This thesis is concerned with modeling of driver behavior based on data collected from real traffic using an advanced instrumented vehicle. In particular, the focus is on driver-following behavior (often called car-following in transport science) for microscopic simulation of road traffic systems. In addition, the modeling methodology developed can be applied for the design of human-centered control algorithms in adaptive cruise control (ACC) and other longitudinal active-safety technologies.

Driver behavior is a constant research topic in the modeling of traffic systems and Intelligent Transportation Systems (ITS), which could be traced back to the work of GeneralMotor (GM) Co. in 1950’s. In the early time, researchers were only interested in the development of driver models fulfilling basic physical properties and producing reasonable flow dynamics on a macroscopic level. With the booming interest on driver modeling on a microscopic level and needs in ITS developments, researchers now emphasize modeling using microscopic data acquired from real world. To follow this research trend, a methodological framework on car-following data acquisition, analysis and modeling has been developed step by step in this thesis, and the basic idea is to build a computational model for car-following behavior by exploration of collected data. To carry out the work, different techniques within the field of modern Artificial Intelligence (AI), namely Computational Intelligence (CI)1, have been applied in the research subtasks e.g. information estimation, behavioral regime classification, regime model integration and model estimation. Therefore, a preliminary introduction of the CI methods being used in this thesis work is included in the text.