A representation for spatial reasoning in robotic planning

Abstract

In order to close the sense-plan-act loop, a robotrequires several capabilities: it must match perceived contextwith general knowledge about the environment, instantiateplans into the metric space of the real world, and detectand react to contingencies. All of these capabilities includesome form of spatial reasoning — however, at different levelsof abstraction. Perception generates metric spatial knowledge,while general knowledge about the environment is often quali-tative in nature. Similarly, plans may call for the achievementof qualitative spatial relations, but actions must be preciselyinstantiated in metric space. This paper focuses on integratingqualitative and metric spatial reasoning for closing the looparound perception and actuation. We propose a knowledgerepresentation and reasoning technique, grounded on well-established spatial calculi, for combining qualitative and metricknowledge and obtaining solutions expressed in actionablemetric terms.