Neural network learning from demonstration and epipolar geometry for visual control of a nonholonomic mobile robot
Само за регистроване кориснике
2014
Чланак у часопису (Објављена верзија)
Метаподаци
Приказ свих података о документуАпстракт
The control of a robot system using camera information is a challenging task regarding unpredictable conditions, such as feature point mismatch and changing scene illumination. This paper presents a solution for the visual control of a nonholonomic mobile robot in demanding real world circumstances based on machine learning techniques. A novel intelligent approach for mobile robots using neural networks (NNs), learning from demonstration (LfD) framework, and epipolar geometry between two views is proposed and evaluated in a series of experiments. A direct mapping from the image space to the actuator command is conducted using two phases. In an offline phase, NN-LfD approach is employed in order to relate the feature position in the image plane with the angular velocity for lateral motion correction. An online phase refers to a switching vision based scheme between the epipole based linear velocity controller and NN-LfD based angular velocity controller, which selection depends on the f...eature distance from the pre-defined interest area in the image. In total, 18 architectures and 6 learning algorithms are tested in order to find optimal solution for robot control. The best training outcomes for each learning algorithms are then employed in real time so as to discover optimal NN configuration for robot orientation correction. Experiments conducted on a nonholonomic mobile robot in a structured indoor environment confirm an excellent performance with respect to the system robustness and positioning accuracy in the desired location.
Кључне речи:
Visual control / Neural network / Mobile robot / Learning from demonstration / Epipolar geometryИзвор:
Soft Computing, 2014, 18, 5, 1011-1025Издавач:
- Springer, New York
Финансирање / пројекти:
- Иновативни приступ у примени интелигентних технолошких система за производњу делова од лима заснован на еколошким принципима (RS-MESTD-Technological Development (TD or TR)-35004)
DOI: 10.1007/s00500-013-1121-8
ISSN: 1432-7643
WoS: 000334522300012
Scopus: 2-s2.0-84898917960
Колекције
Институција/група
Mašinski fakultetTY - JOUR AU - Mitić, Marko AU - Miljković, Zoran PY - 2014 UR - https://machinery.mas.bg.ac.rs/handle/123456789/1894 AB - The control of a robot system using camera information is a challenging task regarding unpredictable conditions, such as feature point mismatch and changing scene illumination. This paper presents a solution for the visual control of a nonholonomic mobile robot in demanding real world circumstances based on machine learning techniques. A novel intelligent approach for mobile robots using neural networks (NNs), learning from demonstration (LfD) framework, and epipolar geometry between two views is proposed and evaluated in a series of experiments. A direct mapping from the image space to the actuator command is conducted using two phases. In an offline phase, NN-LfD approach is employed in order to relate the feature position in the image plane with the angular velocity for lateral motion correction. An online phase refers to a switching vision based scheme between the epipole based linear velocity controller and NN-LfD based angular velocity controller, which selection depends on the feature distance from the pre-defined interest area in the image. In total, 18 architectures and 6 learning algorithms are tested in order to find optimal solution for robot control. The best training outcomes for each learning algorithms are then employed in real time so as to discover optimal NN configuration for robot orientation correction. Experiments conducted on a nonholonomic mobile robot in a structured indoor environment confirm an excellent performance with respect to the system robustness and positioning accuracy in the desired location. PB - Springer, New York T2 - Soft Computing T1 - Neural network learning from demonstration and epipolar geometry for visual control of a nonholonomic mobile robot EP - 1025 IS - 5 SP - 1011 VL - 18 DO - 10.1007/s00500-013-1121-8 ER -
@article{ author = "Mitić, Marko and Miljković, Zoran", year = "2014", abstract = "The control of a robot system using camera information is a challenging task regarding unpredictable conditions, such as feature point mismatch and changing scene illumination. This paper presents a solution for the visual control of a nonholonomic mobile robot in demanding real world circumstances based on machine learning techniques. A novel intelligent approach for mobile robots using neural networks (NNs), learning from demonstration (LfD) framework, and epipolar geometry between two views is proposed and evaluated in a series of experiments. A direct mapping from the image space to the actuator command is conducted using two phases. In an offline phase, NN-LfD approach is employed in order to relate the feature position in the image plane with the angular velocity for lateral motion correction. An online phase refers to a switching vision based scheme between the epipole based linear velocity controller and NN-LfD based angular velocity controller, which selection depends on the feature distance from the pre-defined interest area in the image. In total, 18 architectures and 6 learning algorithms are tested in order to find optimal solution for robot control. The best training outcomes for each learning algorithms are then employed in real time so as to discover optimal NN configuration for robot orientation correction. Experiments conducted on a nonholonomic mobile robot in a structured indoor environment confirm an excellent performance with respect to the system robustness and positioning accuracy in the desired location.", publisher = "Springer, New York", journal = "Soft Computing", title = "Neural network learning from demonstration and epipolar geometry for visual control of a nonholonomic mobile robot", pages = "1025-1011", number = "5", volume = "18", doi = "10.1007/s00500-013-1121-8" }
Mitić, M.,& Miljković, Z.. (2014). Neural network learning from demonstration and epipolar geometry for visual control of a nonholonomic mobile robot. in Soft Computing Springer, New York., 18(5), 1011-1025. https://doi.org/10.1007/s00500-013-1121-8
Mitić M, Miljković Z. Neural network learning from demonstration and epipolar geometry for visual control of a nonholonomic mobile robot. in Soft Computing. 2014;18(5):1011-1025. doi:10.1007/s00500-013-1121-8 .
Mitić, Marko, Miljković, Zoran, "Neural network learning from demonstration and epipolar geometry for visual control of a nonholonomic mobile robot" in Soft Computing, 18, no. 5 (2014):1011-1025, https://doi.org/10.1007/s00500-013-1121-8 . .