Handling uncertain input in multi-user human-robot interaction

Simon Keizer; Mary Ellen Foster; Andre Gaschler; Manuel Giuliani; Amy Isard; Oliver Lemon

doi:10.1109/ROMAN.2014.6926271

Handling uncertain input in multi-user human-robot interaction

Simon Keizer, Mary Ellen Foster, Andre Gaschler, Manuel Giuliani, Amy Isard, Oliver Lemon

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

In this paper we present results from a user evaluation of a robot bartender system which handles state uncertainty derived from speech input by using belief tracking and generating appropriate clarification questions. We present a combination of state estimation and action selection components in which state uncertainty is tracked and exploited, and compare it to a baseline version that uses standard speech recognition confidence score thresholds instead of belief tracking. The results suggest that users are served fewer incorrect drinks when the uncertainty is retained in the state.

Original language	English
Title of host publication	Proceedings of the 23rd IEEE International Symposium on Robot and Human Interactive Communication (IEEE RO-MAN 2014)
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	312-317
Number of pages	6
ISBN (Print)	978-1-4799-6763-6
DOIs	https://doi.org/10.1109/ROMAN.2014.6926271
Publication status	Published - 1 Aug 2014

Access to Document

10.1109/ROMAN.2014.6926271

keizer-etal-roman2014Accepted author manuscript, 1.56 MB

Cite this

Keizer, S., Foster, M. E., Gaschler, A., Giuliani, M., Isard, A., & Lemon, O. (2014). Handling uncertain input in multi-user human-robot interaction. In Proceedings of the 23rd IEEE International Symposium on Robot and Human Interactive Communication (IEEE RO-MAN 2014) (pp. 312-317). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/ROMAN.2014.6926271

@inproceedings{e7b62be67a9c4091b83762959ca75bb2,

title = "Handling uncertain input in multi-user human-robot interaction",

abstract = "In this paper we present results from a user evaluation of a robot bartender system which handles state uncertainty derived from speech input by using belief tracking and generating appropriate clarification questions. We present a combination of state estimation and action selection components in which state uncertainty is tracked and exploited, and compare it to a baseline version that uses standard speech recognition confidence score thresholds instead of belief tracking. The results suggest that users are served fewer incorrect drinks when the uncertainty is retained in the state.",

author = "Simon Keizer and Foster, {Mary Ellen} and Andre Gaschler and Manuel Giuliani and Amy Isard and Oliver Lemon",

year = "2014",

month = aug,

day = "1",

doi = "10.1109/ROMAN.2014.6926271",

language = "English",

isbn = "978-1-4799-6763-6",

pages = "312--317",

booktitle = "Proceedings of the 23rd IEEE International Symposium on Robot and Human Interactive Communication (IEEE RO-MAN 2014)",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

address = "United States",

}

Keizer, S, Foster, ME, Gaschler, A, Giuliani, M, Isard, A & Lemon, O 2014, Handling uncertain input in multi-user human-robot interaction. in Proceedings of the 23rd IEEE International Symposium on Robot and Human Interactive Communication (IEEE RO-MAN 2014). Institute of Electrical and Electronics Engineers (IEEE), pp. 312-317. https://doi.org/10.1109/ROMAN.2014.6926271

Handling uncertain input in multi-user human-robot interaction. / Keizer, Simon; Foster, Mary Ellen; Gaschler, Andre et al.

Proceedings of the 23rd IEEE International Symposium on Robot and Human Interactive Communication (IEEE RO-MAN 2014). Institute of Electrical and Electronics Engineers (IEEE), 2014. p. 312-317.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Handling uncertain input in multi-user human-robot interaction

AU - Keizer, Simon

AU - Foster, Mary Ellen

AU - Gaschler, Andre

AU - Giuliani, Manuel

AU - Isard, Amy

AU - Lemon, Oliver

PY - 2014/8/1

Y1 - 2014/8/1

N2 - In this paper we present results from a user evaluation of a robot bartender system which handles state uncertainty derived from speech input by using belief tracking and generating appropriate clarification questions. We present a combination of state estimation and action selection components in which state uncertainty is tracked and exploited, and compare it to a baseline version that uses standard speech recognition confidence score thresholds instead of belief tracking. The results suggest that users are served fewer incorrect drinks when the uncertainty is retained in the state.

AB - In this paper we present results from a user evaluation of a robot bartender system which handles state uncertainty derived from speech input by using belief tracking and generating appropriate clarification questions. We present a combination of state estimation and action selection components in which state uncertainty is tracked and exploited, and compare it to a baseline version that uses standard speech recognition confidence score thresholds instead of belief tracking. The results suggest that users are served fewer incorrect drinks when the uncertainty is retained in the state.

U2 - 10.1109/ROMAN.2014.6926271

DO - 10.1109/ROMAN.2014.6926271

M3 - Conference contribution

SN - 978-1-4799-6763-6

SP - 312

EP - 317

BT - Proceedings of the 23rd IEEE International Symposium on Robot and Human Interactive Communication (IEEE RO-MAN 2014)

PB - Institute of Electrical and Electronics Engineers (IEEE)

ER -

Handling uncertain input in multi-user human-robot interaction

Abstract

Access to Document

Fingerprint

Cite this