Abstract
A risk estimation system based on Bayesian Networks using a driver model is proposed for achieving a risk estimation function in traffic situations for safe driving support systems. The proposed system uses input traffic and vehicle information to evaluate subsequent driving operations such as acceleration and steering using Bayesian networks. The vehicle trajectory is then forecasted using a dynamical physical model. Next the risk of collision with other vehicles is calculated by considering the trajectories of other vehicles and the possible trajectories of the car itself based on the output probabilities of the Bayesian network and the predictions of the dynamical model. In the scene of the intersection, the effectiveness of the proposal system is shown by comparing in the simulator the scene where the accident occurs to the scene where it does not, and then specifying the difference between the risk transition coefficients of both cases. In the future, the proposed system can be applied to a system that prevents traffic accidents by giving to the automatic control system of the vehicle the optimal evasion driving operation.
