Near-optimal Landmark Selection for Mobile Robot Navigation

The ability to accurately localize themselves is a fundamental pre-condition for service robots designed to carry out navigation and transportation tasks. Because of the high degree of dynamics in populated and real-world environments, often artificial landmarks are used to achieve the desired accuracy in localization. In this paper we consider the problem of optimally placing landmarks for robots navigating frequently on similar trajectories. Our method maximizes conditional mutual information of the states of the robot given the landmark observations. It uses a greedy algorithm which approximates the solution of the NP-hard maximization problem. For this algorithm, we derive a tight constant-factor bound on the approximation error. We furthermore evaluate the selected landmark sets in extensive experiments carried out both in simulation and with a real robot.