Modified Unscented Kalman Filter for improving the integrated visual navigation system

Abstract

This paper presents a modified Unscented Kalman Filter (UKF) for improving the position and orientation errors of the integrated visual navigation system. The visual navigation system is the integration of Inertial Navigation System (INS) with observations of Visual Odometry (VO) system in a vehicle. The multi objective optimization (MOO) for optimizing the parameters used in the unscented transformation which is the main procedure of UKF in order to decrease the position and orientation errors of the vehicle that is used. The (MOO) with Genetic Algorithm (GA) is used to optimize the parameters. The simulation results present the reduction of final position and orientation errors and Root Mean Square Error (RMSE), using optimized UKF instead of conventional UKF.