Bayesian Probabilistic Vehicle Lane Matching for Link-Level In-Vehicle Navigation

Today´s typical in-vehicle navigation systems that use the Global Positioning System (GPS) to measure longitudinal and latitudinal position of a vehicle do not have sufficient lane-positioning accuracy for detailed navigational tasks such as vehicle maneuvers and safety. This paper presents a unique estimation methodology that can determine a vehicle´s lane position in real time by mapping the spatial position measurements onto the specific lane the vehicle is running on with reference to a lane-enhanced digital map. This vehicle lane positioning system is described, comprising a low-cost real-time differential GPS system, a high accuracy digital map, and a lane-determination algorithm. Further, the developed low-cost system has been tested on a number of roadways and has performed very well when used with accurately surveyed map data. Lane-level positioning opens up the door to a number of new applications such as link-level maneuvering and vehicle safety applications