首页 | 本学科首页   官方微博 | 高级检索  
     

基于改进D?Lite遗传算法路径规划研究
引用本文:李俊,舒志兵. 基于改进D?Lite遗传算法路径规划研究[J]. 机床与液压, 2019, 47(11): 39-42
作者姓名:李俊  舒志兵
作者单位:南京工业大学电气工程与控制科学学院,江苏南京,211800;南京工业大学电气工程与控制科学学院,江苏南京,211800
摘    要:针对遗传算法在移动机器人路径规划中易产生早熟现象和收敛速度慢的问题,提出了改进的D~* Lite遗传算法。该算法将D~* Lite算法和遗传算法相结合,通过引入碰撞系数和可视检测技术以提高路径安全性,寻找最短路径。在遗传算法设计中加入动态调整交叉与变异概率,以解决算法在路径规划中因陷入局部最优值而不能到达目标点的问题。最后,通过实验仿真可知:与蚁群算法和免疫遗传算法相比,改进的D~* Lite遗传算法执行效率高,可以快速规划出全局最优路径。

关 键 词:D?Lite  遗传算法  自适应  路径规划

Research on Path Planning Based on Improved D*Lite Genetic Algorithm
Abstract:An improved D*Lite genetic algorithm is proposed to solve the problem that the genetic algorithm is prone to premature and slow convergence in the path planning of mobile robots. The algorithm was combined of the D*Lite algorithm with the genetic algorithm. By introducing the collision coefficient and visual detection technology, the path security was improved and the shortest path was found. In genetic algorithm design, dynamic adjustment of crossover and mutation probability were added to solve the problem that algorithm can not reach the target point when it falls into local optimal value in path planning. Finally, the experimental simulation shows that compared with the ant colony algorithm and immune genetic algorithm, the improved D*Lite genetic algorithm is efficient and can quickly plan the global optimal path.
Keywords:D*lite  Genetic algorithm  Self adaption  Path planning
本文献已被 CNKI 万方数据 等数据库收录!
点击此处可从《机床与液压》浏览原始摘要信息
点击此处可从《机床与液压》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号