abstract

What Makes a Good Demonstration for Robot Learning Generalization?

Authors:

H. F. Machiel Van der Loos,

Elizabeth CroftAuthors Info & Claims

HRI '21 Companion: Companion of the 2021 ACM/IEEE International Conference on Human-Robot Interaction

Pages 607 - 609

https://doi.org/10.1145/3434074.3446362

Published: 08 March 2021 Publication History

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.

References

[1]

Brenna D Argall, Sonia Chernova, Manuela Veloso, and Brett Browning. 2009. A survey of robot learning from demonstration. Robotics and autonomous systems 57, 5 (2009), 469--483.

[2]

Maya Cakmak and Andrea L Thomaz. 2014. Eliciting good teaching from humans for machine learners. Artificial Intelligence 217 (2014), 198--215.

Digital Library

[3]

Sylvain Calinon. 2016. A tutorial on task-parameterized movement learning and retrieval. Intelligent service robotics 9, 1 (2016), 1--29.

[4]

Jason Chen and Alex Zelinsky. 2003. Programing by demonstration: Coping with suboptimal teaching actions. The International Journal of Robotics Research 22, 5 (2003), 299--319.

[5]

Jia Deng,Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei. 2009. Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition. Ieee, 248--255.

[6]

Kerstin Fischer, Franziska Kirstein, Lars Christian Jensen, Norbert Krüger, Kamil Kukliński, Maria Vanessa aus der Wieschen, and Thiusius Rajeeth Savarimuthu. 2016. A comparison of types of robot control for programming by demonstration. In 2016 11th ACM/IEEE International Conference on Human-Robot Interaction (HRI). IEEE, 213--220.

[7]

Fabrizio Flacco, Alessandro De Luca, and Oussama Khatib. 2012. Prioritized multi-task motion control of redundant robots under hard joint constraints. In 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems. IEEE, 3970--3977.

[8]

Tamar Flash and Neville Hogan. 1985. The coordination of arm movements: an experimentally confirmed mathematical model. Journal of neuroscience 5, 7 (1985), 1688--1703.

[9]

Daniel H Grollman and Aude Billard. 2011. Donut as I do: Learning from failed demonstrations. In 2011 IEEE International Conference on Robotics and Automation. IEEE, 3804--3809.

[10]

Noémie Jaquier, Leonel Rozo, Darwin G Caldwell, and Sylvain Calinon. 2020. Geometry-aware manipulability learning, tracking, and transfer. The International Journal of Robotics Research (2020). https://doi.org/10.1177/0278364920946815

Digital Library

[11]

Michael Kaiser, Holger Friedrich, and Rudiger Dillmann. 1995. Obtaining good performance from a bad teacher. In Programming by Demonstration vs. Learning from Examples Workshop at ML, Vol. 95.

[12]

Jonathan Feng-Shun Lin, Vincent Bonnet, Adina M Panchea, Nacim Ramdani, Gentiane Venture, and Dana Kulić. 2016. Human motion segmentation using cost weights recovered from inverse optimal control. In IEEE/RAS Int Conf Hum Robot. 1107--1113.

[13]

Peter Moylan and Brian Anderson. 1973. Nonlinear regulator theory and an inverse optimal control problem. IEEE Trans. Automat. Control 18, 5 (1973), 460--465.

[14]

Takayuki Osa, Joni Pajarinen, Gerhard Neumann, J AndrewBagnell, Pieter Abbeel, and Jan Peters. 2018. An algorithmic perspective on imitation learning. arXiv preprint arXiv:1811.06711 (2018).

[15]

Richard A Schmidt and Craig A Wrisberg. 2008. Motor learning and performance: A situation-based learning approach. Human kinetics.

[16]

Aran Sena and Matthew Howard. 2020. Quantifying teaching behavior in robot learning from demonstration. The International Journal of Robotics Research 39, 1 (2020), 54--72.

Digital Library

[17]

Nikolaus Vahrenkamp and Tamim Asfour. 2015. Representing the robot's workspace through constrained manipulability analysis. Autonomous Robots 38, 1 (2015), 17--30.

Digital Library

[18]

Nikolaus Vahrenkamp, Tamim Asfour, Giorgio Metta, Giulio Sandini, and Rüdiger Dillmann. 2012. Manipulability analysis. In 2012 12th ieee-ras international conference on humanoid robots (humanoids 2012). IEEE, 568--573.

[19]

Anna-Lisa Vollmer, Manuel Mühlig, Jochen J Steil, Karola Pitsch, Jannik Fritsch, Katharina J Rohlfing, and Britta Wrede. 2014. Robots show us how to teach them: Feedback from robots shapes tutoring behavior during action learning. PloS one 9, 3 (2014), e91349.

