Feature Selection Criteria for Real Time EKF-SLAM Algorithm

This paper presents a seletion procedure for environmet features for the correction stage of a SLAM (Simultaneous Localization and Mapping) algorithm based on an Extended Kalman Filter (EKF). This approachdecreases the computational time of the correction stage which allows for real and constant-time implementationsof the SLAM. The selection procedure consists in chosing the features the SLAM system state covariance is moresensible to. The entire system is implemented on a mobile robot equipped with a range sensor laser. The featuresextracted from the environment correspond to lines and corners. Experimental results of the real time SLAMalgorithm and an analysis of the processing-time consumed by the SLAM with the feature selection procedureproposed are shown. A comparison between the feature selection approach proposed and the classical sequentialEKF-SLAM along with an entropy feature selection approach is also performed