基于IACO-ABC算法的变电站巡检机器人路径规划Path Planning of Substation Patrol Robot Based on IACO-ABC Algorithms
薛阳,俞志程,吴海东,张宁
XUE Yang,YU Zhicheng,WU Haidong,ZHANG Ning
摘要(Abstract):
目前,变电站智能巡检机器人的路径规划中,各种智能算法如ACO(蚁群优化)、 ABC(人工蜂群)等应用较为广泛,但传统ACO算法存在容易陷入局部最优值、收敛速度较慢等问题。为此,在对传统ACO算法进行改进的基础上,结合ABC算法的优势,提出IACO-ABC(改进蚁群-蜂群融合)算法,将其应用到变电站巡检机器人路径规划中,以提高路径规划算法的鲁棒性,并解决算法陷入局部最优的问题。采用栅格法建立工作环境进行仿真,结果表明采用该算法能够有效解决上述问题,在复杂环境下的规划能力和鲁棒性能较好,并提高了路径质量以及算法效率。
ACO(ant colony optimization), ABC(artificial bee colony) and other intelligent algorithms are widely used in path planning of intelligent substation inspection robot. However, the traditional ACO is prone to slow local optimal solution and convergence speed. Therefore, an IACO-ABC(improved ant colony optimization-artificial bee colony) is proposed and applied by improving the traditional ACO and in combination with advantages of ABC to the path planning of substation inspection robot to improve the robustness and proneness to the local optimal solution. The grid-based method is used to establish an operating environment for simulation, and the result shows that the method can better solve the problems with favourable planning capacity and robustness as well as path quality and efficiency under complex situations.
关键词(KeyWords):
路径规划;巡检机器人;蚁群算法;人工蜂群算法
path planning;patrol robot;ant colony algorithm;ABC
基金项目(Foundation): 国网浙江省电力有限公司科技项目(5211HZ17000F);; 国家自然科学青年基金资助项目(51405286);; 上海市电站自动化技术重点实验室项目(13DZ2273800)
作者(Author):
薛阳,俞志程,吴海东,张宁
XUE Yang,YU Zhicheng,WU Haidong,ZHANG Ning
DOI: 10.19585/j.zjdl.201911002
参考文献(References):
- [1]朱大奇,颜明重.移动机器人路径规划技术综述[J].控制与决策,2010,25(7):961-967.
- [2]BAKDI A,HENTOUT A,BOUTAMI H,et al.Optimal path planning and execution for mobile robots using genetic algorithm and adaptive fuzzy-logic control[J].Robotics and Autonomous Systems,2017,89(1):95-109.
- [3]易欣,郭武士,赵丽.利用自适应选择算子结合遗传算法的机器人路径规划方法[J].计算机应用研究,2019,37(6):1-6.
- [4]潘杰,王雪松,程玉虎.基于改进蚁群算法的移动机器人路径规划[J].中国矿业大学学报,2012,41(1):108-113.
- [5]占伟,屈军锁,芦鑫,等.基于改进蚁群算法的移动机器人全局路径规划[J].现代电子技术,2018,41(24):170-173.
- [6]金丹.基于改进RRT算法的移动机器人路径规划[J].现代计算机(专业版),2018(18):41-44.
- [7]陈瑶,陈阿莲,李向东,等.变电站智能巡检机器人全局路径规划设计[J].山东科学,2015,28(1):114-119.
- [8]杨天宇,薛阳,张亚飞.基于蚁群-粒子群算法的巡检机器人路径规划[J].现代计算机(专业版),2017(29):48-51.
- [9]屈鸿,黄利伟,柯星.动态环境下基于改进蚁群算法的机器人路径规划研究[J].电子科技大学学报,2015,44(2):260-265.
- [10]LU Y H,LIANG M H,YE Z Y,et al.Improved particle swarm optimization algorithm and its application in text selection[J].Applied Soft Computing,2015(7):629-636.
- [11]裴振兵,陈雪波.改进蚁群算法及其在机器人避障中的应用[J].智能系统学报,2015(1):90-96.
- [12]高玮,张飞君.相遇蚁群算法在边坡非圆弧临界滑动面搜索中的应用研究[J].岩土力学,2014,35(增刊1):391-398.
- [13]张飞,君高玮,汪磊.奖惩蚁群算法[J].计算机工程与应用,2010,46(10):44-47.
- [14]游晓明,刘升,吕金秋.一种动态搜索策略的蚁群算法及其在机器人路径规划中的应用[J].控制与决策,2017(3):553-556.
- [15]WANG H Q,LIAO L,WANG D Y.Improved artificial bee colony algorithm and its application in LQR controller optimization[J].Mathematical Problems in Engineering,2014,140(1):1-8.
- [16]黎竹娟.人工蜂群算法在移动机器人路径规划中的应用[J].计算机仿真,2012,29(12):247-250.
- [17]文政颍,翟红生.基于混沌人工蜂群算法的无线传感器网络覆盖优化[J].计算机测量与控制,2014,22(5):1609-1612.
- [18]ZHU G P,KWONG S.Gbest-guided artificial bee colony algorithm for numerical function optimization[J].Applied Mathematics and Computation,2010,217(1):3166-3173.
- [19]郑健,黄敏,张腾,等.求解指路标指引路径规划问题的改进人工蜂群算法[J].计算机应用研究,2017,34(8):2355-2359.
- [20]王海泉,胡瀛月,廖伍代,等.基于改进人工蜂群算法的机器人路径规划[J].控制工程,2016,23(9):1407-1411.
- [21]何宗耀,王翔.蜂群—蚁群自适应优化算法[J].计算机应用研究,2012,29(1):130-133.
- [22]钱金菊,彭向阳,麦晓明,等.架空输电线路巡检机器人自动上下线装置[J].广东电力,2017,30(5):101-107.
- [23]钱金菊,吴功平,彭向阳,等.架空输电线路巡检机器人风载下姿态检测及作业控制技术[J].广东电力,2017,30(1):116-120.
- [24]易琳,秦晓科,王刚,等.基于改进蚁群算法的电力巡检路径规划[J].广东电力,2018,31(3):115-119.