Learning responsive robot behavior by imitation

Hani Ben Amor, David Vogt, Marco Ewerton, Erik Berger, Bernhard Jung, Jan Peters

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

20 Citations (Scopus)

Abstract

In this paper we present a new approach for learning responsive robot behavior by imitation of human interaction partners. Extending previous work on robot imitation learning, that has so far mostly concentrated on learning from demonstrations by a single actor, we simultaneously record the movements of two humans engaged in on-going interaction tasks and learn compact models of the interaction. Extracted interaction models can thereafter be used by a robot to engage in a similar interaction with a human partner. We present two algorithms for deriving interaction models from motion capture data as well as experimental results on a humanoid robot.

Original languageEnglish (US)
Title of host publicationIEEE International Conference on Intelligent Robots and Systems
Pages3257-3264
Number of pages8
DOIs
StatePublished - 2013
Externally publishedYes
Event2013 26th IEEE/RSJ International Conference on Intelligent Robots and Systems: New Horizon, IROS 2013 - Tokyo, Japan
Duration: Nov 3 2013Nov 8 2013

Other

Other2013 26th IEEE/RSJ International Conference on Intelligent Robots and Systems: New Horizon, IROS 2013
CountryJapan
CityTokyo
Period11/3/1311/8/13

Fingerprint

Robot learning
Robots
Data acquisition
Demonstrations

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Software
  • Computer Vision and Pattern Recognition
  • Computer Science Applications

Cite this

Ben Amor, H., Vogt, D., Ewerton, M., Berger, E., Jung, B., & Peters, J. (2013). Learning responsive robot behavior by imitation. In IEEE International Conference on Intelligent Robots and Systems (pp. 3257-3264). [6696819] https://doi.org/10.1109/IROS.2013.6696819

Learning responsive robot behavior by imitation. / Ben Amor, Hani; Vogt, David; Ewerton, Marco; Berger, Erik; Jung, Bernhard; Peters, Jan.

IEEE International Conference on Intelligent Robots and Systems. 2013. p. 3257-3264 6696819.

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

Ben Amor, H, Vogt, D, Ewerton, M, Berger, E, Jung, B & Peters, J 2013, Learning responsive robot behavior by imitation. in IEEE International Conference on Intelligent Robots and Systems., 6696819, pp. 3257-3264, 2013 26th IEEE/RSJ International Conference on Intelligent Robots and Systems: New Horizon, IROS 2013, Tokyo, Japan, 11/3/13. https://doi.org/10.1109/IROS.2013.6696819
Ben Amor H, Vogt D, Ewerton M, Berger E, Jung B, Peters J. Learning responsive robot behavior by imitation. In IEEE International Conference on Intelligent Robots and Systems. 2013. p. 3257-3264. 6696819 https://doi.org/10.1109/IROS.2013.6696819
Ben Amor, Hani ; Vogt, David ; Ewerton, Marco ; Berger, Erik ; Jung, Bernhard ; Peters, Jan. / Learning responsive robot behavior by imitation. IEEE International Conference on Intelligent Robots and Systems. 2013. pp. 3257-3264
@inproceedings{2fafa959a18f47b0ac37b469dfeaa55b,
title = "Learning responsive robot behavior by imitation",
abstract = "In this paper we present a new approach for learning responsive robot behavior by imitation of human interaction partners. Extending previous work on robot imitation learning, that has so far mostly concentrated on learning from demonstrations by a single actor, we simultaneously record the movements of two humans engaged in on-going interaction tasks and learn compact models of the interaction. Extracted interaction models can thereafter be used by a robot to engage in a similar interaction with a human partner. We present two algorithms for deriving interaction models from motion capture data as well as experimental results on a humanoid robot.",
author = "{Ben Amor}, Hani and David Vogt and Marco Ewerton and Erik Berger and Bernhard Jung and Jan Peters",
year = "2013",
doi = "10.1109/IROS.2013.6696819",
language = "English (US)",
isbn = "9781467363587",
pages = "3257--3264",
booktitle = "IEEE International Conference on Intelligent Robots and Systems",

}

TY - GEN

T1 - Learning responsive robot behavior by imitation

AU - Ben Amor, Hani

AU - Vogt, David

AU - Ewerton, Marco

AU - Berger, Erik

AU - Jung, Bernhard

AU - Peters, Jan

PY - 2013

Y1 - 2013

N2 - In this paper we present a new approach for learning responsive robot behavior by imitation of human interaction partners. Extending previous work on robot imitation learning, that has so far mostly concentrated on learning from demonstrations by a single actor, we simultaneously record the movements of two humans engaged in on-going interaction tasks and learn compact models of the interaction. Extracted interaction models can thereafter be used by a robot to engage in a similar interaction with a human partner. We present two algorithms for deriving interaction models from motion capture data as well as experimental results on a humanoid robot.

AB - In this paper we present a new approach for learning responsive robot behavior by imitation of human interaction partners. Extending previous work on robot imitation learning, that has so far mostly concentrated on learning from demonstrations by a single actor, we simultaneously record the movements of two humans engaged in on-going interaction tasks and learn compact models of the interaction. Extracted interaction models can thereafter be used by a robot to engage in a similar interaction with a human partner. We present two algorithms for deriving interaction models from motion capture data as well as experimental results on a humanoid robot.

UR - http://www.scopus.com/inward/record.url?scp=84893734170&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84893734170&partnerID=8YFLogxK

U2 - 10.1109/IROS.2013.6696819

DO - 10.1109/IROS.2013.6696819

M3 - Conference contribution

AN - SCOPUS:84893734170

SN - 9781467363587

SP - 3257

EP - 3264

BT - IEEE International Conference on Intelligent Robots and Systems

ER -