A two-stage verification process for Car-to-X mobility data based on path prediction and probabilistic maneuver recognition

Security is a prerequisite for successfully establishing Car-to-X technology on the market. Sender authentication, message integrity as well as plausibility of the message content represent one of the key aspects in this domain. While the first two requirements are covered by means of cryptography, the latter is still subject to current research. Recent works in the area of vehicle behavior analysis include promising approaches, but are still prone to errors in case of highly dynamic driving maneuvers. In this work we present a novel two-stage verification process for reliable Car-to-X mobility data verification. The first stage consists of a mobility estimator realized by a Kalman filter. The Kalman filter is thereby used to evaluate received mobility data with respect to the path history of vehicles. In the second stage a plausibility check for highly dynamic traffic situations is applied using probabilistic traffic maneuver recognition based on Hidden Markov Models. The overall framework is implemented and its effectiveness is evaluated by means of real world experiments.