Probabilistic reference and grounding with PRAGR for dialogues with robots

Abstract

In this paper, we present a system for effective referential human–robot communication in the face of perceptual deviation using the Probabilistic Reference And GRounding mechanism PRAGR and vague feature models based on prototypes. PRAGR can handle descriptions of arbitrary complexity including spatial relations and uses flexible concept assignment in generation and resolution of referring expressions for bridging conceptual gaps in referential robot–robot or human–robot interaction. We evaluate the benefit of using vague as compared to crisp properties regarding referential success and robustness towards perspective alignment error in referential robot–robot and human–robot communication.

Keywords:

• Reference handling
• symbol grounding
• human–machine interaction
• vagueness
• perceptual deviation
• dialogue

Acknowledgements

Funding by the Deutsche Forschungsgemeinschaft (DFG) for the SFB/TR 8 Spatial Cognition, project I5-[DiaSpace], by the European Commission through FP7 Marie Curie IEF actions under project COGNITIVE-AMI (https://sites.google.com/site/cognitiveami/) (GA 328763), by the Universität Bremen under project Cognitive Qualitative Descriptions and Applications (https://sites.google.com/site/cogqda/) (CogQDA) and by Technologieallianz Oberfranken (TAO) is gratefully acknowledged. We thank Florian Maaß and Thomas Röfer from the B-Human RoboCup team Bremen for providing the robotic platforms. We thank Kees van Deemter and three anonymous reviewers for highly valuable feedback.

Notes

No potential conflict of interest was reported by the authors.

1 http://tx4.us/nbs-iscc.htm (Accessed August 2014)

Additional information

Funding

This work was supported by the Deutsche Forschungsgemeinschaft (DFG) for the SFB/TR 8 Spatial Cognition, project I5-[DiaSpace]; European Commission through FP7 Marie Curie IEF actions under project COGNITIVE-AMI (GA 328763); Universität Bremen under project Cognitive Qualitative Descriptions and Applications (CogQDA); Technologieallianz Oberfranken (TAO).