增强蚁群算法的机器人最优路径规划  

Path planning optimization based on reinforcement of artificial potential field

作　　者：齐勇[1,2] 魏志强[2] 殷波[2] 费云瑞[2] 于忠达[2] 庄晓东[2] 

机构地区：[1]山东省科学院海洋仪器仪表研究所,青岛266001 [2]中国海洋大学计算机科学系,青岛266100

出　　处：《哈尔滨工业大学学报》2009年第3期130-133,共4页Journal of Harbin Institute of Technology

基　　金：国家自然科学基金资助项目(60374031)

摘　　要：为解决复杂环境中机器人最优路径规划问题,本文结合增强学习和人工势场法的原理,提出一种基于增强势场优化的机器人路径规划方法,引入增强学习思想对人工势场法进行自适应路径规划.再把该规划结果作为先验知识,对蚁群算法进行初始化,提高了蚁群算法的优化效率,同时克服了传统人工势场法的局部极小问题.仿真实验结果表明,该方法在复杂环境中,对机器人的路径规划效果令人满意.In order to solve the problem of optimal path planning for robot in complex environment, a path planning method based on the artificial potential field optimization is proposed in this paper. The ant algorithm is initialized by the planning result of the artificial potential field reinforcement as the prior knowledge, which improves the algorithm＇s efficiency. On the other hand, the local minima problem in the artificial potential field method is solved successfully. The result of simulation shows that the method in this paper works well in solving the relevant problems.

关 键 词：增强学习 增强势场 蚁群算法 最优路径 

分 类 号：TP24[自动化与计算机技术—检测技术与自动化装置]