Prediction of Robot Execution Failures Using Neural Networks
2013
Preuzimanje 🢃
Konferencijski prilog (Objavljena verzija)
Metapodaci
Prikaz svih podataka o dokumentuApstrakt
In recent years, the industrial robotic systems are designed with abilities to adapt and to learn in a structured or unstructured environment. They are able to predict and to react to the undesirable and uncontrollable disturbances which frequently interfere in mission accomplishment. In order to prevent system failure and/or unwanted robot behaviour, various techniques have been addressed. In this study, a novel approach based on the neural networks (NNs) is employed for prediction of robot execution failures. The training and testing dataset used in the experiment consists of forces and torques memorized immediately after the real robot failed in assignment execution. Two types of networks are utilized in order to find best prediction method - recurrent NNs and feedforward NNs. Moreover, we investigated 24 neural architectures implemented in Matlab software package. The experimental results confirm that this approach can be successfully applied to the failures prediction problem, and... that the NNs outperform other artificial intelligence techniques in this domain. To further validate a novel method, real world experiments are conducted on a Khepera II mobile robot in an indoor structured environment. The obtained results for trajectory tracking problem proved usefulness and the applicability of the proposed solution.
Ključne reči:
Neural networks / Mobile robot / Execution failures / Prediction method / The failures prediction problemIzvor:
Proceedings of the 35th International Conference on Production Engineering (ICPE-S 2013), 25 – 28 September 2013 Kraljevo-Kopaonik, 2013, 335-338Izdavač:
- Kraljevo : Faculty of Mechanical and Civil Engineering
Finansiranje / projekti:
- Inovativni pristup u primeni inteligentnih tehnoloških sistema za proizvodnju delova od lima zasnovan na ekološkim principima (RS-MESTD-Technological Development (TD or TR)-35004)
Kolekcije
Institucija/grupa
Mašinski fakultetTY - CONF AU - Mitić, Marko AU - Miljković, Zoran AU - Vuković, Najdan AU - Babić, Bojan AU - Diryag, Ali PY - 2013 UR - https://machinery.mas.bg.ac.rs/handle/123456789/4473 AB - In recent years, the industrial robotic systems are designed with abilities to adapt and to learn in a structured or unstructured environment. They are able to predict and to react to the undesirable and uncontrollable disturbances which frequently interfere in mission accomplishment. In order to prevent system failure and/or unwanted robot behaviour, various techniques have been addressed. In this study, a novel approach based on the neural networks (NNs) is employed for prediction of robot execution failures. The training and testing dataset used in the experiment consists of forces and torques memorized immediately after the real robot failed in assignment execution. Two types of networks are utilized in order to find best prediction method - recurrent NNs and feedforward NNs. Moreover, we investigated 24 neural architectures implemented in Matlab software package. The experimental results confirm that this approach can be successfully applied to the failures prediction problem, and that the NNs outperform other artificial intelligence techniques in this domain. To further validate a novel method, real world experiments are conducted on a Khepera II mobile robot in an indoor structured environment. The obtained results for trajectory tracking problem proved usefulness and the applicability of the proposed solution. PB - Kraljevo : Faculty of Mechanical and Civil Engineering C3 - Proceedings of the 35th International Conference on Production Engineering (ICPE-S 2013), 25 – 28 September 2013 Kraljevo-Kopaonik T1 - Prediction of Robot Execution Failures Using Neural Networks EP - 338 SP - 335 UR - https://hdl.handle.net/21.15107/rcub_machinery_4473 ER -
@conference{ author = "Mitić, Marko and Miljković, Zoran and Vuković, Najdan and Babić, Bojan and Diryag, Ali", year = "2013", abstract = "In recent years, the industrial robotic systems are designed with abilities to adapt and to learn in a structured or unstructured environment. They are able to predict and to react to the undesirable and uncontrollable disturbances which frequently interfere in mission accomplishment. In order to prevent system failure and/or unwanted robot behaviour, various techniques have been addressed. In this study, a novel approach based on the neural networks (NNs) is employed for prediction of robot execution failures. The training and testing dataset used in the experiment consists of forces and torques memorized immediately after the real robot failed in assignment execution. Two types of networks are utilized in order to find best prediction method - recurrent NNs and feedforward NNs. Moreover, we investigated 24 neural architectures implemented in Matlab software package. The experimental results confirm that this approach can be successfully applied to the failures prediction problem, and that the NNs outperform other artificial intelligence techniques in this domain. To further validate a novel method, real world experiments are conducted on a Khepera II mobile robot in an indoor structured environment. The obtained results for trajectory tracking problem proved usefulness and the applicability of the proposed solution.", publisher = "Kraljevo : Faculty of Mechanical and Civil Engineering", journal = "Proceedings of the 35th International Conference on Production Engineering (ICPE-S 2013), 25 – 28 September 2013 Kraljevo-Kopaonik", title = "Prediction of Robot Execution Failures Using Neural Networks", pages = "338-335", url = "https://hdl.handle.net/21.15107/rcub_machinery_4473" }
Mitić, M., Miljković, Z., Vuković, N., Babić, B.,& Diryag, A.. (2013). Prediction of Robot Execution Failures Using Neural Networks. in Proceedings of the 35th International Conference on Production Engineering (ICPE-S 2013), 25 – 28 September 2013 Kraljevo-Kopaonik Kraljevo : Faculty of Mechanical and Civil Engineering., 335-338. https://hdl.handle.net/21.15107/rcub_machinery_4473
Mitić M, Miljković Z, Vuković N, Babić B, Diryag A. Prediction of Robot Execution Failures Using Neural Networks. in Proceedings of the 35th International Conference on Production Engineering (ICPE-S 2013), 25 – 28 September 2013 Kraljevo-Kopaonik. 2013;:335-338. https://hdl.handle.net/21.15107/rcub_machinery_4473 .
Mitić, Marko, Miljković, Zoran, Vuković, Najdan, Babić, Bojan, Diryag, Ali, "Prediction of Robot Execution Failures Using Neural Networks" in Proceedings of the 35th International Conference on Production Engineering (ICPE-S 2013), 25 – 28 September 2013 Kraljevo-Kopaonik (2013):335-338, https://hdl.handle.net/21.15107/rcub_machinery_4473 .