张成,凌有铸,陈孟元.改进蚁群算法求解移动机器人路径规划[J].电子测量与仪器学报,2016,30(11):1758-1764
改进蚁群算法求解移动机器人路径规划
Path planning of mobile robot based on an improved ant colony algorithm
  
DOI:10.13382/j.jemi.2016.11.018
中文关键词:  路径规划  移动机器人  蚁群算法  信息素
英文关键词:path planning  mobile robot  ant colony algorithm  pheromone
基金项目:2016年度安徽高校自然科学项目(KJ2016A794)资助
作者单位
张成 安徽工程大学安徽省电气传动与控制重点实验室芜湖241000 
凌有铸 安徽工程大学安徽省电气传动与控制重点实验室芜湖241000 
陈孟元 安徽工程大学安徽省电气传动与控制重点实验室芜湖241000 
AuthorInstitution
Zhang Cheng Anhui Polytechnic University, Anhui Key Laboratory of Electric Drive and Control, Wuhu 241000, China 
Ling Youzhu Anhui Polytechnic University, Anhui Key Laboratory of Electric Drive and Control, Wuhu 241000, China 
Chen Mengyuan Anhui Polytechnic University, Anhui Key Laboratory of Electric Drive and Control, Wuhu 241000, China 
摘要点击次数: 90
全文下载次数: 89
中文摘要:
      在全局静态环境下,提出一种改进蚁群算法,解决传统蚁群算法用于路径规划出现的收敛速性差、局部最优和求解质量差等不足。该算法引入障碍物排斥权重和新的启发因子到路径选择概率中,提高避障能力,增加路径选择的多样性;然后,设置局部信息素的阈值和限定范围更新局部信息素,采用交叉操作获取新路径,引入最优解和最差解,改变全局信息素的更新方式,提高全局搜索能力和解的质量,避免算法陷入局部最优。仿真结果表明,该算法能有效获得最优路径,在长度上比蚁群算法及其他算法分别减少了18%、5.7%和11%,算法迭代次数及运行时间都有所降低,提高了收敛速度和搜索能力。
英文摘要:
      An improved ant colony algorithm is proposed to solve the deficiency of the traditional ant colony algorithm such as bad convergence, local optimum and poor quality for path planning under the global static environment. The algorithm introduces the obstacle repulsion weights and a new heuristic factor to path selection probability, which improves the ability of obstacle avoidance and increases the strength of the way selection diversity. Then, the value of local pheromone is set and the scope local pheromone update is defined, and the crossover operation is used to obtain a new path. Introducing the optimal solution and the worst solution, the global information pheromone updating method is changed to improve the global searching ability and solution quality and avoid falling into local optimum algorithm. The simulation results show that the algorithm can effectively obtain the optimal path, which is reduced by 11%, 5.7% and 18% in the length, respectively. The number of iteration and running time of the algorithm is reduced, and both the convergence speed and the search ability are improved.
查看全文  查看/发表评论  下载PDF阅读器