International Journal of Control, Automation, and Systems (2012) 10(3):517-528 DOI 10.1007/s12555-012-0308-6 ISSN:1598-6446 eISSN:2005-4092 http://www.springer.com/12555 A Hierarchical Fuzzy System for Modeling Driver’s Behavior Sehraneh Ghaemi, Sohrab Khanmohammadi, Mohammad Ali Tinati, and Mohammad Ali Badamchizadeh Abstract: The study of human behavior during driving is of primary importance for improving the driver’s security. In this study, we propose a hierarchical driver_vehicle_environment fuzzy system to analyze driver’s behavior under stress conditions on a road. We include climate, road and car condi- tions in fuzzy modeling. For obtaining fuzzy rules, experts’ opinions are benefited by means of ques- tionnaires on effects of parameters such as climate, road and car conditions on driving capabilities. The number of fuzzy rules is optimized by Particle Swarm Optimization (PSO) algorithm. Also the fre- quency of pressing on brake and gas pedals and the number of car’s direction changes are used to de- termine the driver’s behavior under different conditions. Three different positions are considered for driving and decision making; one position in driving lane and two positions in opposite lane. A fuzzy model called Model 1 is presented for modeling the change of steering angle and speed control by con- sidering time distances with existing cars in these three positions, the information about the speed and direction of car, and the steering angle of car. The behaviors of different drivers under two stress condi- tions are investigated. Also we obtained two other models based on fuzzy rules called Model 2 and Model 3 by using Sugeno fuzzy inference. Model 2 has two linguistic terms and Model 3 has four lin- guistic terms for estimating the time distances with other cars. The results of three models are com- pared. The comparative studies have shown that simulation results are in good agreement with the real world situations. Keywords: Decision making, driver_vehicle_environment system, driver’s behavior, fuzzy modeling, mathematical modeling, stress condition. 1. INTRODUCTION Vehicles play important roles in the development of civilization and economy in different societies. However, vehicles also cause problems such as transport congestion, environmental pollution, etc. Perhaps the most serious problem among them is accidents. Hence there is a great need to develop accident reduction procedures. In recent years safety in driving has been improved by using new control ideas. Macadam [1] developed an optimal preview control algorithm; however, this algorithm could only be applied to single input single output systems. Fenton [2] applied Linear Quadratic algorithm to design a controller for steering. Lee [3] developed a discrete time preview control algorithm for four-wheel steering vehicles and found that the control accuracy was improved substantially by taking the preview behavior into account. Macadam and Johnson [4] presented the use of elementary neural networks to represent the driver steering behavior in double lane change and S-curve maneuvers. Harris and An [5] adopted a Cerebellar Model Articulation Controller (CMAC) for developing an adaptive driver model for collision avoidance in the case of longitudinal lane following. Data describing characteristics of driving environ- ments are not generally available to drivers in precise numerical format. Instead drivers perceive and describe the environment in imprecise terms such as ‘high speed’ or ‘enough space to change lanes’. An important outcome of imprecision is the possibility of assigning more than one symbolic value at the same time to the same variable with different degrees of truth in each of these values. Because of fuzzy logic’s ability to handle these cases, it has been successfully used in modeling human behavior in general and driver behavior in particular. The fuzzy logic has proven to be a very effective tool for handling imprecision and uncertainty. This makes fuzzy logic a powerful candidate tool in most traffic engineering studies [6]. Kamada et al. [7] proposed a fuzzy logic lateral controller. Hessburg and Tomizuka [8] developed a fuzzy logic controller for vehicle lateral guidance which consisted of three sub- controllers: preview, feedback and gain scheduling. Michon introduced a hierarchical control structure for the driving task and suggested this structure as basis for a comprehensive driving behavior model. Lin et al. [9] analyzed the relationship between the change of human’s physiological and psychological states and the performance on vehicle control. Gohara et © ICROS, KIEE and Springer 2012 __________ Manuscript received October 21, 2009; revised November 14, 2011; accepted March 15, 2012. Recommended by Editorial Board member Sungshin Kim under the direction of Editor Young-Hoon Joo. Sehraneh Ghaemi, Sohrab Khanmohammadi, Mohammad Ali Tinati, and Mohammad Ali Badamchizadeh are with the Faculty of Electrical and Computer Engineering, University of Tabriz, Tabriz, Iran (e-mails: {ghaemi, khan, tinati, mbadamchi}@ tabrizu.ac.ir.).