Using Coverage Maps to Represent the Environment of Mobile Robots

Generating maps belongs to the fundamental tasks of mobile robots. In the past, many approaches have used occupancy grid maps to represent the environment during mapping and exploration. Occupancy grids, however, are based on the assumption that each cell is either occupied or free. In this paper we introduce coverage maps as an alternative way of representing the environment of a robot. Coverage maps store for each cell of a given grid a posterior about the amount the corresponding cell is covered by an obstacle. We also present a model that allows us to update coverage maps upon input obtained from proximity sensors. We furthermore describe how to use coverage maps for a decision theoretic approach to exploration. Finally we present experimental results illustrating that coverage maps can be used to efficiently learn highly accurate models even if noisy sensors such as ultrasounds are used.