Highlighted Map for Mobile Robot Localization and Its Generation Based on Reinforcement Learning

This article proposes a new kind of map for mobile robot localization and its generation method. We call the map a highlighted map, on which uniquely shaped objects (landmarks) in monotonous environments are highlighted. By using this map, robots can use such landmarks as clues for localization, and thus, their localization performance can be improved without having to update their sensors or online computation. Furthermore, this map can be easily combined with many other existing localization algorithms. We formulate the problem of making a highlighted map and propose a numerical optimization method based on reinforcement learning. This optimization method automatically identifies and emphasizes the important landmarks on the map. The generated highlighted map is adapted to situations such as the sensor characteristics and robot dynamics because this method uses the actual sensor measurement data. It is proven that the optimization converges under certain technical assumptions. We performed a numerical simulation and real-world experiment showing that the highlighted map provides better localization accuracy than a conventional map.