Modeling of Drivers' Longitudinal Behavior

Summary, in English

In the last few years, many vehicle manufacturers have introduced advance driver support in some of their automobiles. One of those new features is adaptive cruise control (ACC), which extends the conventional cruise control system to control of relative speed and distance to other vehicles. In order to design an ACC controller, it is suitable to have a model of drivers' behavior. Our approach to find dynamical models of the drivers' behavior was to use system identification. Basic data analysis is made by means of system identification methodology, and several models of drivers' longitudinal behavior are proposed, including both linear regression models and subspace-based models. In various situations, detection for when a driver's behavior changes or deviates from the normal is useful. To that purpose, a GARCH (generalized autoregressive conditional heteroskedasticity) model was used to model the driver in situations such as arousal.

• Author: Johan Bengtsson; Rolf Johansson; Agneta Sjögren
• Department/s: Department of Automatic Control
• Publishing year: 2001
• Language: English
• Pages: 41-58
• Publication/Series: Nonlinear and Hybrid Systems in Automotive Control
• Full text: - 545 kB; Download statistics
• Links: http://dx.doi.org/10.1109/AIM.2001.936845
• Document type: Conference paper
• Publisher: Springer
• Topic: Control Engineering
• Conference name: 2001 IEEE/ASME International Conference on Advanced Intelligent Mechatronics
• Conference date: 2001-07-08
• Conference place: Como, Italy
• Status: Published