Neural networks for prediction of robot failures
Само за регистроване кориснике
2014
Чланак у часопису (Објављена верзија)
Метаподаци
Приказ свих података о документуАпстракт
It is known that the supervision and learning of robotic executions is not a trivial problem. Nowadays, robots must be able to tolerate and predict internal failures in order to successfully continue performing their tasks. This study presents a novel approach for prediction of robot execution failures based on neural networks. Real data consisting of robot forces and torques recorded immediately after the system failure are used for the neural network training. The multilayer feedforward neural networks are employed in order to find optimal solution for the failure prediction problem. In total, 7 learning algorithms and 24 neural architectures are implemented in two environments - Matlab and specially designed software titled BPnet. The results show that the neural networks can successfully be applied for the problem in hand with prediction rate of 95.4545%, despite having the erroneous or otherwise incomplete sensor measurements invoked in the dataset. Additionally, the real-world ex...periments are conducted on a mobile robot for obstacle detection and trajectory tracking problems in order to prove the robustness of the proposed prediction approach. In over 96% for the detection problem and 99% for the tracking experiments, neural network successfully predicted the failed information, which evidences the usefulness and the applicability of the developed intelligent method.
Кључне речи:
trajectory tracking / prediction / obstacle detection / Neural networks / mobile robot / execution failuresИзвор:
Proceedings of The Institution of Mechanical Engineers Part C-Journal of Mechanical Engineering Scie, 2014, 228, 8, 1444-1458Издавач:
- Sage Publications Ltd, London
Финансирање / пројекти:
DOI: 10.1177/0954406213507704
ISSN: 0954-4062
WoS: 000336919200014
Scopus: 2-s2.0-84900524079
Колекције
Институција/група
Mašinski fakultetTY - JOUR AU - Diryag, Ali AU - Mitić, Marko AU - Miljković, Zoran PY - 2014 UR - https://machinery.mas.bg.ac.rs/handle/123456789/1875 AB - It is known that the supervision and learning of robotic executions is not a trivial problem. Nowadays, robots must be able to tolerate and predict internal failures in order to successfully continue performing their tasks. This study presents a novel approach for prediction of robot execution failures based on neural networks. Real data consisting of robot forces and torques recorded immediately after the system failure are used for the neural network training. The multilayer feedforward neural networks are employed in order to find optimal solution for the failure prediction problem. In total, 7 learning algorithms and 24 neural architectures are implemented in two environments - Matlab and specially designed software titled BPnet. The results show that the neural networks can successfully be applied for the problem in hand with prediction rate of 95.4545%, despite having the erroneous or otherwise incomplete sensor measurements invoked in the dataset. Additionally, the real-world experiments are conducted on a mobile robot for obstacle detection and trajectory tracking problems in order to prove the robustness of the proposed prediction approach. In over 96% for the detection problem and 99% for the tracking experiments, neural network successfully predicted the failed information, which evidences the usefulness and the applicability of the developed intelligent method. PB - Sage Publications Ltd, London T2 - Proceedings of The Institution of Mechanical Engineers Part C-Journal of Mechanical Engineering Scie T1 - Neural networks for prediction of robot failures EP - 1458 IS - 8 SP - 1444 VL - 228 DO - 10.1177/0954406213507704 ER -
@article{ author = "Diryag, Ali and Mitić, Marko and Miljković, Zoran", year = "2014", abstract = "It is known that the supervision and learning of robotic executions is not a trivial problem. Nowadays, robots must be able to tolerate and predict internal failures in order to successfully continue performing their tasks. This study presents a novel approach for prediction of robot execution failures based on neural networks. Real data consisting of robot forces and torques recorded immediately after the system failure are used for the neural network training. The multilayer feedforward neural networks are employed in order to find optimal solution for the failure prediction problem. In total, 7 learning algorithms and 24 neural architectures are implemented in two environments - Matlab and specially designed software titled BPnet. The results show that the neural networks can successfully be applied for the problem in hand with prediction rate of 95.4545%, despite having the erroneous or otherwise incomplete sensor measurements invoked in the dataset. Additionally, the real-world experiments are conducted on a mobile robot for obstacle detection and trajectory tracking problems in order to prove the robustness of the proposed prediction approach. In over 96% for the detection problem and 99% for the tracking experiments, neural network successfully predicted the failed information, which evidences the usefulness and the applicability of the developed intelligent method.", publisher = "Sage Publications Ltd, London", journal = "Proceedings of The Institution of Mechanical Engineers Part C-Journal of Mechanical Engineering Scie", title = "Neural networks for prediction of robot failures", pages = "1458-1444", number = "8", volume = "228", doi = "10.1177/0954406213507704" }
Diryag, A., Mitić, M.,& Miljković, Z.. (2014). Neural networks for prediction of robot failures. in Proceedings of The Institution of Mechanical Engineers Part C-Journal of Mechanical Engineering Scie Sage Publications Ltd, London., 228(8), 1444-1458. https://doi.org/10.1177/0954406213507704
Diryag A, Mitić M, Miljković Z. Neural networks for prediction of robot failures. in Proceedings of The Institution of Mechanical Engineers Part C-Journal of Mechanical Engineering Scie. 2014;228(8):1444-1458. doi:10.1177/0954406213507704 .
Diryag, Ali, Mitić, Marko, Miljković, Zoran, "Neural networks for prediction of robot failures" in Proceedings of The Institution of Mechanical Engineers Part C-Journal of Mechanical Engineering Scie, 228, no. 8 (2014):1444-1458, https://doi.org/10.1177/0954406213507704 . .