Low Cost Sensors Ego Localization with IMM Approach for unusual Maneuvers

This paper presents the problematic of outdoor vehicle localization in unusual maneuvers under the IMM (interacting multiple model) approach. The IMM, contrary to the non modular methods, is based on the discretization of the vehicle evolution space into simple maneuvers, represented each by a simple dynamic model such as constant velocity or constant turning etc. This allows the method to be optimized for highly dynamic vehicles. In this work, we focus on the various vehicle dynamics identification in some special driving situations, including very strong accelerations, turning with a high speed (more than 15 mldrs^-1) or backward driving with stops. The presented results are based on real measurements collected from different scenarios. These results show a real interest in using the IMM method in order to reach our goal.