Automated Robot Path Planning for Camera-Based Magnetic Particle Inspection
e-Journal of Nondestructive Testing · 2026-07 · 31 (7)
DOI: 10.58286/33198 ↗Kurz gefasst
Fachartikel in der Zeitschrift e-Journal of Nondestructive Testing, 2026-07. Verfasst von Benedict Gürtl.
Abstract (Originalsprache)
This extended abstract presents a modular path-planning approach for robotic Magnetic Particle Inspection (MPI). The objective is to automatically compute robot trajectories that position and orient the workpiece in front of an MPI camera so that all relevant surfaces become visible for imaging and further analysis. The method transforms geometric part data and parametric process models into collision-free trajectories that operate within industrial cycle-time limits. The geometric core of the planner builds on globally smooth direction fields and stripe-based surface parameterization methods to generate consistent viewpoint distributions on complex shapes. These fields provide structured guidance for selecting camera poses while respecting accessibility and occlusion constraints. For refining viewpoint selection and ensuring full coverage, graph-cut-based energy minimization principles are incorporated to optimize region visibility and reduce redundant motion. The modular design decouples geometric processing, trajectory generation, and process-model evaluation, enabling flexible integration of alternative inspection methods and different workcells. Experiments on industrial components show that the planner achieves complete coverage with minimal motion overhead, significantly reducing manual robot programming and supporting autonomous per-part reconfiguration.
Zitieren
APA
Gürtl, B. (2026). Automated Robot Path Planning for Camera-Based Magnetic Particle Inspection. e-Journal of Nondestructive Testing, 31(7). https://doi.org/10.58286/33198
Vancouver
Gürtl B. Automated Robot Path Planning for Camera-Based Magnetic Particle Inspection. e-Journal of Nondestructive Testing. 2026;31(7). doi:10.58286/33198
BibTeX
@article{Grtl2026,
author = {Gürtl, Benedict},
title = {Automated Robot Path Planning for Camera-Based Magnetic Particle Inspection},
journal = {e-Journal of Nondestructive Testing},
year = {2026},
volume = {31},
number = {7},
doi = {10.58286/33198}
}
EUVIMED