交通运输系统工程与信息 ›› 2018, Vol. 18 ›› Issue (6): 55-62.

• 智能交通系统与信息技术 • 上一篇    下一篇

基于改进蚁群算法的多AGV泊车路径规划

郭保青* a, b,郝树运 a,朱力强 a, b,余祖俊 a, b   

  1. 北京交通大学 a. 机械与电子控制工程学院;b. 载运工具先进制造与测控技术教育部重点实验室,北京 100044
  • 收稿日期:2018-07-09 修回日期:2018-08-27 出版日期:2018-12-25 发布日期:2018-12-25
  • 作者简介:郭保青(1978-),男,河北人,副教授.
  • 基金资助:

    国家重点研发计划/ The National Key Research and Development Program of China(2016YFB1200100).

Multi-AGV Parking Path Planning Based on Improved Ant Colony Algorithm

GUO Bao-qing a, b, HAO Shu-yun a, ZHU Li-qiang a, b, YU Zu-jun a, b   

  1. a. School of Mechanical, Electronic and Control Engineering; b. Key Laboratory of Vehicle Advanced Manufacturing, Measuring and Control Technology, Ministry of Education, Beijing Jiaotong University, Beijing 100044, China
  • Received:2018-07-09 Revised:2018-08-27 Online:2018-12-25 Published:2018-12-25

摘要:

针对智能停车库中自动导引小车(Automated Guided Vehicle,AGV)存取车的路径规划问题,提出一种基于改进蚁群算法的多AGV泊车路径规划方法.单AGV路径规划方面,在基本蚁群算法基础上引入蚂蚁回退策略来增强适应性,同时改进启发式信息和信息素更新策略提高算法的收敛速度和寻优能力.多AGV路径规划方面,提出改进冲突解决策略来解决多AGV之间的冲突,其中采用临时规避—重新寻路策略来解决相向冲突.针对某典型停车场抽象模型的仿真结果表明,改进蚁群算法寻路成功率更高,并具有较强的全局搜索能力和较快的收敛速度,改进冲突解决策略能合理避免冲突,可以满足多AGV存取车路径规划的要求.

关键词: 智能交通, 路径规划, 改进蚁群算法, AGV, 回退策略, 临时规避

Abstract:

For automated guided vehicle (AGV) path planning in smart parking garages, a multi-AGV path planning method based on improved ant colony algorithm is proposed. For single AGV, fallback strategy is introduced to the basic ant colony algorithm to enhance the adaptability. And a new heuristic information and novel pheromone update strategies are also presented to improve the convergence speed and optimization ability. To solve the opposite conflict of multi-AGV, an improved conflict resolution strategy of temporary avoidance and path re-planning is proposed. The simulation results for a typical real underground parking garage show that the improved ant colony algorithm has higher rate of successful path finding, stronger global search capability and faster convergence speed. Our algorithm can solve multi-AGV conflicts and satisfy multi-AGV path planning requirements.

Key words: intelligent transportation, path planning, improved ant colony algorithm, AGV, fallback strategy, temporary avoidance

中图分类号: