Application of convolutional neural networks for visual control of intelligent robotic systems
Само за регистроване кориснике
2021
Аутори
Miljković, ZoranĐokić, Lazar
Petrović, Milica
Остала ауторства
Šibalija, TatjanaDavim, J. Paulo
Поглавље у монографији (Објављена верзија)
Метаподаци
Приказ свих података о документуАпстракт
Intelligent mobile robots are foreseen as one of the possible solutions to efficiently
performing transportation and manipulation tasks in intelligent manufacturing
systems (IMS) of Industry 4.0. In the last few decades, deep learning models have been
recognized as a promising technique to enable the intelligent behavior of mobile robots
for performing such tasks. For the particular problems of object detection and classification,
a class of deep learning models, namely Convolutional Neural Networks (CNN),
is the most widely used. This chapter presents an application of Region-based
CNN (R-CNN) for advanced object identification tasks by using transfer learning.
The proposed learning approach is further used for the improvement of Image-
Based Visual Servoing (IBVS) algorithm used to control an intelligent mobile robot.
The proposed algorithms are implemented in the MATLAB software package, and
both simulation and the experimental verification of the proposed concept are per...formed
on intelligent mobile robot, DOMINO (Deep learning Omnidirectional Mobile
robot with INtelligent cOntrol). Four different CNN models are trained for object detection
and classification, and the most suitable CNN model is ResNet-18, with the
best recorded mean Average Precision (mAP) of 77%. Achieved experimental results
show the applicability of CNN for accurate detection and classification of different
manufacturing entities and the IBVS algorithm for efficient mobile robot control
within IMS.
Кључне речи:
intelligent manufacturing systems / intelligent mobile robots / deep learning / convolutional neural networks / visual servoingИзвор:
Soft Computing in Smart Manufacturing - Solutions toward Industry 5.0, 2021, 83/3-Издавач:
- De Gruyter, © 2022 Walter de Gruyter GmbH, Berlin/Boston
Финансирање / пројекти:
Колекције
Институција/група
Mašinski fakultetTY - CHAP AU - Miljković, Zoran AU - Đokić, Lazar AU - Petrović, Milica PY - 2021 UR - https://machinery.mas.bg.ac.rs/handle/123456789/3961 AB - Intelligent mobile robots are foreseen as one of the possible solutions to efficiently performing transportation and manipulation tasks in intelligent manufacturing systems (IMS) of Industry 4.0. In the last few decades, deep learning models have been recognized as a promising technique to enable the intelligent behavior of mobile robots for performing such tasks. For the particular problems of object detection and classification, a class of deep learning models, namely Convolutional Neural Networks (CNN), is the most widely used. This chapter presents an application of Region-based CNN (R-CNN) for advanced object identification tasks by using transfer learning. The proposed learning approach is further used for the improvement of Image- Based Visual Servoing (IBVS) algorithm used to control an intelligent mobile robot. The proposed algorithms are implemented in the MATLAB software package, and both simulation and the experimental verification of the proposed concept are performed on intelligent mobile robot, DOMINO (Deep learning Omnidirectional Mobile robot with INtelligent cOntrol). Four different CNN models are trained for object detection and classification, and the most suitable CNN model is ResNet-18, with the best recorded mean Average Precision (mAP) of 77%. Achieved experimental results show the applicability of CNN for accurate detection and classification of different manufacturing entities and the IBVS algorithm for efficient mobile robot control within IMS. PB - De Gruyter, © 2022 Walter de Gruyter GmbH, Berlin/Boston T2 - Soft Computing in Smart Manufacturing - Solutions toward Industry 5.0 T1 - Application of convolutional neural networks for visual control of intelligent robotic systems SP - 83/3 DO - 10.1515/9783110693225-003 ER -
@inbook{ author = "Miljković, Zoran and Đokić, Lazar and Petrović, Milica", year = "2021", abstract = "Intelligent mobile robots are foreseen as one of the possible solutions to efficiently performing transportation and manipulation tasks in intelligent manufacturing systems (IMS) of Industry 4.0. In the last few decades, deep learning models have been recognized as a promising technique to enable the intelligent behavior of mobile robots for performing such tasks. For the particular problems of object detection and classification, a class of deep learning models, namely Convolutional Neural Networks (CNN), is the most widely used. This chapter presents an application of Region-based CNN (R-CNN) for advanced object identification tasks by using transfer learning. The proposed learning approach is further used for the improvement of Image- Based Visual Servoing (IBVS) algorithm used to control an intelligent mobile robot. The proposed algorithms are implemented in the MATLAB software package, and both simulation and the experimental verification of the proposed concept are performed on intelligent mobile robot, DOMINO (Deep learning Omnidirectional Mobile robot with INtelligent cOntrol). Four different CNN models are trained for object detection and classification, and the most suitable CNN model is ResNet-18, with the best recorded mean Average Precision (mAP) of 77%. Achieved experimental results show the applicability of CNN for accurate detection and classification of different manufacturing entities and the IBVS algorithm for efficient mobile robot control within IMS.", publisher = "De Gruyter, © 2022 Walter de Gruyter GmbH, Berlin/Boston", journal = "Soft Computing in Smart Manufacturing - Solutions toward Industry 5.0", booktitle = "Application of convolutional neural networks for visual control of intelligent robotic systems", pages = "83/3", doi = "10.1515/9783110693225-003" }
Miljković, Z., Đokić, L.,& Petrović, M.. (2021). Application of convolutional neural networks for visual control of intelligent robotic systems. in Soft Computing in Smart Manufacturing - Solutions toward Industry 5.0 De Gruyter, © 2022 Walter de Gruyter GmbH, Berlin/Boston., 83/3. https://doi.org/10.1515/9783110693225-003
Miljković Z, Đokić L, Petrović M. Application of convolutional neural networks for visual control of intelligent robotic systems. in Soft Computing in Smart Manufacturing - Solutions toward Industry 5.0. 2021;:83/3. doi:10.1515/9783110693225-003 .
Miljković, Zoran, Đokić, Lazar, Petrović, Milica, "Application of convolutional neural networks for visual control of intelligent robotic systems" in Soft Computing in Smart Manufacturing - Solutions toward Industry 5.0 (2021):83/3, https://doi.org/10.1515/9783110693225-003 . .