Localization system of autonomous vehicle via Kalman filtering

This paper proposes a localization system for autonomous vehicle via Kalman filtering. Absolute positioning is required to obtain successful operation of an autonomous vehicle's process. To get reliable positions, there are two ways, either using a GPS or dead reckoning from velocity and steering angle of the vehicle. Error elements exist in both the uses of GPS and dead reckoning. Stable position data of the autonomous vehicle is necessary for a successful operation even with the error elements. Kalman filter is suggested between the GPS and dead reckoning to get stable position data. Correction is performed during the localization of the processing position by using Kalman filter between GPS and dead reckoning.