Mobile robot mapping and localization in non-static environments

Abstract

Whenever mobile robots act in the real world, they need to be able to deal with non-static objects. In the context of mapping, a common technique to deal with dynamic objects is to lter out the spurious measurements cor-responding to such objects. In this paper, we present a novel approach to estimate typical congurations of dy-namic areas in the environment of a mobile robot. Our approach clusters local grid maps to identify the possi-ble congurations. We furthermore describe how these clusters can be utilized within a Rao-Blackwellized par-ticle lter to localize a mobile robot in a non-static en-vironment. In practical experiments carried out with a mobile robot in a typical ofce environment, we demon-strate the advantages of our approach compared to alter-native techniques for mapping and localization in dy-namic environments.