Multi-Modal Anchoring for Human-Robot-Interaction

J. Fritsch, M. Kleinehagenbrock, S. Lang, T. Pl{\"o}tz and G. A. Fink and G. Sagerer
Robotics and Autonomous Systems, Special issue on Anchoring Symbols to Sensor Data in Single and Multiple Robot Systems, 43(2--3), pages 133-147, 2003.

BibTeX

Abstract

This paper presents a hybrid approach for tracking humans with a mobile robot that integrates face and leg detection results extracted from image and laser range data, respectively. The different percepts are linked to their symbolic counterparts legs and face by anchors as defined by Coradeschi and Saffiotti. In order to anchor the composite object person we extend the anchoring framework to combine different component anchors belonging to the same person. This allows to deal with perceptual algorithms having different spatio-temporal properties and provides a structured way for integrating anchor data from multiple modalities. An evaluation demonstrates the performance of our approach.