On the use of 2D navigable maps for enhancing ground vehicle localization

For ground vehicle localization, hybrid-GNSS localizers now use commonly dead-reckoning sensors, like odometers or inertial units. They are designed to increase the accuracy, the integrity and the availability of the localization information, particularly in areas where the satellite signals are subject to outages and multipaths. In this paper, a data-fusion method is proposed to take benefits of 2D navigable road-maps in a tightly-coupled approach. In such a problem, 3D modeling is mandatory to process the pseudo-range information of the satellites. Our proposal is to use a 2D map as a heading measure in a Earth tangential frame. This is called ¿map-aided odometry¿. A Kalman filter, gating the normalized innovation signals, is applied to merge the redundant exteroceptive information in a cautious way. Experimental results are reported to quantify the performance gain of the proposed approach relying on the map-aided technique. We show that this fusion scheme increases the accuracy and the availability of the provided localization specially in GNSS-challenging environments.