Robust Landmark Selection for Mobile Robot Navigation

Precise navigation is a key capability of autonomous mobile robots and required for many tasks including transportation or docking. To guarantee a robust and accurate localization and navigation performance, many practical approaches rely on observations of artificial landmarks. This raises the question of where to place the landmarks along the desired trajectory of the robot. In this paper, we present a novel approach to landmark selection, which aims at selecting the minimal set of landmarks that bounds the uncertainty about the deviation of the robot from its desired trajectory. At the same time the selected landmark sets are robust against the fact that a certain number of landmarks can be obscured from view during operation. Our algorithm is highly efficient due to a linearization of the whole navigation cycle and employs submodular optimization, for which strong formal bounds on the approximation quality are known. In extensive experiments, also carried out with a real robot, we demonstrate that our approach outperforms several other methods and that it enables robust autonomous robot navigation in practice.