].合肥:合肥工业大学,2013.
[10]张殿富,刘福.基于人工势场法的路径规划方法研究及展望[J].计算机工程与科学,2013,35(6):88-95.
[11]史恩秀,陈敏敏,李俊,等.基于蚁群算法的移动机器人全局路径规划方法研究[J].农业机械学报,2014,45(6):53-57.
[12] ZHANG K,YUAN C M,GAO X S. A greedy algorithm for feedrateplanning of CNC machines along curved tool paths with confined jerk[J]. Robotics and Computer Integrated Manufacturing,2012,28(4):472-483.
[13]夏小云,周育人.蚁群优化算法的理论研究进展[J].智能系统学报,2016,11(1):27-36.
[14]李明磊,赵杰,李戈.面向方形节点拓扑地图下的移动机器人路径规划算法研究[J].机械与电子,2015(10):67-70.
[15]陈超,唐坚,靳祖光.一种基于可视图法导盲机器人路径规划的研究[J].机械科学与技术,2014,33(4):490-495.
[16]李士勇,陈勇强,李研.蚁群算法及其应用[M].哈尔滨:哈尔滨出版社,2004.
[17]万晓凤,胡伟,方武义,等.基于改进蚁群算法的机器人路径规划研究[J].计算机工程与应用,2014,50(18):63-66.
[18]侯欣蕾,于莲芝.基于改进蚁群算法的移动机器人路径规划[J].软件导刊,2017,16(12):162-164.
[19] MOHAMMAD S M,SAEED D A,FARSHID E,et al.An ant colony al?gorithm(ACA)for solving the new integrated model of job shopscheduling and conflictfree routing of AGVs[J]. Computers and In?dustrial Engineering,2015,86(C):2-13.
[20]王沛栋.改进蚁群算法及在路径规划问题的应用研究[D].青岛:中国海洋大学,2012.
[21]梁嘉俊,曾碧,何元烈.基于改进势场栅格法的清洁机器人路径规划算法研究[J].广东工业大学学报,2016,33(4):30-36.