Towards an Informed Search Behavior for Domestic Robots

Abstract

In this paper we present an object search behavior for a mobile domestic robot that reduces the search space by applying a novel kind of spatial attention system. Different visual cues are mapped in a SLAM-like manner in order to identify hypotheses for possible object locations. These locations are scanned for known objects using a recognition method consisting of two complementary pathways - a detector measuring color distributions and a classifier using a SVM with a Pyramid Matching Kernel. We show the usefulness of the proposed approach by conducting an evaluation in a real world apartment scenario.