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
Automation in reuse sorting for a resource-efficient circular fashion
University West, Department of Engineering Science.
2022 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

Robots have played an essential part in the automation of repetitive and time-consuming operations, over the last few decades. Their applications are broad and diversified; nonetheless, it is limited in the automation of garment sorting. In fact, nowadays the most common sorting methods are manual or require at least human intervention to assist the process. Thus, designing a complete process of manipulating garments for sorting, upcycling, or reusing purposes, without human intervention, is becoming an indispensable and challenging task to meet economical and environmental requirements. The main goal of this thesis is to automate the sorting process of garments, starting by picking them from a pile to totally unfolding them, for further recognition. This project covers investigations on bin picking methods and technologies for undeformable and deformable objects, to apply them afterwards to garments. The project focuses also on selecting a solution to unfold the picked garment and to test it on pants and long sleeve shirts. Overall, an adequate setup has been implemented, featuring a 3D sensor, an industrial robot and suitable grippers, for both the bin picking and the unfolding procedure. First, to satisfy the extraction of a single garment from a pile, it has been deducted that its highest point represents an adequate grasp point. Second, once the garment picked, it is placed on a fixed gripper and unfolded by grasping it from it lowest point. The coordinates of these points are determined by a 3D camera and sent to a robot controller. At the outcome of the tests and experiments, 93% of the bin picking trials have been successful, resulting on the extraction of a single garment from a pile. Plus, the grasping of the hanging garment from it lowest point for unfolding, presented a success rate of 73%. After conducting these tests to evaluate the selected solutions and approaches, it was deemed that picking clothes for the highest point of the pile is a valid option; as well as grasping the picked garment from its lowest point to unfold it, as long as it is limited to certain types of clothing.

Place, publisher, year, edition, pages
2022. , p. 32
Keywords [en]
Word1, Word2, Word3, Word4, Word5
National Category
Robotics and automation
Identifiers
URN: urn:nbn:se:hv:diva-18695Local ID: EXC915OAI: oai:DiVA.org:hv-18695DiVA, id: diva2:1682627
Subject / course
Robotics
Educational program
Master i robotik och automation
Supervisors
Examiners
Available from: 2022-08-24 Created: 2022-07-11 Last updated: 2025-09-30Bibliographically approved

Open Access in DiVA

No full text in DiVA

By organisation
Department of Engineering Science
Robotics and automation

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 239 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