This research is focused on driver behavior in traffic, especially during car-following situations and safety critical events. Driving behavior is considered as a human decision process in this research which provides opportunities for an artificial driver agent simulator to learn according to naturalistic driving data. This thesis presents two mechine learning methodologies that can be applied to simulate driver naturalistic driving behavior including risk-taking behavior during an incident and lateral evasive behavior which have not yet been captured in existing literature. Two special machine learning approaches Backpropagation (BP) neural network and Neuro-Fuzzy Actor Critic Reinforcement Learning (NFACRL) are proposed to model driver behavior during car-following situation and safety critical events separately. In addition to that, as part of the research, state-of-the-art car-following models are also analyzed and compared to BP neural network approach. Also, driver heterogeneity analyzed by NFACRL method is discussed. Finally, it presents the findings and limitations drawn from each of the specific issues, along with recommendations for further research. / Master of Science

The aim of the research project RADimFOKUS was to develop and evaluate a cyclist waming system (CWS) prototype in order to prevent safety critical events (SCEs), such as accidents, for the specifically vulnerable group of cyclists and, in turn, contributing to an enhanced traffic safety for this sustainable and healthy mode of transport. The basic idea of the system was to warn cyclists in case a SCE is detected. Although research about CWS is rather scarce, :first evaluations of such systems are promising [1]. Considering actual developments and trends, the CWS detects SCEs based on connected traffic information and is in a fust step intended for the implementation in electrified bicycles (i.e. pedelecs), where power supply is provided by the integrated battery. In the scope of the project, we performed the following 3 stages, which are described in the current contribution: (1) Development of the waming model and user interface for the CWS prototype, (2) Development of a bicycle simulator and implementation of the CWS interface for user studies, and (3) First evaluation of the CWS prototype in the scope of a bicycle simulator user study.