基于改进蚁群算法的移动机器人路径规划
|
摘要
传统蚁群算法对移动机器人路径进行最优规划存在计算周期长、收敛慢、搜索路径存在局部最优等问题,因此提出新的蚁群改进方法。改进蚁群算法采用自适应启发式函数,增加目标点的吸引力;对寻优蚂蚁采用奖励制度;引入转向代价。针对蚂蚁死锁问题,通过A*算法辅助,随机对死锁蚂蚁复活。仿真实验结果表明,改进蚁群算法快速收敛于最优路径,具有很强的准确性和稳定性。
An improved ant colony algorithm is proposed to solve the problems including long calculation period,slow convergence and local optimization when applying the traditional ant colony algorithm in the path planning of mobile robot.The new algorithm uses an adaptive heuristic function to increase the attractiveness of target points,and adopts the reward system of outstanding ants,and introduces turning costs.We randomly implement the resurrection mechanism on deadlock ants with A* algorithm assisted to overcome the deadlock.The simulation results show that the improved ant colony algorithm can quickly converges to find the optimal path with sufficient accuracy and stability.
An improved ant colony algorithm is proposed to solve the problems including long calculation period,slow convergence and local optimization when applying the traditional ant colony algorithm in the path planning of mobile robot.The new algorithm uses an adaptive heuristic function to increase the attractiveness of target points,and adopts the reward system of outstanding ants,and introduces turning costs.We randomly implement the resurrection mechanism on deadlock ants with A* algorithm assisted to overcome the deadlock.The simulation results show that the improved ant colony algorithm can quickly converges to find the optimal path with sufficient accuracy and stability.
引文
[1] 赵娟平.移动机器人路径规划的蚁群优化算法研究[D].沈阳:东北大学,2012.
[2] 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.
[3] 朱艳,游小明,刘升,等.基于改进蚁群算法的机器人路径规划问题研究[J].计算机工程与应用,2018,54(19):129-134.
[4] 连晓峰,刘载文,左敏.移动机器人动态人工势场路径规划方法研究[J].计算机仿真,2011,28(1):27-31.
[5] 翟红生,王佳欣.基于人工势场的机器人动态路径规划新方法[J].重庆邮电大学学报(自然科学版):2015,27(6):814-818.
[6] 郭必祥.基于蚁群算法的智能机器人全局路径规划方法研究[D].哈尔滨:哈尔滨工程大学,2005.
[7] 张万绪,张向兰,李莹.改进粒子群算法的智能机器人路径规划[J].计算机应用,2014,34(2):510-513.
[8] Marco Dorigo,Vittorio Maniezzo,Alberto Colorni.The ant system optimization by a colony of cooperating agents[J].IEEE Transaction System,Man,and Cybernetics-part B,1996,26(1):1-13.
[9] 郑家风,田思庆.基于改进蚁群算法的煤矿救援机器人全局路径规划研究[J],电脑知识与技术,2018.14(24):171-184.
[10] 何雨,张志安,韩明明,等.基于全向移动机器人路径规划的蚁群算法研究[J].测试技术学报,2018,32(5):374-380.
[11] 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.
[12] 赵开新,魏勇,王东署.改进蚁群算法在移动机器人路径规划中的研究[J].计算机测量与控制,2014,22(11):67-70.
[13] 赵凯,李声晋,孙娟,等.改进蚁群算法在移动机器人路径规划中的研究[J].微型机与应用,2013,32(4):67-70.
[14] 周东健,张兴国,马海波,等.基于栅格地图-蚁群算法的机器人最优路径规划[J].制造业自动化,2014,(5):1-3,10.
[15] 柴寅.融合栅格法与改进蚁群算法的机器人路径规划[D].武汉:武汉科技大学,2016.
[2] 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.
[3] 朱艳,游小明,刘升,等.基于改进蚁群算法的机器人路径规划问题研究[J].计算机工程与应用,2018,54(19):129-134.
[4] 连晓峰,刘载文,左敏.移动机器人动态人工势场路径规划方法研究[J].计算机仿真,2011,28(1):27-31.
[5] 翟红生,王佳欣.基于人工势场的机器人动态路径规划新方法[J].重庆邮电大学学报(自然科学版):2015,27(6):814-818.
[6] 郭必祥.基于蚁群算法的智能机器人全局路径规划方法研究[D].哈尔滨:哈尔滨工程大学,2005.
[7] 张万绪,张向兰,李莹.改进粒子群算法的智能机器人路径规划[J].计算机应用,2014,34(2):510-513.
[8] Marco Dorigo,Vittorio Maniezzo,Alberto Colorni.The ant system optimization by a colony of cooperating agents[J].IEEE Transaction System,Man,and Cybernetics-part B,1996,26(1):1-13.
[9] 郑家风,田思庆.基于改进蚁群算法的煤矿救援机器人全局路径规划研究[J],电脑知识与技术,2018.14(24):171-184.
[10] 何雨,张志安,韩明明,等.基于全向移动机器人路径规划的蚁群算法研究[J].测试技术学报,2018,32(5):374-380.
[11] 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.
[12] 赵开新,魏勇,王东署.改进蚁群算法在移动机器人路径规划中的研究[J].计算机测量与控制,2014,22(11):67-70.
[13] 赵凯,李声晋,孙娟,等.改进蚁群算法在移动机器人路径规划中的研究[J].微型机与应用,2013,32(4):67-70.
[14] 周东健,张兴国,马海波,等.基于栅格地图-蚁群算法的机器人最优路径规划[J].制造业自动化,2014,(5):1-3,10.
[15] 柴寅.融合栅格法与改进蚁群算法的机器人路径规划[D].武汉:武汉科技大学,2016.