A Framework for Transferring Surface Finishing Skills to New Surface Geometries

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-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.
Original languageEnglish
Title of host publication2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
PublisherIEEE
Publication date26. Dec 2022
Pages7650-7655
ISBN (Print)978-1-6654-7928-8
ISBN (Electronic)978-1-6654-7927-1
DOIs
Publication statusPublished - 26. Dec 2022
Event2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) - Kyoto, Japan
Duration: 23. Oct 202227. Oct 2022

Conference

Conference2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Country/TerritoryJapan
CityKyoto
Period23/10/202227/10/2022
SeriesI E E E International Conference on Intelligent Robots and Systems. Proceedings
ISSN2153-0858

Fingerprint

Dive into the research topics of 'A Framework for Transferring Surface Finishing Skills to New Surface Geometries'. Together they form a unique fingerprint.

Cite this