东北大学学报（自然科学版）

东北大学学报（自然科学版） ›› 2013, Vol. 34 ›› Issue (11): 1521-1524.DOI: 10.12068/j.issn.1005-3026.2013.11.001

• 信息与控制 •    下一篇

基于改进蚁群算法的移动机器人路径规划

张琦1，马家辰1,2，谢玮2，马立勇2   

  1. (1哈尔滨工业大学航天学院，黑龙江哈尔滨150001；2哈尔滨工业大学(威海)信息与电气工程学院，山东威海264209)
  • 发布日期:2013-07-09
  • 通讯作者: 张琦
  • 作者简介:张琦(1982-)，男，辽宁沈阳人，哈尔滨工业大学博士研究生；马家辰(1964-)，男，黑龙江佳木斯人，哈尔滨工业大学教授，博士生导师.
  • 基金资助:
    山东省自然科学基金资助项目(ZR2011FM005).

Improved Ant Colony AlgorithmBased Path Planning for Mobile Robot〓

ZHANG Qi1， MA Jiacheng1,2， XIE Wei2， MA Liyong2   

  1. 1. School of Astronautics， Harbin Institute of Technology， Harbin 150001， China； 2.Department of Information Science and Engineering， Harbin Institute of Technology at Weihai， Weihai 264209， China.
  • Published:2013-07-09
  • Contact: ZHANG Qi
  • About author:-
  • Supported by:
    -

RichHTML

0

PDF (PC)

1312

摘要： 针对蚁群算法中收敛速度和局部最优的矛盾，提出一种适用于静态环境的基于改进蚁群算法的移动机器人路径规划方法.在环境建模方面，利用机器人起点和终点的位置建立环境的可视图.改进的蚁群算法将环境中局部的路径信息加入到信息素的初始化和路径选择概率中，提高了算法收敛速度的同时尽可能地避免算法早熟.当算法陷入停滞时，引入交叉操作并调整α，β和ρ的值，增加了算法的逃逸能力.仿真结果证明了所提方法提高了最优路径的搜索效率，整体性能优于标准蚁群算法.

关键词: 移动机器人, 环境建模, 简化可视图, 蚁群算法, 路径规划

Abstract: To solve the contradictory between the convergence speed and the local optimum in ant colony algorithm，an improved ant colony optimization algorithm(IACO) was proposed for path planning of mobile robot in the static environment. The locations of start and goal were utilized to build the environmental model based on the simplified visibility graph. In IACO， the local path information was integrated with the initialization of pheromone and the selected probabilities of the paths，resulting in improving the convergence speed and avoiding the premature phenomenon as far as possible. For overcoming the possible stagnation phenomenon， crossover operation is drawn into the proposed algorithm and the value of α，β and ρ were updated， which enhanced the capability of escaping stagnation phenomenon. The simulation results demonstrated that the search efficiency of optimum path and the overall performance of the proposed algorithm were improved to be better than that of standard ACO.

Key words: mobile robot, environment modeling, visibility graph, ant colony optimization(ACO), path planning

中图分类号: