[2018 ]Unscented Kalman Filtering-Supported Accident Prevention System Based on Prediction of Vehicle Tire Forces Guided by Using Digital Map
Improvements of traffic safety is the ultimate objective of intelligent vehicle systems. This paper presents a novel approach for preventing traffic accidents by predicting vehicle’s tire forces in the upcoming roads. The biggest advantage of this approach is to warn the drivers about an upcoming dangerous situation before the accidents. It provides more time for the drivers to make correct decisions to handle the situations. The main contributions of this paper include two aspects: the algorithm of using digital maps to retrieve the road information ahead of vehicle and the algorithm of estimating and evaluating vehicle’s dynamics status. A new map data structure is defined to facilitate map information retrievals. The sensor fusion methods like Kalman filter and unscented Kalman filter are employed to minimize the estimation error of the observations. Experimental data validated the proposed algorithm as an efficient method to prevent traffic accidents.