Supervised and unsupervised learning in vision-guided robotic bin picking applications for mixed-model assembly

Abstract

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.