Stochastic driver speed control behavior modeling in urban intersections using risk potential-based motion planning framework

In unsignalized intersections with poor visibility, proactive driving with hazard anticipation is required in order to avoid collisions with other traffic participants from a blind corner. However, for elderly drivers and novice drivers, it is difficult to recognize potential hazardous area and difficult to select an appropriate speed to pass the intersections safely. To assist such drivers, a driver model which can recommend the appropriate speed by learning driving data of expert drivers based on a statistical approach is useful for a driver assistance system. The proposed method automatically estimates parameters of the driver model from the actual driving data by defining risk potential functions for representing braking behaviors while passing through intersections, oncoming vehicles and pedestrians. To evaluate the proposed method, the driving data of instructors of a driving school are collected. The results show that the accuracy (RMSE) of the estimated braking behavior model is 2.5 km/h against the actual data.