Low-cost GPS sensor improvement using stereovision fusion

This paper presents a new real-time hierarchical (topological/metric) localization system applied to the robust self-location of a vehicle in large-scale urban environments. Our proposal improves the current vehicle navigation systems based only on GPS sensor. It is exclusively based on the information provided by both, a low-cost wide-angle stereo camera and a low-cost GPS. A low level metric process obtains a 3D sequential mapping of natural landmarks and the vehicle location/orientation. GPS measurements are integrated within this low level, improving vehicle positioning. A higher topological processing level, based on fingerprints and the multi level relaxation (MLR) algorithm, has been added to reduce the global error keeping real-time constraints. Some experimental tests, using a real car navigation system on urban environments with loop closures, have been carried out. Main results and conclusions are presented.