Localised and Learnt Applications of Machine Learning for Robotic Incremental Sheet Forming

Paul Nicholas; Mateusz Zwierzycki; Mette Ramsgaard Thomsen

doi:10.1007/978-981-10-6611-5_32

Localised and Learnt Applications of Machine Learning for Robotic Incremental Sheet Forming

Paul Nicholas, Mateusz Zwierzycki, Mette Ramsgaard Thomsen

Publications: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

495 Downloads (Pure)

Abstract

While fabrication is becoming a well-established field for architectural robotics, new possibilities for modelling and control situate feedback, modelling methods and adaptation as key concerns. In this paper we detail two methods for implementing adaptation, in the context of Robotic Incremental Sheet Forming (ISF) and exemplified in the fabrication of a bridge structure. The methods we describe compensate for springback and improve forming tolerance by using localised in process distance sensing to adapt tool-paths, and by using pre-process supervised machine learning to predict stringback and generate corrected fabrication models.

Original language	English
Title of host publication	Humanizing Digital Reality : Design Modelling Symposium Paris 2017
Number of pages	10
Publisher	Springer
Publication date	2017
Pages	373-382
ISBN (Print)	978-981-10-6610-8
ISBN (Electronic)	978-981-10-6611-5
DOIs	https://doi.org/10.1007/978-981-10-6611-5_32
Publication status	Published - 2017

Keywords

Machine learning
incremental sheet forming
Robotic fabrication
Digital architecture

Artistic research

No

Access to Document

10.1007/978-981-10-6611-5_32

2017_Nicholas_LocalisedAndLearntFinal published version, 579 KBLicence: Unspecified

Complex Modelling
Ramsgaard Thomsen, M., Tamke, M., Ayres, P., Nicholas, P., Stasiuk, D., Holden Deleuran, A., Pauly, M. & Gengnagel, C.
01/09/2013 → 31/08/2017
Project: Research

Cite this

@inproceedings{1e2631aa10f44c919093746971341f43,

title = "Localised and Learnt Applications of Machine Learning for Robotic Incremental Sheet Forming",

abstract = "While fabrication is becoming a well-established field for architectural robotics, new possibilities for modelling and control situate feedback, modelling methods and adaptation as key concerns. In this paper we detail two methods for implementing adaptation, in the context of Robotic Incremental Sheet Forming (ISF) and exemplified in the fabrication of a bridge structure. The methods we describe compensate for springback and improve forming tolerance by using localised in process distance sensing to adapt tool-paths, and by using pre-process supervised machine learning to predict stringback and generate corrected fabrication models.",

keywords = "Machine learning, incremental sheet forming, Robotic fabrication, Digital architecture",

author = "Paul Nicholas and Mateusz Zwierzycki and {Ramsgaard Thomsen}, Mette",

year = "2017",

doi = "10.1007/978-981-10-6611-5_32",

language = "English",

isbn = "978-981-10-6610-8",

pages = "373--382",

booktitle = "Humanizing Digital Reality",

publisher = "Springer",

}

TY - GEN

T1 - Localised and Learnt Applications of Machine Learning for Robotic Incremental Sheet Forming

AU - Nicholas, Paul

AU - Zwierzycki, Mateusz

AU - Ramsgaard Thomsen, Mette

PY - 2017

Y1 - 2017

N2 - While fabrication is becoming a well-established field for architectural robotics, new possibilities for modelling and control situate feedback, modelling methods and adaptation as key concerns. In this paper we detail two methods for implementing adaptation, in the context of Robotic Incremental Sheet Forming (ISF) and exemplified in the fabrication of a bridge structure. The methods we describe compensate for springback and improve forming tolerance by using localised in process distance sensing to adapt tool-paths, and by using pre-process supervised machine learning to predict stringback and generate corrected fabrication models.

AB - While fabrication is becoming a well-established field for architectural robotics, new possibilities for modelling and control situate feedback, modelling methods and adaptation as key concerns. In this paper we detail two methods for implementing adaptation, in the context of Robotic Incremental Sheet Forming (ISF) and exemplified in the fabrication of a bridge structure. The methods we describe compensate for springback and improve forming tolerance by using localised in process distance sensing to adapt tool-paths, and by using pre-process supervised machine learning to predict stringback and generate corrected fabrication models.

KW - Machine learning

KW - incremental sheet forming

KW - Robotic fabrication

KW - Digital architecture

U2 - 10.1007/978-981-10-6611-5_32

DO - 10.1007/978-981-10-6611-5_32

M3 - Article in proceedings

SN - 978-981-10-6610-8

SP - 373

EP - 382

BT - Humanizing Digital Reality

PB - Springer

ER -

Localised and Learnt Applications of Machine Learning for Robotic Incremental Sheet Forming

Abstract

Keywords

Artistic research

Access to Document

Projects

Complex Modelling

Cite this