Skip to Main content Skip to Navigation
Journal articles

A Hybrid Bayesian Framework for Map Matching: Formulation Using Switching Kalman Filter

Cherif Smaili 1 Maan El Badaoui El Najjar 1 François Charpillet 2
1 STF - Systèmes Tolérants aux Fautes
CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189
2 MAIA - Autonomous intelligent machine
Inria Nancy - Grand Est, LORIA - AIS - Department of Complex Systems, Artificial Intelligence & Robotics
Abstract : This paper addresses an important issue for intelligent transportation system, namely the ability of vehicles to safely and reliably localize themselves within an a priori known road map network. For this purpose, we propose an approach based on hybrid dynamic bayesian networks enabling to implement in a unified framework two of the most successful families of probabilistic model commonly used for localization: linear Kalman filters and Hidden Markov Models. The combination of these two models enables to manage and manipulate multi-hypotheses and multi-modality of observations characterizing Map Matching problems and it improves integrity approach. Another contribution of the paper is a chained-form state space representation of vehicle evolution which permits to deal with non-linearity of the used odometry model. Experimental results, using data from encoders’ sensors, a DGPS receiver and an accurate digital roadmap, illustrate the performance of this approach, especially in ambiguous situations.
Complete list of metadata

https://hal.inria.fr/hal-01091321
Contributor : François Charpillet <>
Submitted on : Friday, December 5, 2014 - 10:35:07 AM
Last modification on : Friday, December 11, 2020 - 6:44:03 PM

Identifiers

Citation

Cherif Smaili, Maan El Badaoui El Najjar, François Charpillet. A Hybrid Bayesian Framework for Map Matching: Formulation Using Switching Kalman Filter. Journal of Intelligent and Robotic Systems, Springer Verlag, 2014, 74 (3-4), pp.18. ⟨10.1007/s10846-013-9844-4⟩. ⟨hal-01091321⟩

Share

Metrics

Record views

663