Precise vehicle positioning by cooperative feature association and tracking in vehicular networks

In cooperative intelligent transportation systems, precise vehicle positioning is a critical requirement that cannot be met by stand-alone Global Positioning Systems (GPSs). This paper proposes a distributed Bayesian data association and localization method, called Implicit Cooperative Positioning with Data Association (ICP-DA, where connected vehicles detect a set of passive features in the driving environment, solve the association task by pairing them with on-board sensor measurements and cooperatively localize the features to enhance the GPS accuracy. Results show that ICP-DA significantly outperforms GPS, with negligible performance loss compared to ICP with perfect data association knowledge.