Please use this identifier to cite or link to this item:
doi:10.22028/D291-41139
Title: | Application of machine learning to object manipulation with bio-inspired microstructures |
Author(s): | Samri, Manar Thiemecke, Jonathan Hensel, René Arzt, Eduard |
Language: | English |
Title: | Journal of Materials Research and Technology |
Volume: | 27 |
Startpage: | 1406 |
Endpage: | 1416 |
Publisher/Platform: | Elsevier |
Year of Publication: | 2023 |
Free key words: | Bioinspired-adhesives Microstructures Pick and place Machine learning Classification |
DDC notations: | 620 Engineering and machine engineering |
Publikation type: | Journal Article |
Abstract: | Bioinspired fibrillar adhesives have been proposed for novel gripping systems with enhanced scalability and resource efficiency. Here, we propose an in-situ optical monitoring system of the contact signatures, coupled with image processing and machine learning. Visual features were extracted from the contact signature images recorded at maximum compressive preload and after lifting a glass object. The algorithm was trained to cope with several degrees of misalignment and with unbalanced weight distributions by off-center gripping. The system allowed an assessment of the picking process for objects of various mass (200, 300, and 400 g). Several classifiers showed a high accuracy of about 90 % for successful prediction of attachment, depending on the mass of the object. The results promise improved reliability of handling objects, even in difficult situations. |
DOI of the first publication: | 10.1016/j.jmrt.2023.09.311 |
URL of the first publication: | https://www.sciencedirect.com/science/article/pii/S2238785423024365 |
Link to this record: | urn:nbn:de:bsz:291--ds-411395 hdl:20.500.11880/37204 http://dx.doi.org/10.22028/D291-41139 |
ISSN: | 2238-7854 |
Date of registration: | 30-Jan-2024 |
Faculty: | NT - Naturwissenschaftlich- Technische Fakultät |
Department: | NT - Materialwissenschaft und Werkstofftechnik |
Professorship: | NT - Prof. Dr. Eduard Arzt |
Collections: | SciDok - Der Wissenschaftsserver der Universität des Saarlandes |
Files for this record:
File | Description | Size | Format | |
---|---|---|---|---|
1-s2.0-S2238785423024365-main.pdf | 3,03 MB | Adobe PDF | View/Open |
This item is licensed under a Creative Commons License