In this paper, the Extended Set Membership (ESM) based on out-bounding ellipsoidal algorithm is used as a means of improving the performance of land vehicle position accuracy. Contrary to classical Extended Kalman Filtering (EKF), this approach provides guaranteed result in the sense that a set is computed that contains all of the feasible state that are consistent with the data and hypotheses. Simulation results are given to show that the ESM is superior to the EKF in state estimation of land vehicle navigation system.