Transferring Human Manipulation Knowledge to Robots with Inverse Reinforcement Learning

Emil Blixt Hansen; Rasmus Eckholdt Andersen; Steffen Madsen; Simon Bøgh

doi:10.1109/SII46433.2020.9025873

Transferring Human Manipulation Knowledge to Robots with Inverse Reinforcement Learning

Emil Blixt Hansen^*, Rasmus Eckholdt Andersen, Steffen Madsen, Simon Bøgh

^*Corresponding author for this work

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

5 Citations (Scopus)

146 Downloads (Pure)

Abstract

The need for adaptable models, e.g. reinforcement learning, have in recent years been more present within the industry. In this paper, we show how two versions of inverse reinforcement learning can be used to transfer task knowledge from a human expert to a robot in a dynamic environment. Moreover, a second method called Principal Component Analysis weighting is presented and discussed. The method shows potential in the use case but requires some more research.

Original language	English
Title of host publication	Proceedings of the 2020 IEEE/SICE International Symposium on System Integration, SII 2020
Number of pages	5
Publisher	IEEE
Publication date	2020
Pages	933-937
Article number	9025873
ISBN (Electronic)	9781728166674
DOIs	https://doi.org/10.1109/SII46433.2020.9025873
Publication status	Published - 2020
Event	IEEE/SICE International Symposium on System Integration - Hawaii Convention Center, Honolulu, United States Duration: 12 Jan 2020 → 15 Jan 2020

Conference

Conference	IEEE/SICE International Symposium on System Integration
Location	Hawaii Convention Center
Country/Territory	United States
City	Honolulu
Period	12/01/2020 → 15/01/2020

Series	Proceedings of the 2020 IEEE/SICE International Symposium on System Integration
ISSN	2474-2325

Keywords

Inverse Reinforcement Learning
Deep Reinforcement Learning
Robotics
Artificial Intelligence
Human-Robot interaction

Access to Document

10.1109/SII46433.2020.9025873

(2020) Transferring Human Manipulation Knowledge to Robots with Inverse Reinforcement Learning PREPRINTSubmitted manuscript, 886 KB

AUB Link

Search for the material in Aalborg University Library's search engine

Cite this

@inproceedings{873d0181828b4a74983728913de68d17,

title = "Transferring Human Manipulation Knowledge to Robots with Inverse Reinforcement Learning",

abstract = "The need for adaptable models, e.g. reinforcement learning, have in recent years been more present within the industry. In this paper, we show how two versions of inverse reinforcement learning can be used to transfer task knowledge from a human expert to a robot in a dynamic environment. Moreover, a second method called Principal Component Analysis weighting is presented and discussed. The method shows potential in the use case but requires some more research.",

keywords = "Inverse Reinforcement Learning, Deep Reinforcement Learning, Robotics, Artificial Intelligence, Human-Robot interaction",

author = "Hansen, {Emil Blixt} and Andersen, {Rasmus Eckholdt} and Steffen Madsen and Simon B{\o}gh",

year = "2020",

doi = "10.1109/SII46433.2020.9025873",

language = "English",

series = "Proceedings of the 2020 IEEE/SICE International Symposium on System Integration",

pages = "933--937",

booktitle = "Proceedings of the 2020 IEEE/SICE International Symposium on System Integration, SII 2020",

publisher = "IEEE",

address = "United States",

note = "IEEE/SICE International Symposium on System Integration ; Conference date: 12-01-2020 Through 15-01-2020",

}

Hansen, EB, Andersen, RE, Madsen, S & Bøgh, S 2020, Transferring Human Manipulation Knowledge to Robots with Inverse Reinforcement Learning. in Proceedings of the 2020 IEEE/SICE International Symposium on System Integration, SII 2020., 9025873, IEEE, Proceedings of the 2020 IEEE/SICE International Symposium on System Integration, pp. 933-937, IEEE/SICE International Symposium on System Integration, Honolulu, Hawaii, United States, 12/01/2020. https://doi.org/10.1109/SII46433.2020.9025873

Transferring Human Manipulation Knowledge to Robots with Inverse Reinforcement Learning. / Hansen, Emil Blixt; Andersen, Rasmus Eckholdt; Madsen, Steffen et al.
Proceedings of the 2020 IEEE/SICE International Symposium on System Integration, SII 2020. IEEE, 2020. p. 933-937 9025873 (Proceedings of the 2020 IEEE/SICE International Symposium on System Integration).

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

TY - GEN

T1 - Transferring Human Manipulation Knowledge to Robots with Inverse Reinforcement Learning

AU - Hansen, Emil Blixt

AU - Andersen, Rasmus Eckholdt

AU - Madsen, Steffen

AU - Bøgh, Simon

PY - 2020

Y1 - 2020

N2 - The need for adaptable models, e.g. reinforcement learning, have in recent years been more present within the industry. In this paper, we show how two versions of inverse reinforcement learning can be used to transfer task knowledge from a human expert to a robot in a dynamic environment. Moreover, a second method called Principal Component Analysis weighting is presented and discussed. The method shows potential in the use case but requires some more research.

AB - The need for adaptable models, e.g. reinforcement learning, have in recent years been more present within the industry. In this paper, we show how two versions of inverse reinforcement learning can be used to transfer task knowledge from a human expert to a robot in a dynamic environment. Moreover, a second method called Principal Component Analysis weighting is presented and discussed. The method shows potential in the use case but requires some more research.

KW - Inverse Reinforcement Learning

KW - Deep Reinforcement Learning

KW - Robotics

KW - Artificial Intelligence

KW - Human-Robot interaction

UR - http://www.scopus.com/inward/record.url?scp=85082629480&partnerID=8YFLogxK

U2 - 10.1109/SII46433.2020.9025873

DO - 10.1109/SII46433.2020.9025873

M3 - Article in proceeding

T3 - Proceedings of the 2020 IEEE/SICE International Symposium on System Integration

SP - 933

EP - 937

BT - Proceedings of the 2020 IEEE/SICE International Symposium on System Integration, SII 2020

PB - IEEE

T2 - IEEE/SICE International Symposium on System Integration

Y2 - 12 January 2020 through 15 January 2020

ER -

Hansen EB, Andersen RE, Madsen S, Bøgh S. Transferring Human Manipulation Knowledge to Robots with Inverse Reinforcement Learning. In Proceedings of the 2020 IEEE/SICE International Symposium on System Integration, SII 2020. IEEE. 2020. p. 933-937. 9025873. (Proceedings of the 2020 IEEE/SICE International Symposium on System Integration). doi: 10.1109/SII46433.2020.9025873

Transferring Human Manipulation Knowledge to Robots with Inverse Reinforcement Learning

Abstract

Conference

Keywords

Access to Document

AUB Link

Other files and links

Fingerprint

MADE Digital WP5.3 - Designing Self-Configuring and Self-Learning Smart Factories

Cite this

Transferring Human Manipulation Knowledge to Robots with Inverse Reinforcement Learning

Abstract

Conference

Keywords

Access to Document

AUB Link

Other files and links

Fingerprint

Projects

MADE Digital WP5.3 - Designing Self-Configuring and Self-Learning Smart Factories

Cite this