Workpiece Pose Classification Framework for Flexible Part Feeding Systems Using Machine Learning and Synthetic Datasets

authored by: Torge Kolditz, Pitt Müller, Annika Raatz
Abstract: In previous work, a concept for a novel flexible part feeding system based on aerodynamic feeding was presented. In contrast to conventional part feeding systems, such as vibratory bowl feeders, aerodynamic part feeding systems use controlled pressurized air jets to reorient the workpieces. The proposed concept aims to increase flexibility and eliminate retooling times to meet the challenges of modern automated production with regard to increasing uncertainties, shorter product life cycles and higher cost pressure. Regarding these objectives, the determination of the workpiece poses in the feeding system requires flexible image processing, which will be enabled using machine learning and synthetic datasets. This work presents a framework which enables the classification of workpiece poses using a standard industrial camera and convolutional neural networks (CNN). The training of CNNs usually requires large datasets. However, in order to eliminate the need to create and label datasets of real images, which would cause machine downtimes and increase the retooling effort, the CNNs will be trained with synthetic datasets. Based on the CAD-data of the workpieces, artificial images of each pose are rendered using the open source engine Blender. Several CNN architectures are selected, trained with the artificial datasets and evaluated using real images of the workpieces. The results show that high classification accuracies of over 99 % can be achieved. It is concluded that the presented approach enables the classification of workpiece poses with high accuracy, while eliminating the need for the cumbersome creation of real image datasets. The approach is not limited to the use in the aerodynamic part feeding system but can be transferred to other applications in which the orientation of a workpiece has to be classified.
Organisation(s): Institute for Assembly Technology and Robotics
Type: Conference article
Journal: Procedia CIRP
Volume: 127
Pages: 92-97
No. of pages: 6
ISSN: 2212-8271
Publication date: 2024
Publication status: Published
Peer reviewed: Yes
ASJC Scopus subject areas: Control and Systems Engineering, Industrial and Manufacturing Engineering
Electronic version(s): https://doi.org/10.1016/j.procir.2024.07.017 (Access: Open)

BibTeX

@article{9fc8e3423b2547b894f4d80583640292,
title = "Workpiece Pose Classification Framework for Flexible Part Feeding Systems Using Machine Learning and Synthetic Datasets",
abstract = "In previous work, a concept for a novel flexible part feeding system based on aerodynamic feeding was presented. In contrast to conventional part feeding systems, such as vibratory bowl feeders, aerodynamic part feeding systems use controlled pressurized air jets to reorient the workpieces. The proposed concept aims to increase flexibility and eliminate retooling times to meet the challenges of modern automated production with regard to increasing uncertainties, shorter product life cycles and higher cost pressure. Regarding these objectives, the determination of the workpiece poses in the feeding system requires flexible image processing, which will be enabled using machine learning and synthetic datasets. This work presents a framework which enables the classification of workpiece poses using a standard industrial camera and convolutional neural networks (CNN). The training of CNNs usually requires large datasets. However, in order to eliminate the need to create and label datasets of real images, which would cause machine downtimes and increase the retooling effort, the CNNs will be trained with synthetic datasets. Based on the CAD-data of the workpieces, artificial images of each pose are rendered using the open source engine Blender. Several CNN architectures are selected, trained with the artificial datasets and evaluated using real images of the workpieces. The results show that high classification accuracies of over 99 % can be achieved. It is concluded that the presented approach enables the classification of workpiece poses with high accuracy, while eliminating the need for the cumbersome creation of real image datasets. The approach is not limited to the use in the aerodynamic part feeding system but can be transferred to other applications in which the orientation of a workpiece has to be classified.",
keywords = "separated by semicolons, Type your keywords here",
author = "Torge Kolditz and Pitt M{\"u}ller and Annika Raatz",
note = "Publisher Copyright: {\textcopyright} 2024 Elsevier B.V.. All rights reserved.; 10th CIRP Conference on Assembly Technology and Systems, CATS 2024 ; Conference date: 24-04-2024 Through 26-04-2024",
year = "2024",
doi = "10.1016/j.procir.2024.07.017",
language = "English",
volume = "127",
pages = "92--97",
journal = "Procedia CIRP",
issn = "2212-8271",
publisher = "Elsevier BV",
}