Real-time vehicle localization by using a top-down process

In this paper, a localization system for a mobile robot is proposed, using a top-down multi-sensorial approach and exploiting a map of the environment. Nowadays the wide development of maps make relevant localization approachesable to use such maps. A crucial point of all localization systems is the way of the data provided by different sensors are fused. The proposed approach is based on a Bayesian network able to select the best feature to detect in the map with the best sensor in order to reach both precision and integrity of the robot localization. This process is working in real time and was validated in simulated and real environments.