Developing a car-following model with consideration of driver’s behavior based on an Adaptive Neuro-Fuzzy Inference System

Article type: Research Article

Authors: Wang, Junhua^a | Zhang, Lanfang^{a; *} | Lu, Siwen^b | Wang, Zhongren^c

Affiliations: [a] School of Transportation Engineering, Tongji University, Cao’an Hwy., Shanghai, China | [b] Shuxin Town Government, Chongmin County, Shanghai, China | [c] Department of Transportation, California, USA

Correspondence: [*] Corresponding author. Lanfang Zhang, School of Transportation Engineering, Tongji University, 4800 Cao’an Hwy., Shanghai 201804, China. Tel./Fax: +86 21 69585717; E-mail: zlf2276@163.com.

Abstract: Based on a car following experiment with a synchronized fifth-wheel system, the Adaptive Neuro-Fuzzy Inference System (ANFIS) is utilized to develop a car following model. Wavelet analysis was used to denoise the high frequently collected fluctuating data. Drivers’ reaction time was calculated using Cross Correlation analysis. In the car-following model developed, relative speed, distance headway between leading and following vehicle, and speed of following vehicle are the three input parameters; while acceleration of the following vehicle is the output. Comparing with the traditional General Motor (GM) car-following model, the results show that the ANFIS-based car-following model can better describe the freeway driving behavior.

Keywords: Car-following, Adaptive Neuro-Fuzzy Inference, driver behavior, reaction time

DOI: 10.3233/IFS-151770

Journal: Journal of Intelligent & Fuzzy Systems, vol. 30, no. 1, pp. 461-466, 2016