A hybrid control method for elderly companion robot based on behavior-based reaction and RNNPB model

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

A hybrid control method based on the behavior-based reaction and the recurrent neural network with parametric bias (RNNPB) model is proposed for the elderly companion robot. Firstly, a multimodal human-robot interaction framework is proposed using agent technology, which is composed of multimodal interaction module, cognitive module, and interaction control module. Then a hybrid control method for elderly companion robot is given, which is composed of behavior-based reaction control and evolutional control using the recurrent neural network with parametric bias (RNNPB) model. Finally, the experiments and results show the effectiveness of the hybrid control method.

Original languageEnglish
Title of host publication2010 8th World Congress on Intelligent Control and Automation, WCICA 2010
Pages6480-6484
Number of pages5
DOIs
StatePublished - 2010
Event2010 8th World Congress on Intelligent Control and Automation, WCICA 2010 - Jinan, China
Duration: 7 Jul 20109 Jul 2010

Publication series

NameProceedings of the World Congress on Intelligent Control and Automation (WCICA)

Conference

Conference2010 8th World Congress on Intelligent Control and Automation, WCICA 2010
Country/TerritoryChina
CityJinan
Period7/07/109/07/10

Keywords

  • Behavior-based reaction
  • Elderly companion robot
  • Multi-agent
  • Multi-agent interaction
  • RNNPB

Fingerprint

Dive into the research topics of 'A hybrid control method for elderly companion robot based on behavior-based reaction and RNNPB model'. Together they form a unique fingerprint.

Cite this