Cited By

Abal-Fernández SCaramazana-Zarzosa CLoureiro-Casalderrey MMartínez SBalaguer CDíaz-de-María FGonzález-Díaz I(2023)Learning RL policies for anticipative assistive robots by simulating human-robot interactions in real scenarios using egocentric videos2023 IEEE International Conference on Robotics and Biomimetics (ROBIO)10.1109/ROBIO58561.2023.10354837(1-8)Online publication date: 4-Dec-2023
https://doi.org/10.1109/ROBIO58561.2023.10354837
Sakr MLi ZVan der Loos HKulic DCroft E(2022)Quantifying Demonstration Quality for Robot Learning and GeneralizationIEEE Robotics and Automation Letters10.1109/LRA.2022.31919507:4(9659-9666)Online publication date: Oct-2022
https://doi.org/10.1109/LRA.2022.3191950

Index Terms

What Makes a Good Demonstration for Robot Learning Generalization?
1. Computer systems organization
  1. Embedded and cyber-physical systems
    1. Robotics
      1. Robotic autonomy
2. Computing methodologies
  1. Machine learning
    1. Learning settings
      1. Learning from demonstrations

Recommendations

The Effects of a Robot's Performance on Human Teachers for Learning from Demonstration Tasks
HRI '21: Proceedings of the 2021 ACM/IEEE International Conference on Human-Robot Interaction

Learning from Demonstration (LfD) algorithms seek to enable end-users to teach robots new skills through human demonstration of a task. Previous studies have analyzed how robot failure affects human trust, but not in the context of the human teaching ...
Skill Demonstration Transfer for Learning from Demonstration
HRI'15 Extended Abstracts: Proceedings of the Tenth Annual ACM/IEEE International Conference on Human-Robot Interaction Extended Abstracts

Learning from Demonstration is an effective method for interactively teaching skills to a robot learner. However, a skill learned via demonstrations is often learned within a particular environment and uses a specific set of objects, and thus may not be ...
A survey of robot learning from demonstration

We present a comprehensive survey of robot Learning from Demonstration (LfD), a technique that develops policies from example state to action mappings. We introduce the LfD design choices in terms of demonstrator, problem space, policy derivation and ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

HRI '21 Companion: Companion of the 2021 ACM/IEEE International Conference on Human-Robot Interaction

March 2021

756 pages

ISBN:9781450382908

DOI:10.1145/3434074

General Chairs:
Cindy Bethel
Mississippi State University, USA
,
Ana Paiva
INESC-ID, IST, University of Lisbon, Portugal & Radcliffe Institute for Advanced Study, Harvard University, USA
,
Program Chairs:
Elizabeth Broadbent
University of Auckland, New Zealand
,
David Feil-Seifer
University of Nevada Reno, USA
,
Daniel Szafir
University of Colorado Boulder, USA

Copyright © 2021 Owner/Author.

Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored. For all other uses, contact the Owner/Author.

Sponsors

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 08 March 2021

Check for updates

Author Tags

Qualifiers

Abstract

Funding Sources

Natural Sciences and Engineering Research Council of Canada

Conference

HRI '21

Sponsor:

HRI '21: ACM/IEEE International Conference on Human-Robot Interaction

March 8 - 11, 2021

CO, Boulder, USA

Acceptance Rates

Overall Acceptance Rate 192 of 519 submissions, 37%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

2
Total Citations
View Citations
192
Total Downloads

Downloads (Last 12 months)24
Downloads (Last 6 weeks)1

Reflects downloads up to 17 Oct 2024

Other Metrics

View Author Metrics

Citations

Cited By

Abal-Fernández SCaramazana-Zarzosa CLoureiro-Casalderrey MMartínez SBalaguer CDíaz-de-María FGonzález-Díaz I(2023)Learning RL policies for anticipative assistive robots by simulating human-robot interactions in real scenarios using egocentric videos2023 IEEE International Conference on Robotics and Biomimetics (ROBIO)10.1109/ROBIO58561.2023.10354837(1-8)Online publication date: 4-Dec-2023
https://doi.org/10.1109/ROBIO58561.2023.10354837
Sakr MLi ZVan der Loos HKulic DCroft E(2022)Quantifying Demonstration Quality for Robot Learning and GeneralizationIEEE Robotics and Automation Letters10.1109/LRA.2022.31919507:4(9659-9666)Online publication date: Oct-2022
https://doi.org/10.1109/LRA.2022.3191950

View Options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents