Joint Action Understanding improves Robot-to-Human Object Handover

Elena Corina Grigore, Kerstin I Eder, Anthony Pipe, Christopher R Melhuish, Ute B Leonards

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

39 Citations (Scopus)

Abstract

The development of trustworthy human-assistive robots is a challenge that goes beyond the traditional boundaries of engineering. Essential components of trustworthiness are safety, predictability and usefulness. In this paper we demonstrate that the integration of joint action understanding from human-human interaction into the human-robot context can significantly improve the success rate of robot-to-human object handover tasks. We take a two layer approach. The first layer handles the physical aspects of the handover. The robot’s decision to release the object is informed by a Hidden Markov Model that estimates the state of the handover. We then introduce a higher-level cognitive layer that models behaviour to be expected from the human user in a handover situation inspired by human-human handover observations. In particular, we focus on the inclusion of eye gaze / head orientation into the robot’s decision making. Our results demonstrate that by integrating these non-verbal cues the success rate of robot-to-human handovers can be significantly improved, resulting in a more robust and therefore safer system.
Original languageEnglish
Title of host publicationIEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Place of PublicationTokyo
Pages4622-4629
Number of pages8
Volumetbc
Editiontbc
ISBN (Electronic)tbc
Publication statusPublished - Nov 2013
EventIEEE/RSJ International Conference on Intelligent Robots and Systems - Tokyo, Japan
Duration: 3 Nov 20138 Nov 2013

Conference

ConferenceIEEE/RSJ International Conference on Intelligent Robots and Systems
CountryJapan
CityTokyo
Period3/11/138/11/13

Structured keywords

  • Brain and Behaviour
  • Cognitive Science
  • Visual Perception

Keywords

  • Human Robot Interaction, Safety, Verification and Validation, Joint Action, Joint Attention

Fingerprint Dive into the research topics of 'Joint Action Understanding improves Robot-to-Human Object Handover'. Together they form a unique fingerprint.

Cite this