https://oldena.lpnu.ua/handle/ntb/52433| Title: | Model and Training Methods of Autonomous Navigation System for Compact Drones |
| Authors: | Moskalenko, Vyacheslav Moskalenko, Alona Korobov, Artem Boiko, Olha Martynenko, Serhii Borovenskyi, Oleksandr |
| Affiliation: | Sumy State University |
| Bibliographic description (Ukraine): | Model and Training Methods of Autonomous Navigation System for Compact Drones / Vyacheslav Moskalenko, Alona Moskalenko, Artem Korobov, Olha Boiko, Serhii Martynenko, Oleksandr Borovenskyi // Data stream mining and processing : proceedings of the IEEE second international conference, 21-25 August 2018, Lviv. — Львів : Lviv Politechnic Publishing House, 2018. — P. 503–508. — (Machine Vision and Pattern Recognition). |
| Bibliographic description (International): | Model and Training Methods of Autonomous Navigation System for Compact Drones / Vyacheslav Moskalenko, Alona Moskalenko, Artem Korobov, Olha Boiko, Serhii Martynenko, Oleksandr Borovenskyi // Data stream mining and processing : proceedings of the IEEE second international conference, 21-25 August 2018, Lviv. — Lviv Politechnic Publishing House, 2018. — P. 503–508. — (Machine Vision and Pattern Recognition). |
| Is part of: | Data stream mining and processing : proceedings of the IEEE second international conference, 2018 |
| Conference/Event: | IEEE second international conference "Data stream mining and processing" |
| Issue Date: | 28-Feb-2018 |
| Publisher: | Lviv Politechnic Publishing House |
| Place of the edition/event: | Львів |
| Temporal Coverage: | 21-25 August 2018, Lviv |
| Keywords: | navigation visual odometry convolutional neural network neural gas information criterion support vector regression |
| Number of pages: | 6 |
| Page range: | 503-508 |
| Start page: | 503 |
| End page: | 508 |
| Abstract: | The paper presents a novel model of convolutional neural network for visual feature extraction, support vector machine for position prediction and information-extreme classifier for obstacle prediction with new training methods to build decision rules of autonomous navigation system for compact drones are presented in the paper. Sparse-coding neural gas algorithm for unsupervised training of the convolution filters, supervised incremental learning method for training the regression model and particle swarm optimization algorithm for training the classifier model are proposed. The complex criterion for choosing parameter of feature extractor model is considered. Simulation results with optimal model on test open datasets confirm the suitability of proposed algorithms for practical usage. |
| URI: | https://ena.lpnu.ua/handle/ntb/52433 |
| ISBN: | © Національний університет „Львівська політехніка“, 2018 © Національний університет „Львівська політехніка“, 2018 |
| Copyright owner: | © Національний університет “Львівська політехніка”, 2018 |
| URL for reference material: | http://cs231n.stanford.edu/reports/ https://arxiv.org/pdf/1611.06069.pdf https://www.researchgate.net/publication/238519783_A_New_SVR_I |
| References (Ukraine): | [1] S. Wang, Z. Deng, and G. Yin, An Accurate GPS-IMU/DR Data Fusion Method for Driverless Car Based on a Set of Predictive Models and Grid Constraints,’ Basel, Switzerland : Multidisciplinary Digital Publishing Institute, vol. 16(3), pp. 280–293, 2016. [2] B. Suwandi, T. Kitasuka, and M. Aritsugi, “Low-cost IMU and GPS fusion strategy for apron vehicle positioning,” TENCON 2017, IEEE Region 10 Conference, Penang, Malaysia, pp. 449–454, Nov. 2017. [3] B. A. Mary, and P. H. Gerhard, “Pose Estimation of a Mobile Robot Based on Fusion of IMU Data and Vision Data Using an Extended Kalman Filter,” Basel, Switzerland : Multidisciplinary Digital Publishing Institute, vol. 17(10), pp. 2164, 2017. [4] J. Folkesson, J. Leederkerken, R. Williams, and A. Patrikalakis, “A Feature Based Navigation System for an Autonomous Underwater Robot,” In: Laugier C., Siegwart R. (eds) Field and Service Robotics. Springer Tracts in Advanced Robotics. Springer : Berlin/Heidelberg, 2008. vol. 42, pp. 105-114. [5] C. Cadena, L. Carlone, H. Carrillo, Y. Latif, D. Scaramuzza, J. Neira, I. Reid, and J. J. Leonard, “Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Age,” IEEE Transactions on Robotics, vol. 32, no. 6, pp. 1309–1332, 2016. [6] G.