Druckansicht der Internetadresse:

Fakultät für Mathematik, Physik und Informatik

Angewandte Informatik III - Robotik und eingebettete Systeme - Prof. Dr. Dominik HENRICH

Seite drucken

Publikationsdatenbank

All fields:
Author:
Project:
Year:

Publication

Online intention learning for human-robot interaction by scene observation
Muhammad Awais , Dominik Henrich

Abstract (english)
Intention recognition plays a key role in the cooperation among the humans. An intention describes an action or sequence of actions to be performed for achieving the intended purpose. The cooperating humans learn each others intentions while cooperation. In this paper we propose three ways how a robot can learn the intention of the cooperating human. In the first case, the robot learns the human intention by mapping the known human intention given in terms of scene information to the observed action sequence. The actions are already known to the robot. In the second case, the robot is only given the human actions but the robot estimates the human intention in terms of the changes that occur in the scene due to the human actions. The robot learns the human intention by mapping the observed action sequence to the human intention. The human intention is estimated from the scene information. In the third case, only the scene information is used in order to learn the human intention mapping. The scene information is used to infer the human actions as well as the human intention.

Publication data

Year: 2012
Publication date: 21. May 2012
Source: 2012 IEEE International Workshop on Advanced Robotics and its Social Impacts (ARSO), TU München
Referrer: https://www.ai3.uni-bayreuth.de/de/publikationen/resypub/index.php?mode=pub_show&pub_ref=awais2012a

BibTeX

@ARTICLE{awais2012a,
  TITLE             = "Online intention learning for human-robot interaction by scene observation",
  AUTHOR            = "Awais, Muhammad and Henrich, Dominik",
  YEAR              = "2012",
  JOURNAL           = "2012 IEEE International Workshop on Advanced Robotics and its Social Impacts (ARSO), TU München",
  HOWPUBLISHED      = "\url{https://www.ai3.uni-bayreuth.de/de/publikationen/resypub/index.php?mode=pub_show&pub_ref=awais2012a}",
}

Download

Filename   Size   Language   Format
awais2012a.Online.intention.learning.for.humanrobot.interact
ion.by.scene.observation.pdf
  242K   english   PDF download preprint

Twitter Youtube-Kanal UBT-A Kontakt