Driver behavior modeling based on database of personal mobility driving in urban area

This paper proposes the modeling of longitudinal driving behavior based on urban driving data of one-person micro-scale electric vehicle for developing the personalized driver adaptive assistance system. The system enables us to realize a practical cooperative safety system that suits individual maneuvering behavior in real-world traffic situation. First, the urban driving data is collected by on-road experiments using continuous sensing drive recorder equipped in the micro-scale electric vehicle. Next, the human pedal operation for longitudinal vehicle control is divided into several modes. Consequently, the driver model is formulated by setting up the input-output relationship of each operation mode and the mode switching rules based on the collected urban driving data. It is proved that the proposed driver model is effective to express driver pedal operation. Finally, the proposed driver model is applied to detect hurry driving by comparison between the model-based estimated pedal operation and the measured value in hurry driving situation.