Purpose The purpose of this paper is to describe a robot vision system which put rings on hooks that are moving freely on a conveyor belt. The hook can show a significant swinging which can be well approximated by a pendulum movement. The problem is of large relevance for many industrial applications and the challenge is to compute a 3D pose that is sufficiently precise to allow for successful placements of the rings. Design/methodology/approach This requires a fast and precise tracking and a compensation for latencies connected to the processing of visual information as well as the actual robot action. Findings The authors achieve this through a precise pose estimation in a high‐resolution stereo setup, as well as a modeling of the hook movement as a combination of a translational and a pendulum movement. Originality/value The paper shows that under normal conditions close to 100 percent success can be achieved such that this technology now can be transferred into industrial systems.
No takes yet. Share an insight, caveat, or question.
Kjær‐Nielsen et al. (2011) studied this question.
Synapse has enriched 4 closely related papers on similar clinical questions. Consider them for comparative context: