Supervised and unsupervised learning in vision-guided robotic bin picking applications for mixed-model assembly
Paper i proceeding, 2021

Mixed-model assembly usually involves numerous component variants that require effective materials supply. Here, picking activities are often performed manually, but the prospect of robotics for bin picking has potential to improve quality while reducing man-hour consumption. Robots can make use of vision systems to learn how to perform their tasks. This paper aims to understand the differences in two learning approaches, supervised learning, and unsupervised learning. An experiment containing engineering preparation time (EPT) and recognition quality (RQ) is performed. The findings show an improved RQ but longer EPT with a supervised compared to an unsupervised approach.


Kit preparation

Materials Handling

Order picking

Bin picking


Patrik Fager

Chalmers, Teknikens ekonomi och organisation, Supply and Operations Management

Robin Hanson

Chalmers, Teknikens ekonomi och organisation, Supply and Operations Management

Åsa Fasth Berglund

Maskinteknik, mekatronik och automatisering, teknisk design samt sjöfart och marin teknik

Sven Ekered

Chalmers, Industri- och materialvetenskap, Produktionssystem

Procedia CIRP

22128271 (ISSN)

Vol. 104 1304-1309

54th CIRP Conference on Manufacturing Ssystems, CMS 2021
Patras, Greece,



Robotteknik och automation

Datavetenskap (datalogi)



Mer information

Senast uppdaterat