Representing and Selecting Landmarks in Autonomous Learning of Robot Navigation

Navigation based on detected landmarks is an important facet of robot navigation. This work investigates into a qualitative representation of landmarks for an autonomous learning task where a robot learns a goal directed navigation strategy with reinforcement learning. We discuss how to build a suitable landmark-based representation. In particular, we focus on selection of landmarks to regard when experiencing a multitude of landmarks, because representing all of them would blow up the state space inappropriately. Thus, we examine strategies for this selection. Furthermore, we introduce a background knowledge based structure-aware landmark selection mechanism to limit landmark observation to the cases where it is really needed.