Advances in machine vision for flexible feeding of assembly parts

Publikation: Bidrag til tidsskriftKonferenceartikelForskningpeer review

Resumé

Human-robot collaboration envisions production teams of human workers and robots sharing workload to achieve a common goal. When used for assembly operations, robots and humans team-up to integrate parts and components to structure a final product. These parts need to be presented to the robot in a known orientation. This process of presenting parts to the robot for assembly tasks is referred to as parts feeding which needs to be adaptable to dynamics of part’s design, shape, location, and orientation. The traditional automation methods for parts feeding are part-specific mechanical devices e.g. vibratory bowl feeders which are inflexible towards part variations. This is a hindrance in getting maximum advantage of the flexibility potential of human-robot collaboration. This paper explores the development of machine-vision to form flexible feeding systems for human-robot assembly cells. A specification model is presented to develop a vision-guided flexible feeding system. Various vision-based feeding techniques are presented and validated through an industrial case study. The results helped to compare the efficiency of each feeding technique.
OriginalsprogEngelsk
TidsskriftProcedia Manufacturing
Antal sider9
ISSN2351-9789
StatusAccepteret/In press - jun. 2019
Begivenhed29th International Conference for Flexible Automation & Intelligent Manufacturing: Beyond Industry 4.0: Industrial Advances, Engineering Education and Intelligent Manufacturing - Limerick, Irland
Varighed: 23. jun. 201927. jun. 2019

Konference

Konference29th International Conference for Flexible Automation & Intelligent Manufacturing
LandIrland
ByLimerick
Periode23/06/201927/06/2019

Fingeraftryk

Computer vision
Robots
Automation
Specifications

Citer dette

@inproceedings{36a728b1b8c944fb8ad8e53e6bdf5d0a,
title = "Advances in machine vision for flexible feeding of assembly parts",
abstract = "Human-robot collaboration envisions production teams of human workers and robots sharing workload to achieve a common goal. When used for assembly operations, robots and humans team-up to integrate parts and components to structure a final product. These parts need to be presented to the robot in a known orientation. This process of presenting parts to the robot for assembly tasks is referred to as parts feeding which needs to be adaptable to dynamics of part’s design, shape, location, and orientation. The traditional automation methods for parts feeding are part-specific mechanical devices e.g. vibratory bowl feeders which are inflexible towards part variations. This is a hindrance in getting maximum advantage of the flexibility potential of human-robot collaboration. This paper explores the development of machine-vision to form flexible feeding systems for human-robot assembly cells. A specification model is presented to develop a vision-guided flexible feeding system. Various vision-based feeding techniques are presented and validated through an industrial case study. The results helped to compare the efficiency of each feeding technique.",
author = "Malik, {Ali Ahmad} and Arne Bilberg",
year = "2019",
month = "6",
language = "English",
journal = "Procedia Manufacturing",
issn = "2351-9789",
publisher = "Elsevier",

}

Advances in machine vision for flexible feeding of assembly parts. / Malik, Ali Ahmad; Bilberg, Arne.

I: Procedia Manufacturing, 06.2019.

Publikation: Bidrag til tidsskriftKonferenceartikelForskningpeer review

TY - GEN

T1 - Advances in machine vision for flexible feeding of assembly parts

AU - Malik, Ali Ahmad

AU - Bilberg, Arne

PY - 2019/6

Y1 - 2019/6

N2 - Human-robot collaboration envisions production teams of human workers and robots sharing workload to achieve a common goal. When used for assembly operations, robots and humans team-up to integrate parts and components to structure a final product. These parts need to be presented to the robot in a known orientation. This process of presenting parts to the robot for assembly tasks is referred to as parts feeding which needs to be adaptable to dynamics of part’s design, shape, location, and orientation. The traditional automation methods for parts feeding are part-specific mechanical devices e.g. vibratory bowl feeders which are inflexible towards part variations. This is a hindrance in getting maximum advantage of the flexibility potential of human-robot collaboration. This paper explores the development of machine-vision to form flexible feeding systems for human-robot assembly cells. A specification model is presented to develop a vision-guided flexible feeding system. Various vision-based feeding techniques are presented and validated through an industrial case study. The results helped to compare the efficiency of each feeding technique.

AB - Human-robot collaboration envisions production teams of human workers and robots sharing workload to achieve a common goal. When used for assembly operations, robots and humans team-up to integrate parts and components to structure a final product. These parts need to be presented to the robot in a known orientation. This process of presenting parts to the robot for assembly tasks is referred to as parts feeding which needs to be adaptable to dynamics of part’s design, shape, location, and orientation. The traditional automation methods for parts feeding are part-specific mechanical devices e.g. vibratory bowl feeders which are inflexible towards part variations. This is a hindrance in getting maximum advantage of the flexibility potential of human-robot collaboration. This paper explores the development of machine-vision to form flexible feeding systems for human-robot assembly cells. A specification model is presented to develop a vision-guided flexible feeding system. Various vision-based feeding techniques are presented and validated through an industrial case study. The results helped to compare the efficiency of each feeding technique.

M3 - Conference article

JO - Procedia Manufacturing

JF - Procedia Manufacturing

SN - 2351-9789

ER -