abstract

Leveraging Human Inputs in Interactive Machine Learning for Human Robot Interaction

Authors:

Emmanuel Senft,

Séverin Lemaignan,

Paul E. Baxter,

Tony BelpaemeAuthors Info & Claims

HRI '17: Proceedings of the Companion of the 2017 ACM/IEEE International Conference on Human-Robot Interaction

Pages 281 - 282

https://doi.org/10.1145/3029798.3038385

Published: 06 March 2017 Publication History

Get Access

Abstract

A key challenge of HRI is allowing robots to be adaptable, especially as robots are expected to penetrate society at large and to interact in unexpected environments with non-technical users. One way of providing this adaptability is to use Interactive Machine Learning, i.e. having a human supervisor included in the learning process who can steer the action selection and the learning in the desired direction. We ran a study exploring how people use numeric rewards to evaluate a robot's behaviour and guide its learning. From the results we derive a number of challenges when designing learning robots: what kind of input should the human provide? How should the robot communicate its state or its intention? And how can the teaching process by made easier for human supervisors?

References

[1]

S. Amershi, M. Cakmak, W. B. Knox, and T. Kulesza. Power to the people: The role of humans in interactive machine learning. AI Magazine, 35(4):105--120, 2014.

Digital Library

Google Scholar

[2]

M. Cakmak and A. L. Thomaz. Designing robot learners that ask good questions. In HRI'12, pages 17--24, 2012.

Digital Library

Google Scholar

[3]

J. A. Fails and D. R. Olsen Jr. Interactive machine learning. In IUI'03, pages 39--45, 2003.

Digital Library

Google Scholar

[4]

W. B. Knox and P. Stone. Interactively shaping agents via human reinforcement: The tamer framework. In K-CAP'09, pages 9--16, 2009.

Digital Library

Google Scholar

[5]

E. Senft, P. Baxter, J. Kennedy, and T. Belpaeme. SPARC: Supervised progressively autonomous robot competencies. In ICSR'15, pages 603--612, 2015.

Crossref

Google Scholar

[6]

E. Senft, S. Lemaignan, P. E. Baxter, and T. Belpaeme. Sparc: an efficient way to combine reinforcement learning and supervised autonomy. In FILM Workshop at NIPS'16, 2016.

Google Scholar

[7]

R. S. Sutton and A. G. Barto. Reinforcement learning: An introduction, volume 1. MIT press Cambridge, 1998.

Digital Library

Google Scholar

[8]

A. L. Thomaz and C. Breazeal. Teachable robots: Understanding human teaching behavior to build more effective robot learners. Artificial Intelligence, 172(6):716--737, 2008.

Digital Library

Google Scholar

Cited By

View all

Hindemith LBruns ONoller AHemion NSchneider SVollmer A(2023)Interactive Robot Task Learning: Human Teaching Proficiency With Different Feedback ApproachesIEEE Transactions on Cognitive and Developmental Systems10.1109/TCDS.2022.318627015:4(1938-1947)Online publication date: Dec-2023
https://doi.org/10.1109/TCDS.2022.3186270
Chhetri CGenaro Motti V(2022)User-Centric Privacy Controls for Smart HomesProceedings of the ACM on Human-Computer Interaction10.1145/35557696:CSCW2(1-36)Online publication date: 11-Nov-2022
https://dl.acm.org/doi/10.1145/3555769
Candello HPinhanez CMuller MWessel M(2022)Unveiling Practices of Customer Service Content Curators of Conversational AgentsProceedings of the ACM on Human-Computer Interaction10.1145/35557686:CSCW2(1-33)Online publication date: 11-Nov-2022
https://dl.acm.org/doi/10.1145/3555768
Show More Cited By

Index Terms

Leveraging Human Inputs in Interactive Machine Learning for Human Robot Interaction

Recommendations

Supervised autonomy for online learning in human-robot interaction

When a robot is learning it needs to explore its environment and how its environment responds on its actions. When the environment is large and there are a large number of possible actions the robot can take, this exploration phase can take ...
Learning interaction protocols by mimicking understanding and reproducing human interactive behavior

Four phases system for learning human interactive behavior is proposed.The system is based on constrained motif discovery for basic action discovery.Controller generation is achieved through a piecewise-linear control generator.Models learned from ...
Toward a framework for levels of robot autonomy in human-robot interaction

Autonomy is a critical construct related to human-robot interaction (HRI) and varies widely across robot platforms. Levels of robot autonomy (LORA), ranging from teleoperation to fully autonomous systems, influence the way in which humans and robots ...

