What makes a good demonstration for robot learning generalization?

Maram Sakr, H. F.Machiel Van Der Loos, Dana Kulić, Elizabeth Croft

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

Abstract

Robot learning from demonstration (LfD) is a common approach that allows robots to perform tasks after observing teacher's demonstrations. Thus, users without a robotics background could use LfD to teach robots. However, such users may provide low-quality demonstrations. Besides, demonstration quality plays a crucial role in robot learning and generalization. Hence, it is important to ensure quality demonstrations before using them for robot learning. This abstract proposes an approach for quantifying demonstration quality which in turn enhances robot learning and generalization.

Original languageEnglish
Title of host publicationHRI'21 - Companion of the 2021 ACM/IEEE International Conference on Human-Robot Interaction
EditorsElizabeth Broadbent, David Feil-Seifer, Daniel Szafir
Place of PublicationNew York NY USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages607-609
Number of pages3
ISBN (Electronic)9781450382908
DOIs
Publication statusPublished - 2021
EventAnnual ACM/IEEE International Conference on Human-Robot Interaction (HRI) 2021 - Online, United States of America
Duration: 9 Mar 202111 Mar 2021
Conference number: 16th
https://humanrobotinteraction.org/2021/ (Website)

Publication series

NameACM/IEEE International Conference on Human-Robot Interaction
PublisherThe Association for Computing Machinery
ISSN (Electronic)2167-2148

Conference

ConferenceAnnual ACM/IEEE International Conference on Human-Robot Interaction (HRI) 2021
Abbreviated titleHRI 2021
Country/TerritoryUnited States of America
CityOnline
Period9/03/2111/03/21
Internet address

Keywords

  • Inverse optimal control
  • Learning from demonstration

Cite this