Towards an Estimate of Confidence in a Road-Matched Location

This paper describes a method that provides an estimated location of an outdoor vehicle relative to a digital road map using Belief Theory and Kalman filtering. Firstly, an Extended Kalman Filter combines the DGPS and odometer measurements to produce an approximation of the vehicle’s pose, which is then used to select the most likely segment from a road network database. The selection strategy merges several criteria based on distance, direction and velocity measurements using Belief Theory. In this work, a particular attention is given to the elaboration of a Localization Uncertainty Gauge which takes into account imprecision of data sources (the sensors and the map) and uncertainty of the techniques used in the fusion process. This Gauge indicates the level of confidence assigned to the selected road by the system. Real experimental results illustrate this approach.