Feedback-based Fabric Strip Folding

Vladimir Petrik; Ville Kyrki

doi:10.1109/IROS40897.2019.8967657

Feedback-based Fabric Strip Folding

Vladimir Petrik, Ville Kyrki

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussa › Conference contribution › Scientific › vertaisarvioitu

8 Sitaatiot (Scopus)

121 Lataukset (Pure)

Abstrakti

Accurate manipulation of a deformable body such as a piece of fabric is difficult because of its many degrees of freedom and unobservable properties affecting its dynamics. To alleviate these challenges, we propose the application of feedback-based control to robotic fabric strip folding. The feedback is computed from the low dimensional state extracted from a camera image. We trained the controller using reinforcement learning in simulation which was calibrated to cover the real fabric strip behaviors. The proposed feedback-based folding was experimentally compared to two state-of-the-art folding methods and our method outperformed both of them in terms of accuracy.

Alkuperäiskieli	Englanti
Otsikko	Proceedings of the 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2019
Kustantaja	IEEE
Sivut	773-778
Sivumäärä	6
ISBN (elektroninen)	9781728140049
DOI - pysyväislinkit	https://doi.org/10.1109/IROS40897.2019.8967657
Tila	Julkaistu - 1 marrask. 2019
OKM-julkaisutyyppi	A4 Artikkeli konferenssijulkaisussa
Tapahtuma	IEEE/RSJ International Conference on Intelligent Robots and Systems - The Venetian Macao, Macau, Kiina Kesto: 4 marrask. 2019 → 8 marrask. 2019 https://www.iros2019.org/

Julkaisusarja

Nimi	Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems
Kustantaja	IEEE
ISSN (painettu)	2153-0858
ISSN (elektroninen)	2153-0866

Conference

Conference	IEEE/RSJ International Conference on Intelligent Robots and Systems
Lyhennettä	IROS
Maa/Alue	Kiina
Kaupunki	Macau
Ajanjakso	04/11/2019 → 08/11/2019
www-osoite	https://www.iros2019.org/

Pääsy asiakirjaan

10.1109/IROS40897.2019.8967657

ELEC_Petrik_etal_Feedback-Based-Fabric-Strip_IROS2019_authoracceptedmanuscriptAccepted author manuscript, 771 KB

OpenUrl-saatavuus

Koko teksti

Muut tiedostot ja linkit

Link to publication in Scopus

-: AI hämähäkin seitti
Kyrki, V., Arndt, K., Petrik, V. & Blanco Mulero, D.
01/01/2018 → 31/12/2022
Projekti: Academy of Finland: Other research funding

Siteeraa tätä

@inproceedings{cd66620205364aaaa1ee9550318e9a1a,

title = "Feedback-based Fabric Strip Folding",

abstract = "Accurate manipulation of a deformable body such as a piece of fabric is difficult because of its many degrees of freedom and unobservable properties affecting its dynamics. To alleviate these challenges, we propose the application of feedback-based control to robotic fabric strip folding. The feedback is computed from the low dimensional state extracted from a camera image. We trained the controller using reinforcement learning in simulation which was calibrated to cover the real fabric strip behaviors. The proposed feedback-based folding was experimentally compared to two state-of-the-art folding methods and our method outperformed both of them in terms of accuracy.",

keywords = "Fabrics, Feedback, Learning systems, Manipulators",

author = "Vladimir Petrik and Ville Kyrki",

year = "2019",

month = nov,

day = "1",

doi = "10.1109/IROS40897.2019.8967657",

language = "English",

series = "Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems",

publisher = "IEEE",

pages = "773--778",

booktitle = "Proceedings of the 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2019",

address = "United States",

note = "IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS ; Conference date: 04-11-2019 Through 08-11-2019",

url = "https://www.iros2019.org/",

}

Petrik, V & Kyrki, V 2019, Feedback-based Fabric Strip Folding. julkaisussa Proceedings of the 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2019., 8967657, Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, Sivut 773-778, IEEE/RSJ International Conference on Intelligent Robots and Systems, Macau, Kiina, 04/11/2019. https://doi.org/10.1109/IROS40897.2019.8967657

Feedback-based Fabric Strip Folding. / Petrik, Vladimir; Kyrki, Ville.
Proceedings of the 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2019. IEEE, 2019. s. 773-778 8967657 (Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems).

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussa › Conference contribution › Scientific › vertaisarvioitu

TY - GEN

T1 - Feedback-based Fabric Strip Folding

AU - Petrik, Vladimir

AU - Kyrki, Ville

PY - 2019/11/1

Y1 - 2019/11/1

N2 - Accurate manipulation of a deformable body such as a piece of fabric is difficult because of its many degrees of freedom and unobservable properties affecting its dynamics. To alleviate these challenges, we propose the application of feedback-based control to robotic fabric strip folding. The feedback is computed from the low dimensional state extracted from a camera image. We trained the controller using reinforcement learning in simulation which was calibrated to cover the real fabric strip behaviors. The proposed feedback-based folding was experimentally compared to two state-of-the-art folding methods and our method outperformed both of them in terms of accuracy.

AB - Accurate manipulation of a deformable body such as a piece of fabric is difficult because of its many degrees of freedom and unobservable properties affecting its dynamics. To alleviate these challenges, we propose the application of feedback-based control to robotic fabric strip folding. The feedback is computed from the low dimensional state extracted from a camera image. We trained the controller using reinforcement learning in simulation which was calibrated to cover the real fabric strip behaviors. The proposed feedback-based folding was experimentally compared to two state-of-the-art folding methods and our method outperformed both of them in terms of accuracy.

KW - Fabrics

KW - Feedback

KW - Learning systems

KW - Manipulators

UR - http://www.scopus.com/inward/record.url?scp=85081160160&partnerID=8YFLogxK

U2 - 10.1109/IROS40897.2019.8967657

DO - 10.1109/IROS40897.2019.8967657

M3 - Conference contribution

AN - SCOPUS:85081160160

T3 - Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems

SP - 773

EP - 778

BT - Proceedings of the 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2019

PB - IEEE

T2 - IEEE/RSJ International Conference on Intelligent Robots and Systems

Y2 - 4 November 2019 through 8 November 2019

ER -

Feedback-based Fabric Strip Folding

Abstrakti

Julkaisusarja

Conference

Pääsy asiakirjaan

OpenUrl-saatavuus

Muut tiedostot ja linkit

Sormenjälki

Projektit

-: AI hämähäkin seitti

Siteeraa tätä