一种基于混合学习策略移动机器人路径规划方法_郜园园.pdfVIP

DOI ：10.13195/j.cd.2012.12.65.gaoyy.023 第27 卷 第12 期 控 制 与 决 策 2012 年 12 月 Vol. 27 No. 12 Control and Decision Dec. 2012 文章编号: 1001-0920 (2012) 12-1822-06 一种基于混合学习策略的移动机器人路径规划方法 郜园园, 阮晓钢, 宋洪军, 于建均 (北京工业大学电子信息与控制工程学院，北京100124) 摘 要: 针对未知环境下移动机器人路径规划问题, 以操作条件反射学习机制为基础, 根据模糊推理系统和学习自 动机的原理, 提出一种应用于移动机器人导航的混合学习策略. 运用仿生的自组织学习方法, 通过不断与外界未知环 境交互从而使机器人具有自学习和自适应的功能. 仿真结果表明, 该方法能使机器人学会避障和目标导航任务, 与传 统的人工势场法相比, 能有效地克服局部极小和振荡情况. 关键词: 模糊推理系统；学习自动机；操作条件反射；混合学习策略；路径规划 中图分类号: TP242 文献标志码: A Path planning method for mobile robot based on a hybrid learning approach GAO Yuan-yuan, RUAN Xiao-gang, SONG Hong-jun, YU Jian-jun (College of Electronic Information and Control Engineering，Beijing University of Technology ，Beijing 100124 ，China ． Correspondent ：GAO Yuan-yuan，E-mail ：yuangao84@163.com) Abstract: Aim to solve the path planning problem of mobile robot in the unknown environment, a hybrid learning approach is proposed for the robot navigation based on the operant conditioning theory and the principle of fuzzy inference system and learning automata. The robot is endowed with the capabilities of self-learning and self-adapting with unknown environment by using a bionic self-organizing method. Simulation results show that, compared with the method of artifical potential field, the proposed method can make the robot learn the ability of obstacle avoidance and goal seeking without being stuck in local minima and oscillation. Key words: fuzzy inference system ；learning automata