Comments

Information & Contributors

Information

Published In

HRI '17: Proceedings of the Companion of the 2017 ACM/IEEE International Conference on Human-Robot Interaction

March 2017

462 pages

ISBN:9781450348850

DOI:10.1145/3029798

General Chairs:
Bilge Mutlu
University of Wisconsin-Madison, USA
,
Manfred Tscheligi
University of Salzburg, Austria
,
Program Chairs:
Astrid Weiss
Vienna University of Technology, Austria
,
James E. Young
University of Manitoba, Canada

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.

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 06 March 2017

Check for updates

Author Tags

Qualifiers

Abstract

Funding Sources

Seventh Framework Programme
H2020 Marie SkBodowska-Curie Actions

Conference

HRI '17

Sponsor:

SIGAI
SIGCHI
IEEE-RAS

HRI '17: ACM/IEEE International Conference on Human-Robot Interaction

March 6 - 9, 2017

Vienna, Austria

Acceptance Rates

HRI '17 Paper Acceptance Rate 51 of 211 submissions, 24%;

Overall Acceptance Rate 192 of 519 submissions, 37%

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

10
Total Citations
View Citations
411
Total Downloads

Downloads (Last 12 months)16
Downloads (Last 6 weeks)0

Reflects downloads up to 14 Sep 2024

Other Metrics

View Author Metrics

Citations

Cited By

View all

Hindemith LBruns ONoller AHemion NSchneider SVollmer A(2023)Interactive Robot Task Learning: Human Teaching Proficiency With Different Feedback ApproachesIEEE Transactions on Cognitive and Developmental Systems10.1109/TCDS.2022.318627015:4(1938-1947)Online publication date: Dec-2023
https://doi.org/10.1109/TCDS.2022.3186270
Chhetri CGenaro Motti V(2022)User-Centric Privacy Controls for Smart HomesProceedings of the ACM on Human-Computer Interaction10.1145/35557696:CSCW2(1-36)Online publication date: 11-Nov-2022
https://dl.acm.org/doi/10.1145/3555769
Candello HPinhanez CMuller MWessel M(2022)Unveiling Practices of Customer Service Content Curators of Conversational AgentsProceedings of the ACM on Human-Computer Interaction10.1145/35557686:CSCW2(1-33)Online publication date: 11-Nov-2022
https://dl.acm.org/doi/10.1145/3555768
Wyche S(2022)Reimagining the Mobile Phone: Investigating Speculative Approaches to Design in Human-Computer Interaction for Development (HCI4D)Proceedings of the ACM on Human-Computer Interaction10.1145/35556486:CSCW2(1-27)Online publication date: 11-Nov-2022
https://dl.acm.org/doi/10.1145/3555648
Rothschild AMeng ADiSalvo CJohnson BShapiro BDiSalvo B(2022)Interrogating Data Work as a Community of PracticeProceedings of the ACM on Human-Computer Interaction10.1145/35551986:CSCW2(1-28)Online publication date: 11-Nov-2022
https://dl.acm.org/doi/10.1145/3555198
Aubin Le Quéré MChiang TLevy KNaaman M(2022)Information Needs of Essential Workers During the COVID-19 PandemicProceedings of the ACM on Human-Computer Interaction10.1145/35551976:CSCW2(1-19)Online publication date: 11-Nov-2022
https://dl.acm.org/doi/10.1145/3555197
Frluckaj HDabbish LWidder DQiu HHerbsleb J(2022)Gender and Participation in Open Source Software DevelopmentProceedings of the ACM on Human-Computer Interaction10.1145/35551906:CSCW2(1-31)Online publication date: 11-Nov-2022
https://dl.acm.org/doi/10.1145/3555190
Singh KKapoor DSohi B(2021)All about human-robot interactionCognitive Computing for Human-Robot Interaction10.1016/B978-0-323-85769-7.00010-0(199-229)Online publication date: 2021
https://doi.org/10.1016/B978-0-323-85769-7.00010-0
Vollmer AHemion N(2018)A User Study on Robot Skill Learning Without a Cost Function: Optimization of Dynamic Movement Primitives via Naive User FeedbackFrontiers in Robotics and AI10.3389/frobt.2018.000775Online publication date: 2-Jul-2018
https://doi.org/10.3389/frobt.2018.00077
Sun XChen HShi JGuo WLi J(2018)From HMI to HRI: Human-Vehicle Interaction Design for Smart CockpitHuman-Computer Interaction. Interaction in Context10.1007/978-3-319-91244-8_35(440-454)Online publication date: 15-Jul-2018
https://dl.acm.org/doi/10.1007/978-3-319-91244-8_35

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.

Cited By

Index Terms

Recommendations

Supervised autonomy for online learning in human-robot interaction

Learning interaction protocols by mimicking understanding and reproducing human interactive behavior

Toward a framework for levels of robot autonomy in human-robot interaction