Physical interaction learning: Behavior adaptation in cooperative human-robot tasks involving physical contact

Shuhei Ikemoto, Hani Ben Amor, Takashi Minato, Hiroshi Ishiguro, Bernhard Jung

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

10 Citations (Scopus)

Abstract

In order for humans and robots to engage in direct physical interaction several requirements have to be met. Among others, robots need to be able to adapt their behavior in order to facilitate the interaction with a human partner. This can be achieved using machine learning techniques. However, most machine learning scenarios to-date do not address the question of how learning can be achieved for tightly coupled, physical touch interactions between the learning agent and a human partner. This paper presents an example for such human in-the-loop learning scenarios and proposes a computationally cheap learning algorithm for this purpose. The efficiency of this method is evaluated in an experiment, where human care givers help an android robot to stand up.

Original languageEnglish (US)
Title of host publicationProceedings - IEEE International Workshop on Robot and Human Interactive Communication
Pages504-509
Number of pages6
DOIs
StatePublished - 2009
Externally publishedYes
Event18th IEEE International Symposium on Robot and Human Interactive, RO-MAN 2009 - Toyama, Japan
Duration: Sep 27 2009Oct 2 2009

Other

Other18th IEEE International Symposium on Robot and Human Interactive, RO-MAN 2009
CountryJapan
CityToyama
Period9/27/0910/2/09

Fingerprint

Robots
Learning systems
Learning algorithms
Experiments

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence
  • Human-Computer Interaction

Cite this

Ikemoto, S., Ben Amor, H., Minato, T., Ishiguro, H., & Jung, B. (2009). Physical interaction learning: Behavior adaptation in cooperative human-robot tasks involving physical contact. In Proceedings - IEEE International Workshop on Robot and Human Interactive Communication (pp. 504-509). [5326164] https://doi.org/10.1109/ROMAN.2009.5326164

Physical interaction learning : Behavior adaptation in cooperative human-robot tasks involving physical contact. / Ikemoto, Shuhei; Ben Amor, Hani; Minato, Takashi; Ishiguro, Hiroshi; Jung, Bernhard.

Proceedings - IEEE International Workshop on Robot and Human Interactive Communication. 2009. p. 504-509 5326164.

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

Ikemoto, S, Ben Amor, H, Minato, T, Ishiguro, H & Jung, B 2009, Physical interaction learning: Behavior adaptation in cooperative human-robot tasks involving physical contact. in Proceedings - IEEE International Workshop on Robot and Human Interactive Communication., 5326164, pp. 504-509, 18th IEEE International Symposium on Robot and Human Interactive, RO-MAN 2009, Toyama, Japan, 9/27/09. https://doi.org/10.1109/ROMAN.2009.5326164
Ikemoto S, Ben Amor H, Minato T, Ishiguro H, Jung B. Physical interaction learning: Behavior adaptation in cooperative human-robot tasks involving physical contact. In Proceedings - IEEE International Workshop on Robot and Human Interactive Communication. 2009. p. 504-509. 5326164 https://doi.org/10.1109/ROMAN.2009.5326164
Ikemoto, Shuhei ; Ben Amor, Hani ; Minato, Takashi ; Ishiguro, Hiroshi ; Jung, Bernhard. / Physical interaction learning : Behavior adaptation in cooperative human-robot tasks involving physical contact. Proceedings - IEEE International Workshop on Robot and Human Interactive Communication. 2009. pp. 504-509
@inproceedings{4b30cf77f38b40d19102d9441934cc04,
title = "Physical interaction learning: Behavior adaptation in cooperative human-robot tasks involving physical contact",
abstract = "In order for humans and robots to engage in direct physical interaction several requirements have to be met. Among others, robots need to be able to adapt their behavior in order to facilitate the interaction with a human partner. This can be achieved using machine learning techniques. However, most machine learning scenarios to-date do not address the question of how learning can be achieved for tightly coupled, physical touch interactions between the learning agent and a human partner. This paper presents an example for such human in-the-loop learning scenarios and proposes a computationally cheap learning algorithm for this purpose. The efficiency of this method is evaluated in an experiment, where human care givers help an android robot to stand up.",
author = "Shuhei Ikemoto and {Ben Amor}, Hani and Takashi Minato and Hiroshi Ishiguro and Bernhard Jung",
year = "2009",
doi = "10.1109/ROMAN.2009.5326164",
language = "English (US)",
isbn = "9781424450817",
pages = "504--509",
booktitle = "Proceedings - IEEE International Workshop on Robot and Human Interactive Communication",

}

TY - GEN

T1 - Physical interaction learning

T2 - Behavior adaptation in cooperative human-robot tasks involving physical contact

AU - Ikemoto, Shuhei

AU - Ben Amor, Hani

AU - Minato, Takashi

AU - Ishiguro, Hiroshi

AU - Jung, Bernhard

PY - 2009

Y1 - 2009

N2 - In order for humans and robots to engage in direct physical interaction several requirements have to be met. Among others, robots need to be able to adapt their behavior in order to facilitate the interaction with a human partner. This can be achieved using machine learning techniques. However, most machine learning scenarios to-date do not address the question of how learning can be achieved for tightly coupled, physical touch interactions between the learning agent and a human partner. This paper presents an example for such human in-the-loop learning scenarios and proposes a computationally cheap learning algorithm for this purpose. The efficiency of this method is evaluated in an experiment, where human care givers help an android robot to stand up.

AB - In order for humans and robots to engage in direct physical interaction several requirements have to be met. Among others, robots need to be able to adapt their behavior in order to facilitate the interaction with a human partner. This can be achieved using machine learning techniques. However, most machine learning scenarios to-date do not address the question of how learning can be achieved for tightly coupled, physical touch interactions between the learning agent and a human partner. This paper presents an example for such human in-the-loop learning scenarios and proposes a computationally cheap learning algorithm for this purpose. The efficiency of this method is evaluated in an experiment, where human care givers help an android robot to stand up.

UR - http://www.scopus.com/inward/record.url?scp=72849124490&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=72849124490&partnerID=8YFLogxK

U2 - 10.1109/ROMAN.2009.5326164

DO - 10.1109/ROMAN.2009.5326164

M3 - Conference contribution

SN - 9781424450817

SP - 504

EP - 509

BT - Proceedings - IEEE International Workshop on Robot and Human Interactive Communication

ER -