首页|U型障碍物多方向多层填充的移动机器人改进蚁群算法

U型障碍物多方向多层填充的移动机器人改进蚁群算法

扫码查看
原文链接
  • 国家科技期刊平台
  • NETL
  • NSTL
  • 万方数据
  • 维普
针对传统蚁群算法在移动机器人路径规划中典型的U型障碍物死锁问题,提出了一种U型障碍物多方向多层填充的改进蚁群算法.首先证明了路径规划的最优解不会进入U型障碍物之中;其次证明了运用此多方向多层填充法在填充U型障碍物解决死锁问题的同时,不会造成原有通路的阻塞,具有原通路保持性,且填充的迭代次数与迭代总时间少;之后对填充图形的迭代次数给出了理论性的判定,此填充方法不仅适用于U型障碍物还适用于其它可填充区域,且其对于可填充区域可实现完全填充;最后将此填充方法与蚁群算法结合.仿真结果表明,改进蚁群算法相比于传统蚁群算法有效率提升.
Improved Ant Colony Algorithm for Mobile Robot with Multi-Directional and Multi-Layer Filling of U-Shaped Obstacles
Aiming at the typical deadlock problem of U-shaped obstacles when applying traditional ant colony algorithm in mobile robot path planning,an improved ant colony algorithm with multi-directional and multi-layer filling of U-shaped obstacles is proposed.Firstly,it is proved that the optimal solution of path planning will not enter the U-shaped obstacles;Secondly,it is proved that the multi-directional and multi-layer filling method can fill U-shaped obstacles to solve the deadlock problem without blocking the original path,which has the retention of the original path and has less filling iteration times and total iteration time;After that,the number of iterations of the filling graph is theoretically determined.This filling method is not only suitable for U-shaped obstacles,but also suitable for other filling areas,and it can completely fill the fillable areas;Finally,this filling method is combined with ant colony algorithm to realize mobile robot path planning.The simulation results show that the improved ant colony algorithm is more efficient than the traditional ant colony algorithm.

mobile robotpath planningimproved ant colony algorithmu-shaped obstaclemultidirectional multilayer filling method

陈青桢、龚家宝、于潇雁、邵宇飞

展开 >

福州大学 机械工程及自动化学院,福州 350116

福州大学 流体动力与电液智能控制福建省高校重点实验室,福州 350116

山东鑫光节能科技有限公司,山东烟台 264006

移动机器人 路径规划 改进蚁群算法 U型障碍物 多方向多层填充法

国家自然科学基金福建省自然科学基金福建省工业机器人基础部件技术重大研发平台项目

517415022020J014502014H21010011

2024

10.13433/j.cnki.1003-8728.20220259

机械科学与技术
西北工业大学

机械科学与技术

CSTPCD北大核心
影响因子：0.565
ISSN：1003-8728
年,卷(期)：2024.43(4)
  • 16