Evaluating state-based intention recognition algorithms against human performance

Craig Schlenoff, Sebti Foufou

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we describe a novel intention recognition approach based on the representation of state information in a cooperative human-robot environment. We compare the output of the intention recognition algorithms to those of an experiment involving humans attempting to recognize the same intentions in a manufacturing kitting domain. States are represented by a combination of spatial relationships in a Cartesian frame along with cardinal direction information. Based upon a set of predefined high-level states relationships that must be true for future actions to occur, a robot can use the approaches described in this paper to infer the likelihood of subsequent actions occurring. This would enable the robot to better help the human with the operation or, at a minimum, better stay out of his or her way.

Original languageEnglish (US)
Title of host publicationRobot Intelligence Technology and Applications 2 - Results from the 2nd International Conference on Robot Intelligence Technology and Applications
PublisherSpringer-Verlag
Pages219-232
Number of pages14
ISBN (Electronic)9783319055817
DOIs
StatePublished - Jan 1 2014
Event2nd International Conference on Robot Intelligence Technology and Applications, RiTA 2013 - Denver, United States
Duration: Dec 18 2013Dec 20 2013

Publication series

NameAdvances in Intelligent Systems and Computing
Volume274
ISSN (Print)2194-5357

Other

Other2nd International Conference on Robot Intelligence Technology and Applications, RiTA 2013
CountryUnited States
CityDenver
Period12/18/1312/20/13

Fingerprint

Robots
Experiments

Keywords

  • Human performance
  • Human robot safety
  • Intention recognition
  • Ontologies
  • Rcc-8
  • Robotics
  • State-based representation

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Science(all)

Cite this

Schlenoff, C., & Foufou, S. (2014). Evaluating state-based intention recognition algorithms against human performance. In Robot Intelligence Technology and Applications 2 - Results from the 2nd International Conference on Robot Intelligence Technology and Applications (pp. 219-232). (Advances in Intelligent Systems and Computing; Vol. 274). Springer-Verlag. https://doi.org/10.1007/978-3-319-05582-4_19

Evaluating state-based intention recognition algorithms against human performance. / Schlenoff, Craig; Foufou, Sebti.

Robot Intelligence Technology and Applications 2 - Results from the 2nd International Conference on Robot Intelligence Technology and Applications. Springer-Verlag, 2014. p. 219-232 (Advances in Intelligent Systems and Computing; Vol. 274).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Schlenoff, C & Foufou, S 2014, Evaluating state-based intention recognition algorithms against human performance. in Robot Intelligence Technology and Applications 2 - Results from the 2nd International Conference on Robot Intelligence Technology and Applications. Advances in Intelligent Systems and Computing, vol. 274, Springer-Verlag, pp. 219-232, 2nd International Conference on Robot Intelligence Technology and Applications, RiTA 2013, Denver, United States, 12/18/13. https://doi.org/10.1007/978-3-319-05582-4_19
Schlenoff C, Foufou S. Evaluating state-based intention recognition algorithms against human performance. In Robot Intelligence Technology and Applications 2 - Results from the 2nd International Conference on Robot Intelligence Technology and Applications. Springer-Verlag. 2014. p. 219-232. (Advances in Intelligent Systems and Computing). https://doi.org/10.1007/978-3-319-05582-4_19
Schlenoff, Craig ; Foufou, Sebti. / Evaluating state-based intention recognition algorithms against human performance. Robot Intelligence Technology and Applications 2 - Results from the 2nd International Conference on Robot Intelligence Technology and Applications. Springer-Verlag, 2014. pp. 219-232 (Advances in Intelligent Systems and Computing).
@inproceedings{97092bf9aa02415c863e2a497b8def66,
title = "Evaluating state-based intention recognition algorithms against human performance",
abstract = "In this paper, we describe a novel intention recognition approach based on the representation of state information in a cooperative human-robot environment. We compare the output of the intention recognition algorithms to those of an experiment involving humans attempting to recognize the same intentions in a manufacturing kitting domain. States are represented by a combination of spatial relationships in a Cartesian frame along with cardinal direction information. Based upon a set of predefined high-level states relationships that must be true for future actions to occur, a robot can use the approaches described in this paper to infer the likelihood of subsequent actions occurring. This would enable the robot to better help the human with the operation or, at a minimum, better stay out of his or her way.",
keywords = "Human performance, Human robot safety, Intention recognition, Ontologies, Rcc-8, Robotics, State-based representation",
author = "Craig Schlenoff and Sebti Foufou",
year = "2014",
month = "1",
day = "1",
doi = "10.1007/978-3-319-05582-4_19",
language = "English (US)",
series = "Advances in Intelligent Systems and Computing",
publisher = "Springer-Verlag",
pages = "219--232",
booktitle = "Robot Intelligence Technology and Applications 2 - Results from the 2nd International Conference on Robot Intelligence Technology and Applications",

}

TY - GEN

T1 - Evaluating state-based intention recognition algorithms against human performance

AU - Schlenoff, Craig

AU - Foufou, Sebti

PY - 2014/1/1

Y1 - 2014/1/1

N2 - In this paper, we describe a novel intention recognition approach based on the representation of state information in a cooperative human-robot environment. We compare the output of the intention recognition algorithms to those of an experiment involving humans attempting to recognize the same intentions in a manufacturing kitting domain. States are represented by a combination of spatial relationships in a Cartesian frame along with cardinal direction information. Based upon a set of predefined high-level states relationships that must be true for future actions to occur, a robot can use the approaches described in this paper to infer the likelihood of subsequent actions occurring. This would enable the robot to better help the human with the operation or, at a minimum, better stay out of his or her way.

AB - In this paper, we describe a novel intention recognition approach based on the representation of state information in a cooperative human-robot environment. We compare the output of the intention recognition algorithms to those of an experiment involving humans attempting to recognize the same intentions in a manufacturing kitting domain. States are represented by a combination of spatial relationships in a Cartesian frame along with cardinal direction information. Based upon a set of predefined high-level states relationships that must be true for future actions to occur, a robot can use the approaches described in this paper to infer the likelihood of subsequent actions occurring. This would enable the robot to better help the human with the operation or, at a minimum, better stay out of his or her way.

KW - Human performance

KW - Human robot safety

KW - Intention recognition

KW - Ontologies

KW - Rcc-8

KW - Robotics

KW - State-based representation

UR - http://www.scopus.com/inward/record.url?scp=84927658421&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84927658421&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-05582-4_19

DO - 10.1007/978-3-319-05582-4_19

M3 - Conference contribution

AN - SCOPUS:84927658421

T3 - Advances in Intelligent Systems and Computing

SP - 219

EP - 232

BT - Robot Intelligence Technology and Applications 2 - Results from the 2nd International Conference on Robot Intelligence Technology and Applications

PB - Springer-Verlag

ER -