Vision-assisted programming of collaborative robotic welding paths from operator-defined trajectories
Technologia i Automatyzacja Montażu · 2026 · 132 (2) · 37-48
DOI: 10.7862/tiam.2026.2.4 ↗Kurz gefasst
Fachartikel in der Zeitschrift Technologia i Automatyzacja Montażu, 2026. Verfasst von Andrzej Chmielowiec und 2 weiteren Autor:innen.
Abstract (Originalsprache)
Manual programming of robotic welding paths remains a limiting factor in flexible and small-batch production, where workpiece geometries and repair trajectories may vary between tasks. Teach-pendant programming in collaborative robotic welding stations is time-consuming and operator-dependent, while CAD-based offline programming, although common in conventional industrial robotics, is not always available or suitable for variable geometries, or uncertain repair operations. This paper presents a vision-assisted method for digitalising operator-defined welding paths and reconstructing them in the robot task space. The operator manually indicates the desired trajectory on the workpiece surface, which is then acquired from multiple camera viewpoints. A U-Net neural network is used to segment the path, while AprilTag fiducial markers support spatial referencing, projective reconstruction and multi-view triangulation. Experimental validation showed an average three-dimensional path reconstruction error of 0.98 mm. The proposed workflow provides a practical step towards reducing manual programming effort in robotic welding applications requiring operator-defined paths.
Zitieren
APA
Chmielowiec, A., Lichwiarz, K., & Mattera, G. (2026). Vision-assisted programming of collaborative robotic welding paths from operator-defined trajectories. Technologia i Automatyzacja Montażu, 132(2), 37-48. https://doi.org/10.7862/tiam.2026.2.4
Vancouver
Chmielowiec A, Lichwiarz K, Mattera G. Vision-assisted programming of collaborative robotic welding paths from operator-defined trajectories. Technologia i Automatyzacja Montażu. 2026;132(2):37-48. doi:10.7862/tiam.2026.2.4
BibTeX
@article{Chmielowiec2026,
author = {Chmielowiec, Andrzej and Lichwiarz, Kacper and Mattera, Giulio},
title = {Vision-assisted programming of collaborative robotic welding paths from operator-defined trajectories},
journal = {Technologia i Automatyzacja Montażu},
year = {2026},
volume = {132},
number = {2},
pages = {37--48},
doi = {10.7862/tiam.2026.2.4}
}
EUVIMED