J4 ›› 2016, Vol. 13 ›› Issue (4): 669-678.doi: 10.1016/S1672-6529(16)60338-4

• 论文 • 上一篇    下一篇

Swarm Intelligence Algorithm Inspired by Route Choice Behavior

Daxin Tian1,2,3, Junjie Hu1, Zhengguo Sheng4, Yunpeng Wang1,2, Jianming Ma5, Jian Wang6   

  1. 1. Beijing Advanced Innovation Center for Big Data and Brain Computing, Beihang University, Beijing 100191, China
    2. School of Transportation Science and Engineering, Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems and Safety Control, Beihang University, Beijing 100191, China
    3. Jiangsu Province Collaborative Innovation Center of Modern Urban Traffic Technologies, Nanjing 210096, China
    4. Department of Engineering and Design, University of Sussex, Brighton BN1 9RH, UK
    5. The Texas Department of Transportation, Austin TX 78750, USA
    6. College of Computer Science and Technology, Jilin University, Changchun 130012, China
  • 收稿日期:2016-03-15 修回日期:2016-09-15 出版日期:2016-10-10 发布日期:2016-10-10
  • 通讯作者: Jian Wang E-mail:wangjian591@jlu.edu.cn
  • 作者简介:Daxin Tian1,2,3, Junjie Hu1, Zhengguo Sheng4, Yunpeng Wang1,2, Jianming Ma5, Jian Wang6

Swarm Intelligence Algorithm Inspired by Route Choice Behavior

Daxin Tian1,2,3, Junjie Hu1, Zhengguo Sheng4, Yunpeng Wang1,2, Jianming Ma5, Jian Wang6   

  1. 1. Beijing Advanced Innovation Center for Big Data and Brain Computing, Beihang University, Beijing 100191, China
    2. School of Transportation Science and Engineering, Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems and Safety Control, Beihang University, Beijing 100191, China
    3. Jiangsu Province Collaborative Innovation Center of Modern Urban Traffic Technologies, Nanjing 210096, China
    4. Department of Engineering and Design, University of Sussex, Brighton BN1 9RH, UK
    5. The Texas Department of Transportation, Austin TX 78750, USA
    6. College of Computer Science and Technology, Jilin University, Changchun 130012, China
  • Received:2016-03-15 Revised:2016-09-15 Online:2016-10-10 Published:2016-10-10
  • Contact: Jian Wang E-mail:wangjian591@jlu.edu.cn
  • About author:Daxin Tian1,2,3, Junjie Hu1, Zhengguo Sheng4, Yunpeng Wang1,2, Jianming Ma5, Jian Wang6

摘要:

Travelers’ route choice behavior, a dynamical learning process based on their own experience, traffic information, and influence of others, is a type of cooperation optimization and a constant day-to-day evolutionary process. Travelers adjust their route choices to choose the best route, minimizing travel time and distance, or maximizing expressway use. Because route choice behavior is based on human beings, the most intelligent animals in the world, this swarm behavior is expected to incorporate more intelligence. Unlike existing research in route choice behavior, the influence of other travelers is considered for updating route choices on account of the reality, which makes the route choice behavior from individual to swarm. A new swarm intelligence algorithm inspired by travelers’ route choice behavior for solving mathematical optimization problems is introduced in this paper. A comparison of the results of experiments with those of the classical global Particle Swarm Optimization (PSO) algorithm demonstrates the efficacy of the Route Choice Behavior Algorithm (RCBA). The novel algorithm provides a new approach to solving complex problems and new avenues for the study of route choice behavior.

关键词: swarm intelligence, route choice behavior, particle swarm optimization, mathematical optimization

Abstract:

Travelers’ route choice behavior, a dynamical learning process based on their own experience, traffic information, and influence of others, is a type of cooperation optimization and a constant day-to-day evolutionary process. Travelers adjust their route choices to choose the best route, minimizing travel time and distance, or maximizing expressway use. Because route choice behavior is based on human beings, the most intelligent animals in the world, this swarm behavior is expected to incorporate more intelligence. Unlike existing research in route choice behavior, the influence of other travelers is considered for updating route choices on account of the reality, which makes the route choice behavior from individual to swarm. A new swarm intelligence algorithm inspired by travelers’ route choice behavior for solving mathematical optimization problems is introduced in this paper. A comparison of the results of experiments with those of the classical global Particle Swarm Optimization (PSO) algorithm demonstrates the efficacy of the Route Choice Behavior Algorithm (RCBA). The novel algorithm provides a new approach to solving complex problems and new avenues for the study of route choice behavior.

Key words: swarm intelligence, route choice behavior, particle swarm optimization, mathematical optimization