Comparison Of Different Approaches To Adaptation Of Unscented Kalman Filter For Non-Odometry Slam

Abstract

This paper is aimed at utilizing of an Unscented Kalman filter (UKF) for application on non-odometry SLAM problem. Non-odometry SLAM problem lacks state transitions function for part of state vector so theoretical part of the paper describes the derivation of three proposed modifications. The experimental part then shows experiments which evaluate modifications performance in reference to Extended Kalman filter. Experiments are based on simulation of monocular photogrammetry reconstruction problem.