研究论文

基于改进蚁群算法与Morphin算法的机器人路径规划方法

  • 万晓凤 ,
  • 胡伟 ,
  • 郑博嘉 ,
  • 方武义
展开
  • 南昌大学电气与自动化工程系, 南昌330031
万晓凤,教授,研究方向为计算机控制与嵌入式智能仪表,电子信箱:xfwan_jx@163.com

收稿日期: 2014-06-19

  修回日期: 2014-12-26

  网络出版日期: 2015-03-03

基金资助

江西省科技支撑项目(20133BBE50029);江西省科技厅工业支撑计划项目(20132BBE50049)

Robot path planning method based on improved ant colony algorithm and Morphin algorithm

  • WAN Xiaofeng ,
  • HU Wei ,
  • ZHENG Bojia ,
  • FANG Wuyi
Expand
  • Electrical and Automation Engineering Department, Nanchang University, Nanchang 330031, China

Received date: 2014-06-19

  Revised date: 2014-12-26

  Online published: 2015-03-03

摘要

针对动态复杂环境下的机器人路径规划问题,建立栅格地图模型,研究一种改进蚁群算法与Morphin 算法相结合的动态路径规划方法。改进蚁群算法引入拐点参数评价路径优劣,并对路径进行拐角处理以及变更拐角处信息素更新机制,使规划的全局路径更加平滑;Morphin 算法则在机器人行走时,根据全局路径的局部环境实时规划局部路径,使机器人有效地躲避障碍物。仿真试验结果表明,该方法结合全局规划与局部规划的特点,能够使机器人沿着一条短而平滑的最优路径快速、安全地到达目标点。

本文引用格式

万晓凤 , 胡伟 , 郑博嘉 , 方武义 . 基于改进蚁群算法与Morphin算法的机器人路径规划方法[J]. 科技导报, 2015 , 33(3) : 84 -89 . DOI: 10.3981/j.issn.1000-7857.2015.03.014

Abstract

A hybrid planning method combining an improved ant colony algorithm with Morphin algorithm is proposed for dynamic path planning for robot in complicated environment. Grid method is adopted to establish the model. The robot uses the improved ant colony algorithm for global path planning first, then uses Morphin algorithm for partial obstacle avoidance when it is marching on. The improved ant colony algorithm introduces an inflection point parameter to evaluate the path, so that the corner of the path is disposed and the updating mechanism of corner pheromone is changed. The Morphin algorithm is disposed with adjacent grid to meet the grid environments. This method combines the characteristics of global planning with local planning, which can not only realize real-time path planning according to the environment, but also guide the robot to the target with the global optimal path. Simulation results indicate that this method can make the robot avoid obstacles along a short and smooth path to quickly reach the target point.

参考文献

[1] 姚俊武, 张林仙. 非结构环境下移动机器人路径规划[J]. 科技导报, 2010, 28(22): 82-85. Yao Junwu, Zhang Linxian. Path planning of mobile robot in unstructured environment[J]. Science & Technology Review, 2010, 28 (22): 82-85.
[2] 朱磊, 樊继壮, 赵杰, 等. 基于栅格法的矿难搜索机器人全局路径规划 与局部避障[J]. 中南大学学报: 自然科学版, 2011, 42(11): 3421-3428. Zhu Lei, Fan Jizhuang, Zhao Jie, et al. Global path planning and local obstacle avoidance of searching robot in mine disasters based on grid method[J]. Journal of Central South University: Science and Technology, 2011, 42(11): 3421-3428.
[3] 李学洋, 李悦, 张亚伟. 基于遗传变异蚁群算法的机器人路径规划的 改进[J]. 电子设计工程, 2012, 20(15): 38-40. Li Xueyang, Li Yue, Zhang Yawei. Improved ant colony algorithm based on genetic variation apply in robots path planning[J]. Electronic Design Engineering, 2012, 20(15): 38-40.
[4] 罗荣贵, 屠大维. 栅格法视觉传感集成及机器人实时避障[J]. 计算机 工程与应用, 2011, 47(24): 233-235. Luo Ronggui, Tu Dawei. Vision sensors integration based grid-method for robot real-time obstacle detection[J]. Computer Engineering and Applications, 2011, 47(24): 233-235.
[5] Dorigo M, Caro G D. Ant Colony Optimization: a new meta-heuristic [C]//Proceedings of 1999 Congress on Evolutionary Computation. New York: IEEE, 1999: 1470-1477.
[6] 段海滨, 王道波, 朱家强, 等. 蚁群算法理论及应用研究的进展[J]. 控 制与决策, 2004, 19(12): 1321-1326. Duan Haibin, Wang Daobo, Zhu Jiaqiang, et al. Development on ant colony algorithm theory and its application[J]. Control and Decision, 2004, 19(12): 1321-1326.
[7] 蔡荣英, 王李进, 吴超, 等. 一种求解旅行商问题的迭代改进蚁群优化 算法[J]. 山东大学学报: 工学版, 2012, 42(1): 6-11. Cai Rongying, Wang Lijin, Wu Chao, et al. A kind of iterative improvement based ant colony optimization algorithm for the traveling salesman problem[J]. Journal of Shandong University: Engineering Science, 2012, 42(1): 6-11.
[8] Xiong W Q, Wei P. A kind of ant colony algorithm for function optimization[C] //Proceedings of 2002 International Conference on Machine Learning and Cybernetics. New York: IEEE, 2002: 552-555.
[9] 周明秀, 程科, 汪正霞. 动态路径规划中的改进蚁群算法[J]. 计算机科 学, 2013, 40(1): 314-316. Zhou Mingxiu, Cheng Ke, Wang Zhengxia. Improved ant colony algorithm with planning of dynamic path[J]. Computer Science, 2013, 40 (1): 314-316.
[10] Stützle T, Hoos H. MAX-MIN ant system and local search for the traveling salesman problem[C]//Proceedings of 1997 IEEE International Conference on Evolutionary Computation. New York: IEEE, 1997: 309-314.
[11] 肖本贤, 刘刚, 余雷, 等. 基于MMAS 的机器人路径规划[J]. 合肥工 业大学学报: 自然科学版, 2008, 31(1): 63-67. Xiao Benxian, Liu Gang, Yu Lei, et al. Robot path planning based on the MAX-MIN ant system[J]. Journal of Hefei University of Technology: Natural Science, 2008, 31(1): 63-67.
[12] Simmons R, Henriksen L, Chrisman L, et al. Obstacle avoidance and safeguarding for a lunar rover[C]//Proceedings of AIAA Forum on Advanced Developments in Space Robotics. Madison, Wisconsin: AIAA, 1996.
[13] 宋红生, 王东署. 基于改进蚁群算法的移动机器人路径规划[J]. 机床 与液压, 2012, 40(20): 120-125. Song Hongsheng, Wang Dongshu. Path planning for mobile robot based on modified ant colony optimization[J]. Machine Tool & Hydraulics, 2012, 40(20): 120-125.
文章导航

/