Learning object-manipulation verbs for human-robot communication

Komei Sugiura, Naoto Iwahashi

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

16 Citations (Scopus)

Abstract

This paper proposes a machine learning method for mapping object-manipulation verbs with sensory inputs and motor outputs that are grounded in the real world. The method learns motion concepts demonstrated by a user and generates a sequence of motions, using reference-point-dependent probability models. Four components, needed to learn objectmanipulation verbs, are estimated from camera images; (1) a trajector and landmark, which are the objects of transitive verbs; (2) a reference point; (3) an intrinsic coordinate system; and (4) parameters of the motion's probabilistic model. The motion concepts are learned using hidden Markov models (HMMs). In the motion generation phase, our method then combines HMMs to generate trajectories to accomplish goal-oriented tasks. Results from simulation experiments in which our method generates motion by combining learned motion primitives are shown.

Original languageEnglish
Title of host publicationWorkshop on Multimodal Interfaces in Semantic Interaction, WMISI 2007, Proceedings - 9th International Conference on Multimodal Interfaces, ICMI 2007, Post-Conference Workshop
Pages32-38
Number of pages7
DOIs
Publication statusPublished - 2007 Dec 1
Externally publishedYes
EventWorkshop on Multimodal Interfaces in Semantic Interaction, WMISI 2007 - 9th International Conference on Multimodal Interfaces, ICMI 2007 - Nagoya, Japan
Duration: 2007 Nov 152007 Nov 15

Publication series

NameWorkshop on Multimodal Interfaces in Semantic Interaction, WMISI 2007, Proceedings - 9th International Conference on Multimodal Interfaces, ICMI 2007, Post-Conference Workshop

Conference

ConferenceWorkshop on Multimodal Interfaces in Semantic Interaction, WMISI 2007 - 9th International Conference on Multimodal Interfaces, ICMI 2007
Country/TerritoryJapan
CityNagoya
Period07/11/1507/11/15

Keywords

  • HMM
  • human-robot interaction
  • motion generation

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Software

Fingerprint

Dive into the research topics of 'Learning object-manipulation verbs for human-robot communication'. Together they form a unique fingerprint.

Cite this