华南理工大学学报(自然科学版) ›› 2015, Vol. 43 ›› Issue (8): 135-143.doi: 10.3969/j.issn.1000-565X.2015.08.020

• 交通运输工程 • 上一篇    下一篇

改进的基于模糊推理的车辆跟驰行为分析方法

邱小平1,2,3 孙若晓1 于丹1 杨达1,2†   

  1. 1. 西南交通大学 交通运输与物流学院,四川 成都 610031; 2. 西南交通大学 综合交通运输智能化国家地方联合
    工程实验室,四川 成都 610031; 3. 综合运输四川省重点实验室,四川 成都 610031
  • 收稿日期:2015-01-14 修回日期:2015-04-23 出版日期:2015-08-25 发布日期:2015-07-01
  • 通信作者: 杨达(1985-),男,博士,讲师,主要从事智能交通研究. E-mail:yangd8@gmail.com
  • 作者简介: 邱小平(1976-),男,博士,教授,主要从事交通运输规划与管理研究. E-mail: qxp@home.swjtu.edu.cn
  • 基金资助:
     国家自然科学基金资助项目(51408509);四川省科技厅项目(2013GZX0167,2014ZR0091);西南交通大学中央高
    校基本科研业务经费专项资金资助项目(SWJTU11CX080);成都市科技局项目(2014RK0000056ZF,2014RK0000072ZF)

An Improved Method to Analyze Car-Following Behavior Based on Fuzzy Inference System#br#

Qiu Xiao-ping1,2,3  Sun Ruo-xiao Yu Dan Yang Da1,2   

  1. 1. School of Transportation and Logistics,Southwest Jiaotong University,Chengdu 610031,Sichuan,China; 2. Comprehensive Intelligent Transportation National and Local joint Engineering Laboratory,Southwest Jiaotong University,Chengdu 610031,Sichuan,China; 3. Comprehensive Transportation Key Laboratory of Sichuan Province,Southwest Jiaotong University,Chengdu 610031,Sichuan,China
  • Received:2015-01-14 Revised:2015-04-23 Online:2015-08-25 Published:2015-07-01
  • Contact: 杨达(1985-),男,博士,讲师,主要从事智能交通研究. E-mail:yangd8@gmail.com
  • About author: 邱小平(1976-),男,博士,教授,主要从事交通运输规划与管理研究. E-mail: qxp@home.swjtu.edu.cn
  • Supported by:
    Supported by the National Natural Science Foundation of China(51408509)and the Foundation of Science and
    Technology Department of Sichuan Province(2013GZX0167,2014ZR0091)

摘要: 为精确建立车辆跟驰模糊推理系统,提出采用模糊聚类分析的方法为输入、输出变量划分模糊集,并求出对应的高斯隶属度函数;引入 Takagi-Sugeno 推理方法进行车辆跟驰模糊推理与去模糊化处理;利用 NGSIM 数据对模糊推理系统和 Gipps 跟驰模型进行参数标定并评价. 结果表明:改进的建立车辆跟驰模糊推理系统的方法能真实反映数据本身的特征和驾驶员的心理生理特性,并且所建立的模糊推理系统与 Gipps 模型相比,其误差指标的仿真精度均有较大提升.

关键词:  车辆跟驰, 模糊推理系统, 模糊聚类, 高斯隶属度函数, Takagi-Sugeno 推理方法

Abstract:  In order to establish the car-following fuzzy inference system (FIS) accurately,the fuzzy clustering
analysis method is adopted to divide input and output variables into various fuzzy sets,and the corresponding Gaussian membership function is determined. Then,the Takagi-Sugeno inference method is introduced to conductthe car-following fuzzy inference and the defuzzification. Finally,the fuzzy inference system and the Gippscar-following model are calibrated and evaluated by using NGSIM data. The results show that the improved method to establish the car-following fuzzy inference systemcan truly reflect the characteristics of the data itself and the driver’s psychological and physiological features,and that the established fuzzy inference system achieves a much higher simulation accuracy of error indexes in comparison with the Gipps model.

Key words:  car following, fuzzy inference system, fuzzy clustering, Gaussian membership function, Takagi-Su-geno inference method

中图分类号: