A collision risk assessment approach as a basis for the on-board warning generation in cars

The safety of unprotected road users, such as pedestrians, cyclists and motorcyclists, can be improved by means of intelligent technology. In this paper, the topic of on-board warning generation for cars moving in an urban scenario is addressed. A warning can be based on the evaluation of the collision risk. The risk assessment task is performed off-line relying on suitable stochastic models of the unprotected road users behaviour, and on deterministic dynamical model of the car, as well as applying a Monte Carlo simulation-based technique.