kth.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Transformers for snap-fit detection: Deep learning for teaching robots to click components into other components
KTH, School of Electrical Engineering and Computer Science (EECS).
2024 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesisAlternative title
Transformers för snap-fit detection : Deep learning för att lära robotar klicka i komponenter in i andra komponenter (Swedish)
Abstract [en]

If living standards are to continue to improve then more of our manufacturing has to be automated. A difficult problem to solve for automation has been joining two plastic components by pushing one into another until they click into place. This is due to variations in components and and because of this, the task is done manually today. With the resurgence of artificial intelligence a lot of previously difficult to automate tasks have become viable for automation. While some work have been done in the field a lot of work remains in regards to generalization. This master thesis aims to contribute to the field of artificial intelligence by applying a transformer model based on a vision transformer as well as to recreate the results of another paper by using a convolutional neural network on the same problem. The transformer based model is tested in two variants, one more closely resembling the vision transformer and one simplified by removing the trainable the class token from the input. The experiments achieved a test time accuracy of 100% for the convolutional neural network based model as well as both variants of the transformer model. A detailed comparison between approaches revealed that the transformer based model more reliably achieved the 100% test time accuracy, with the simplified variant being even more consistent. The experiments also revealed that performance would vary depending on the percentage of data reserved for training with more training data not being beneficial for test time accuracy past a certain point.

Abstract [sv]

Om levnadsstandarden ska kunna fortsätta att förbättras måste mer av vår tillverkningmåste automatiseras. Ett svårt problem att lösa för automatisering har varit attatt sammanfoga två plastkomponenter genom att trycka in den ena i den andra tills de klickarpå plats. Detta beror på variationer i komponenterna och på grund av detta,görs uppgiften manuellt idag. I och med den artificiella intelligensens återkomsthar många uppgifter som tidigare var svåra att automatisera blivit möjliga att automatisera.Även om en del arbete har utförts inom området återstår mycket arbete när det gällernär det gäller generalisering. Denna masteruppsats syftar till att bidra till området artificiellintelligens genom att tillämpa en Transformer baserad på en Visiontransformersamt att återskapa resultaten från en annan uppsats genom att använda ett faltningneuralt nätverk på samma problem. Den transformatorbaserade modellen testasi två varianter, en som är mer lik Visiontransformern och en som ärförenklad genom att ta bort den utbildbara klassmarkören från indata.Experimenten uppnådde en testtidsnoggrannhet på 100% för den faltningssneuralanätverksbaserade modellen samt båda varianterna av Transformermodellen. endetaljerad jämförelse mellan tillvägagångssätten visade att den Transformerbaserademodellen på ett mer tillförlitligt sätt uppnådde 100

Place, publisher, year, edition, pages
2024. , p. 46
Series
TRITA-EECS-EX ; 2024:1006
Keywords [en]
Snap-fit, Snap assembly, Snap in, Peg-in-hole, Mating, Time-delayed neural network (TDNN), Long Short-Term Memory (LSTM), Transformer
Keywords [sv]
Canvas Lärplattform, Dockerbehållare, Prestandajustering
National Category
Computer and Information Sciences
Identifiers
URN: urn:nbn:se:kth:diva-361660OAI: oai:DiVA.org:kth-361660DiVA, id: diva2:1947171
Supervisors
Examiners
Available from: 2025-03-27 Created: 2025-03-25 Last updated: 2025-03-27Bibliographically approved

Open Access in DiVA

fulltext(1654 kB)41 downloads
File information
File name FULLTEXT02.pdfFile size 1654 kBChecksum SHA-512
290c204a298436568785acc8ff095c62070e54b5e2501c6e4227eecc07baa181725e8bf997512687101c1d74e00a426c79cd022505b7ad2158145b9f40fc6587
Type fulltextMimetype application/pdf

By organisation
School of Electrical Engineering and Computer Science (EECS)
Computer and Information Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 42 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 359 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf