Particle filters for accurate localization of communicant vehicles using GPS and vision systems

For most tracking applications the Kalman filter is reliable and efficient, but it is limited to a relatively restricted class of linear Gaussian problems. Particle filters are proving to be dependable methods for stochastic dynamic estimation. We will present in this paper, an accurate localization strategy for vehicles in urban environments based on the particle filters, the communication between vehicles and the vision systems when GPS data is unavailable or has a poor quality of signal due to the multi-tracks or bad satellite visibility. The method relies on the particle filter for the treatment of the GPS data and the vision data that will be collected from the loading system in the vehicles. From the modelling point of view, a particularity of the method is due to the use of vision systems and the communication through a wireless communication devices. The experiments on our fleet of communicating vehicles carried out in real conditions prove the feasibility of this approach.