基于遗传算法的移动机器人动态避障路径规划方法  

GENETIC PATH PLANNING AND DYNAMIC OBSTACLE AVOIDANCE FOR MOBILE ROBOTS

作　　者：李庆中[1] 顾伟康[1] 叶秀清[1] 

机构地区：[1]浙江大学信息与电子工程学系,杭州310027

出　　处：《模式识别与人工智能》2002年第2期161-166,共6页Pattern Recognition and Artificial Intelligence

摘　　要：本文提出了一种基于遗传算法的简单、有效的移动机器人实时动态避障路径规划方法.为利用遗传算法实时、稳定地进行动态路径规划,本文将复杂的二维路径编码问题简化为一维编码问题,并把路边约束、动态避障要求和最短路径要求融合成一个简单的适度函数.仿真实验表明,本文提出的动态路径规划方法可实时、稳定地产生移动机器人运动的最佳局部规划路径,且具有良好的动态避障性能.该方法也可用于智能车辆的自动导航.Based on Genetic Algorithm, a simple and efficient method for real-time path planning and dynamic obstacle avoidance of mobile robots is developed in this paper. In order to realize the goal of real-time path planning by using Genetic Algorithm stably, the complicated two-dimensional path-coding problem is reduced to a simple one-dimensional problem. And the roadside constraint, requirements for dynamic obstacle avoidance and shortest path are fused to a simple fitness function. Simulation results show that the proposed approach can quickly and robustly generate local optimum path with performance of dynamic obstacle avoidance. This dynamic path planning method can also be applied to intelligent vehicle guidance.

关 键 词：遗传算法 移动机器人 动态避障 路径规划 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置]