A Framework for Transferring Surface Finishing Skills to New Surface Geometries

Yitaek Kim; Christoffer Sloth; Aljaz Kramberger

doi:10.1109/iros47612.2022.9981163

A Framework for Transferring Surface Finishing Skills to New Surface Geometries

Yitaek Kim^*, Christoffer Sloth, Aljaz Kramberger

^*Kontaktforfatter

Publikation: Kapitel i bog/rapport/konference-proceeding › Konferencebidrag i proceedings › Forskning › peer review

Abstract

This paper presents a framework for transferring surface finishing skills to new surface geometries while preserving the surface finish quality. The main idea is to estimate the contact area between the workpiece and the tool by using 3D point cloud approach and replicate a given material removal rate and the accumulated material removal, as these quantities are the main parameters for quality. The grinding motion trajectory is generated by solving a constrained optimization problem that minimizes the maximal point-wise deviation between actual and desired material removal and simultaneously minimizes the average deviation between actual and desired material removal rate. The proposed approach is verified in simulation to show the difference between direct replication of force/motion and the proposed replication of material removal. Finally, experimental results confirm that the quality of a surface finishing task can be transferred to new surface geometries with the proposed method.

Originalsprog	Engelsk
Titel	2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Forlag	IEEE
Publikationsdato	26. dec. 2022
Sider	7650-7655
ISBN (Trykt)	978-1-6654-7928-8
ISBN (Elektronisk)	978-1-6654-7927-1
DOI	https://doi.org/10.1109/iros47612.2022.9981163
Status	Udgivet - 26. dec. 2022
Begivenhed	2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS): Late Breaking Results Poster - Kyoto, Japan Varighed: 23. okt. 2022 → 27. okt. 2022

Konference

Konference	2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Land/Område	Japan
By	Kyoto
Periode	23/10/2022 → 27/10/2022

Navn	Proceedings - IEEE International Conference on Intelligent Robots and Systems
ISSN	2153-0858

Dokumenter og links

10.1109/iros47612.2022.9981163

1 Ph.d.-afhandling

Fast Setup of Robotic Material Processing with Quality Guarantees using Set Invariance
Kim, Y., 23. apr. 2024, Syddansk Universitet. Det Tekniske Fakultet. 110 s.
Publikation: Afhandling › Ph.d.-afhandling

Citationsformater

@inproceedings{82802ad124c84e4db62d441f792f4389,

title = "A Framework for Transferring Surface Finishing Skills to New Surface Geometries",

abstract = "This paper presents a framework for transferring surface finishing skills to new surface geometries while preserving the surface finish quality. The main idea is to estimate the contact area between the workpiece and the tool by using 3D point cloud approach and replicate a given material removal rate and the accumulated material removal, as these quantities are the main parameters for quality. The grinding motion trajectory is generated by solving a constrained optimization problem that minimizes the maximal point-wise deviation between actual and desired material removal and simultaneously minimizes the average deviation between actual and desired material removal rate. The proposed approach is verified in simulation to show the difference between direct replication of force/motion and the proposed replication of material removal. Finally, experimental results confirm that the quality of a surface finishing task can be transferred to new surface geometries with the proposed method.",

author = "Yitaek Kim and Christoffer Sloth and Aljaz Kramberger",

year = "2022",

month = dec,

day = "26",

doi = "10.1109/iros47612.2022.9981163",

language = "English",

isbn = "978-1-6654-7928-8",

series = "Proceedings - IEEE International Conference on Intelligent Robots and Systems",

publisher = "IEEE",

pages = "7650--7655",

booktitle = "2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)",

address = "United States",

note = "2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) : Late Breaking Results Poster ; Conference date: 23-10-2022 Through 27-10-2022",

}

Kim, Y , Sloth, C & Kramberger, A 2022, A Framework for Transferring Surface Finishing Skills to New Surface Geometries. i 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, Proceedings - IEEE International Conference on Intelligent Robots and Systems, s. 7650-7655, 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Kyoto, Japan, 23/10/2022. https://doi.org/10.1109/iros47612.2022.9981163

A Framework for Transferring Surface Finishing Skills to New Surface Geometries. / Kim, Yitaek ; Sloth, Christoffer ; Kramberger, Aljaz.
2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2022. s. 7650-7655 (Proceedings - IEEE International Conference on Intelligent Robots and Systems).

Publikation: Kapitel i bog/rapport/konference-proceeding › Konferencebidrag i proceedings › Forskning › peer review

TY - GEN

T1 - A Framework for Transferring Surface Finishing Skills to New Surface Geometries

AU - Kim, Yitaek

AU - Sloth, Christoffer

AU - Kramberger, Aljaz

PY - 2022/12/26

Y1 - 2022/12/26

N2 - This paper presents a framework for transferring surface finishing skills to new surface geometries while preserving the surface finish quality. The main idea is to estimate the contact area between the workpiece and the tool by using 3D point cloud approach and replicate a given material removal rate and the accumulated material removal, as these quantities are the main parameters for quality. The grinding motion trajectory is generated by solving a constrained optimization problem that minimizes the maximal point-wise deviation between actual and desired material removal and simultaneously minimizes the average deviation between actual and desired material removal rate. The proposed approach is verified in simulation to show the difference between direct replication of force/motion and the proposed replication of material removal. Finally, experimental results confirm that the quality of a surface finishing task can be transferred to new surface geometries with the proposed method.

AB - This paper presents a framework for transferring surface finishing skills to new surface geometries while preserving the surface finish quality. The main idea is to estimate the contact area between the workpiece and the tool by using 3D point cloud approach and replicate a given material removal rate and the accumulated material removal, as these quantities are the main parameters for quality. The grinding motion trajectory is generated by solving a constrained optimization problem that minimizes the maximal point-wise deviation between actual and desired material removal and simultaneously minimizes the average deviation between actual and desired material removal rate. The proposed approach is verified in simulation to show the difference between direct replication of force/motion and the proposed replication of material removal. Finally, experimental results confirm that the quality of a surface finishing task can be transferred to new surface geometries with the proposed method.

U2 - 10.1109/iros47612.2022.9981163

DO - 10.1109/iros47612.2022.9981163

M3 - Article in proceedings

SN - 978-1-6654-7928-8

T3 - Proceedings - IEEE International Conference on Intelligent Robots and Systems

SP - 7650

EP - 7655

BT - 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

PB - IEEE

T2 - 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Y2 - 23 October 2022 through 27 October 2022

ER -

A Framework for Transferring Surface Finishing Skills to New Surface Geometries

Abstract

Konference

Dokumenter og links

Fingeraftryk

Relaterede publikationer

Fast Setup of Robotic Material Processing with Quality Guarantees using Set Invariance

Citationsformater