Activity recognition from the interactions between an assistive robotic walker and human users

Author

Patel, Mitesh ; Miro, Jaime Valls ; Dissanayake, Gamini

Author_Institution

ARC Center of Excellence for Autonomous Syst., Univ. of Technol. Sydney, Sydney, NSW, Australia

fYear

2011

fDate

8-11 March 2011

Firstpage

221

Lastpage

222

Abstract

Detection of individuals´ intention from a sequence of actions is an open and complex problem. In this paper we present a smart walker as mobility aid which can interpret the users´ behaviour patterns to recognize their intentions and consequently act as an intelligent assistant. The result of the experiments performed in this paper demonstrates the potential of dynamic bayesian networks (DBN), in relation to their dynamic and unsupervised nature, for realistic human-robot interaction modelling.

Keywords

belief networks; gesture recognition; human-robot interaction; mobile robots; DBN; activity recognition; assistive robotic walker; behaviour patterns; dynamic Bayesian networks; human users; human-robot interaction modelling; intelligent assistant; smart walker; unsupervised nature; Accuracy; Bayesian methods; Computational modeling; Humans; Legged locomotion; Probabilistic logic; Activity Recognition; Mobility Assistive Robotics; Probabilistic Models;

fLanguage

English

Publisher

ieee

Conference_Titel

Human-Robot Interaction (HRI), 2011 6th ACM/IEEE International Conference on

Conference_Location

Lausanne

ISSN

2167-2121

Print_ISBN

978-1-4673-4393-0

Electronic_ISBN

2167-2121

Type

conf

Filename

6281307