Details
| Original language | English |
|---|---|
| Title of host publication | ROBOVIS 2020 - Proceedings of the International Conference on Robotics, Computer Vision and Intelligent Systems |
| Editors | Peter Galambos, Kurosh Madani |
| Pages | 17-27 |
| Number of pages | 11 |
| ISBN (electronic) | 9789897584794 |
| Publication status | Published - 4 Nov 2020 |
| Externally published | Yes |
| Event | 2020 International Conference on Robotics, Computer Vision and Intelligent Systems, ROBOVIS 2020 - Virtual, Online Duration: 4 Nov 2020 → 6 Nov 2020 |
Publication series
| Name | ROBOVIS 2020 - Proceedings of the International Conference on Robotics, Computer Vision and Intelligent Systems |
|---|
Abstract
As the state-of-the-art deep learning models are taking the leap to generalize and leverage automation, they are becoming useful in real-world tasks such as disassembly of devices by robotic manipulation. We address the problem of analyzing the visual scenes on industrial-grade tasks, for example, automated robotic recycling of a computer hard drive with small components and little space for manipulation. We implement a supervised learning architecture combining deep neural networks and standard pointcloud processing for detecting and recognizing hard drives parts, screws, and gaps. We evaluate the architecture on a custom hard drive dataset and reach an accuracy higher than 75% in every component used in our pipeline. Additionally, we show that the pipeline can generalize on damaged hard drives. Our approach combining several specialized modules can provide a robust description of a device usable for manipulation by a robotic system. To our knowledge, we are the pioneers to offer a complete scheme to address the entire disassembly process of the chosen device. To facilitate the pursuit of this issue of global concern, we provide a taxonomy for the target device to be used in automated disassembly scenarios and publish our collected dataset and code.
Keywords
- Automation, E-waste, Object classification, Object detection, Recycling
ASJC Scopus subject areas
- Engineering(all)
- Control and Systems Engineering
- Computer Science(all)
- Artificial Intelligence
- Engineering(all)
- Electrical and Electronic Engineering
- Computer Science(all)
- Computer Vision and Pattern Recognition
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
ROBOVIS 2020 - Proceedings of the International Conference on Robotics, Computer Vision and Intelligent Systems. ed. / Peter Galambos; Kurosh Madani. 2020. p. 17-27 (ROBOVIS 2020 - Proceedings of the International Conference on Robotics, Computer Vision and Intelligent Systems).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - A Visual Intelligence Scheme for Hard Drive Disassembly in Automated Recycling Routines
AU - Yildiz, Erenus
AU - Brinker, Tobias
AU - Renaudo, Erwan
AU - Hollenstein, Jakob J.
AU - Haller-Seeber, Simon
AU - Piater, Justus
AU - Wörgötter, Florentin
N1 - Publisher Copyright: Copyright © 2020 by SCITEPRESS-Science and Technology Publications, Lda. All rights reserved.
PY - 2020/11/4
Y1 - 2020/11/4
N2 - As the state-of-the-art deep learning models are taking the leap to generalize and leverage automation, they are becoming useful in real-world tasks such as disassembly of devices by robotic manipulation. We address the problem of analyzing the visual scenes on industrial-grade tasks, for example, automated robotic recycling of a computer hard drive with small components and little space for manipulation. We implement a supervised learning architecture combining deep neural networks and standard pointcloud processing for detecting and recognizing hard drives parts, screws, and gaps. We evaluate the architecture on a custom hard drive dataset and reach an accuracy higher than 75% in every component used in our pipeline. Additionally, we show that the pipeline can generalize on damaged hard drives. Our approach combining several specialized modules can provide a robust description of a device usable for manipulation by a robotic system. To our knowledge, we are the pioneers to offer a complete scheme to address the entire disassembly process of the chosen device. To facilitate the pursuit of this issue of global concern, we provide a taxonomy for the target device to be used in automated disassembly scenarios and publish our collected dataset and code.
AB - As the state-of-the-art deep learning models are taking the leap to generalize and leverage automation, they are becoming useful in real-world tasks such as disassembly of devices by robotic manipulation. We address the problem of analyzing the visual scenes on industrial-grade tasks, for example, automated robotic recycling of a computer hard drive with small components and little space for manipulation. We implement a supervised learning architecture combining deep neural networks and standard pointcloud processing for detecting and recognizing hard drives parts, screws, and gaps. We evaluate the architecture on a custom hard drive dataset and reach an accuracy higher than 75% in every component used in our pipeline. Additionally, we show that the pipeline can generalize on damaged hard drives. Our approach combining several specialized modules can provide a robust description of a device usable for manipulation by a robotic system. To our knowledge, we are the pioneers to offer a complete scheme to address the entire disassembly process of the chosen device. To facilitate the pursuit of this issue of global concern, we provide a taxonomy for the target device to be used in automated disassembly scenarios and publish our collected dataset and code.
KW - Automation
KW - E-waste
KW - Object classification
KW - Object detection
KW - Recycling
UR - http://www.scopus.com/inward/record.url?scp=85108105703&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85108105703
T3 - ROBOVIS 2020 - Proceedings of the International Conference on Robotics, Computer Vision and Intelligent Systems
SP - 17
EP - 27
BT - ROBOVIS 2020 - Proceedings of the International Conference on Robotics, Computer Vision and Intelligent Systems
A2 - Galambos, Peter
A2 - Madani, Kurosh
T2 - 2020 International Conference on Robotics, Computer Vision and Intelligent Systems, ROBOVIS 2020
Y2 - 4 November 2020 through 6 November 2020
ER -