基于改进模拟退火算法的机器人全局路径规划  

Global Path Planning Method of Robot Based on Modified Simulated Annealing Algorithm

作　　者：巩敦卫[1] 曾现峰[1,2] 张勇[1] 

机构地区：[1]中国矿业大学信息与电气工程学院,徐州221008 [2]江苏联合职业技术学院徐州机电工程分院,徐州221011

出　　处：《系统仿真学报》2013年第3期480-483,488,共5页Journal of System Simulation

基　　金：国家自然科学基金(61005089);高等学校博士学科点专项科研基金资助课题(20100095120016)

摘　　要：针对全局静态移动机器人路径规划问题,给出了一种简单易行的改进模拟退火算法。算法通过引入脱障算子和一致寻优算子,提出了一种新的状态产生方法。前者采用维值定向扰动策略,使碰撞路段的两个端点以一定步长跳离障碍物,这既保证了路径的无碰性,又加快了寻优效率;后者对随机选取的若干个路径点进行变步长地调整,使产生的候选解可以遍布整个解空间,提高了算法的全局寻优能力。最后,通过对一般环境和"陷阱"环境路径规划问题的仿真,验证了该方法的有效性。Aiming at the path planning problem of robot in global static environment, a modified simulated annealing algorithm was proposed which is easy to implement. In this algorithm, a new method used to generate new status was introduced by defining an off-barrier operator and an optimal search operator. The first operator utilizes a directional disturbance strategy to help path points jump off the obstacles. It not only ensures free-collision of the generated path, but also enhances search efficiency of the algorithm. The second one adjusts the path points chosen randomly with dynamic ranges. Hence, it makes the algorithm be able to generate new position in the whole search space, and enhances the global search capability of the algorithm. Finally, simulation results verify the effectiveness of the Proposed algorithm_

关 键 词：机器人路径规划 模拟退火 脱障算子 一致寻优算子 

分 类 号：TP24[自动化与计算机技术—检测技术与自动化装置]