Entropy based feature selection scheme for real time simultaneous localization and map building

We propose a novel entropy-based method for feature selection in order to reduce the computational burden for real time simultaneous localization and map building (SLAM) for mobile robot navigation. Our approach is based on information (entropy) theory together with a data association method to initialize new features into the map, match measurements to the map features, and remove out-of-date features. The selected features are optimum in the sense that fusion of measurements from those features with existing information would yield the most entropy reduction in estimating the robot location and the map features´ locations. Our method has the advantage of selecting a suitable number of features by considering the computational constraint in real time implementations. Simulation results show that the proposed entropy based feature selection strategy is effective in dealing with the map scaling problem in SLAM.