-L. Dorian, S. Marta, D. T. Juan, and J.M.M. Montiel, “Real-time monocular object SLAM. Robotics and Autonomous Systems,” North-Holland Publishing Co. : Amsterdam, Netherlands, 2016. vol.75, i. PB, pp. 435–449. [7] Th. Ayoul, T. Buckley, and F. Crevier. UAV Navigation above Roads Using Convolutional Neural Networks Available from: http://cs231n.stanford.edu/reports/ 2017/pdfs/553.pdf. [8] V. Mohanty DeepVO: A Deep Learning approach for Monocular Visual Odometry. Computer Vision and Pattern Recognition, 2016. Available from: https://arxiv.org/pdf/1611.06069.pdf [9] K. Labusch, E. Barth, and T. Martinetz, “Sparse Coding Neural Gas: Learning of Overcomplete Data Representations,” Neurocomputing, Elsevier Science Publishers B. V.: Amsterdam, Netherlands, vol. 72, is. 7–9, pp. 1547–1555, 2009. [10] H. Xu, R. Wang, and K. Wang. A New SVR Incremental Algorithm Based on Boundary Vector. 2010. Available from: https://www.researchgate.net/publication/238519783_A_New_SVR_I ncremental_Algorithm_Based_on_Boundary_Vector [11] V. V. Moskalenko, and A. G. Korobov, “Information-extreme algorithm of the system for recognition of objects on the terrain with optimization parameter feature extraction,” Radio Electronics, Computer Science, Control. Zaporizhzhya National Technical University : Zaporizhzhya, Ukraine, no. 2, pp. 38–45, 2017. |
| References (International): | [1] S. Wang, Z. Deng, and G. Yin, An Accurate GPS-IMU/DR Data Fusion Method for Driverless Car Based on a Set of Predictive Models and Grid Constraints,’ Basel, Switzerland : Multidisciplinary Digital Publishing Institute, vol. 16(3), pp. 280–293, 2016. [2] B. Suwandi, T. Kitasuka, and M. Aritsugi, "Low-cost IMU and GPS fusion strategy for apron vehicle positioning," TENCON 2017, IEEE Region 10 Conference, Penang, Malaysia, pp. 449–454, Nov. 2017. [3] B. A. Mary, and P. H. Gerhard, "Pose Estimation of a Mobile Robot Based on Fusion of IMU Data and Vision Data Using an Extended Kalman Filter," Basel, Switzerland : Multidisciplinary Digital Publishing Institute, vol. 17(10), pp. 2164, 2017. [4] J. Folkesson, J. Leederkerken, R. Williams, and A. Patrikalakis, "A Feature Based Navigation System for an Autonomous Underwater Robot," In: Laugier C., Siegwart R. (eds) Field and Service Robotics. Springer Tracts in Advanced Robotics. Springer : Berlin/Heidelberg, 2008. vol. 42, pp. 105-114. [5] C. Cadena, L. Carlone, H. Carrillo, Y. Latif, D. Scaramuzza, J. Neira, I. Reid, and J. J. Leonard, "Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Age," IEEE Transactions on Robotics, vol. 32, no. 6, pp. 1309–1332, 2016. [6] G.-L. Dorian, S. Marta, D. T. Juan, and J.M.M. Montiel, "Real-time monocular object SLAM. Robotics and Autonomous Systems," North-Holland Publishing Co. : Amsterdam, Netherlands, 2016. vol.75, i. PB, pp. 435–449. [7] Th. Ayoul, T. Buckley, and F. Crevier. UAV Navigation above Roads Using Convolutional Neural Networks Available from: http://cs231n.stanford.edu/reports/ 2017/pdfs/553.pdf. [8] V. Mohanty DeepVO: A Deep Learning approach for Monocular Visual Odometry. Computer Vision and Pattern Recognition, 2016. Available from: https://arxiv.org/pdf/1611.06069.pdf [9] K. Labusch, E. Barth, and T. Martinetz, "Sparse Coding Neural Gas: Learning of Overcomplete Data Representations," Neurocomputing, Elsevier Science Publishers B. V., Amsterdam, Netherlands, vol. 72, is. 7–9, pp. 1547–1555, 2009. [10] H. Xu, R. Wang, and K. Wang. A New SVR Incremental Algorithm Based on Boundary Vector. 2010. Available from: https://www.researchgate.net/publication/238519783_A_New_SVR_I ncremental_Algorithm_Based_on_Boundary_Vector [11] V. V. Moskalenko, and A. G. Korobov, "Information-extreme algorithm of the system for recognition of objects on the terrain with optimization parameter feature extraction," Radio Electronics, Computer Science, Control. Zaporizhzhya National Technical University : Zaporizhzhya, Ukraine, no. 2, pp. 38–45, 2017. |
| Content type: | Conference Abstract |
| Appears in Collections: | Data stream mining and processing : proceedings of the IEEE second international conference |
| File | Description | Size | Format | |
|---|---|---|---|---|
| 2018_Moskalenko_V-Model_and_Training_Methods_503-508.pdf | 552.91 kB | Adobe PDF | View/Open | |
| 2018_Moskalenko_V-Model_and_Training_Methods_503-508__COVER.png | 537.49 kB | image/png | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.