MODELS AND METHODS OF INTELLECTUAL INFORMATION TECHNOLOGY OF AUTONOMOUS NAVIGATION FOR COMPACT DRONES

Authors

  • V. V. Moskalenko Sumy State University, Sumy, Ukraine, Ukraine
  • A. S. Moskalenko Sumy State University, Sumy, Ukraine, Ukraine
  • A. G. Korobov Sumy State University, Sumy, Ukraine, Ukraine

DOI:

https://doi.org/10.15588/1607-3274-2018-3-8

Keywords:

navigation, visual odometry, unmanned aerial vehicle, convolutional neural network, neural gas, information criterion, support vector method.

Abstract

Context of this article topics is that the issues of choosing the optimal in information and cost sense of models and methods of data
analysis in autonomous navigation systems under a priori uncertainty, resource and information constraints are not sufficiently investigated
and are still not fully resolved.
Objective – to increase the efficiency of the autonomous navigation system of a compact drone on the terrain, based on data from visual
and inertial sensors, operating in training and exam modes in the conditions of limited computing resources and the volume of the training sample, in the information and value sense.
Methods of a research are based on the usage of technology of convolutional neural networks for the formation of a feature representation of visual observations, sparse-coding neural gas algorithms for the training of convolutional filters, the model of support vectors for regression analysis of data, on the principles of mathematical statistics and information theory for constructing and evaluating the functional efficiency of classification decision rules.
Results: new models and methods of information intelligent technology of autonomous navigation for compact drones have been developed,
allowing the training of the most computationally labor-intensive component of the system, the feature extractor from observation, in
unsupervised manner in the process of direct propagation of the signal. In this case, the criterion for choosing the optimal parameters in information and cost sense for model of data analysis is proposed, and it is shown by the results of physical modeling that the validity of the
formed decision rules is acceptable for practical use.
Conclusions. The architecture of the convolutional neural network and the method of its unsupervised learning for the formation of a
feature representation of observations in the autonomous navigation problem based on the algorithm of sparse coding neural gas is proposed. The criterion for choosing data analysis parameters is developed and according to the results of physical modeling, the suitability for practical use of developed algorithms of navigation on unknown terrain is proved. The practical value of the results obtained for unmanned aviation is to form a modern scientific and methodological basis for designing capable of training autonomous navigation systems for compact drones operating in the conditions of resource and information constraints.

References

Wang S., Deng Z. , Yin G. An Accurate GPS-IMU/DR Data Fusion Method for Driverless Car Based on a Set of Predictive Models and Grid Constraints. Sensors [Electronic resource]. Basel, Switzerland, Multidisciplinary Digital Publishing Institute, 2016, Vol. 16(3), pp. 280–293. DOI 10.3390/s16030280.

Suwandi B., Kitasuka T., Aritsugi M. Low-cost IMU and GPS

fusion strategy for apron vehicle positioning, TENCON 2017 IEEE Region 10 Conference, 2017, Penang, Malaysia, 5–8 Nov. 2017 : proceedings, pp. 449–454. DOI: 10.1109/TENCON.2017.8227906.

Mary B., Gerhard P. H. A. Pose Estimation of a Mobile Robot

Based on Fusion of IMU Data and Vision Data Using an Extended Kalman Filter. [Electronic resource], Sensors, 2017, Vol. 17(10), P. 2164. DOI: 10.3390/s17102164.

Folkesson J. , Leederkerken J. , Williams R. , Patrikalakis A. 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. DOI 10.1007/978-3-540-75404-6_10.

Fanani N., Stürck A., Ochs M., Bradler H. , Mester R. Predictive monocular odometry (PMO): What is possible without RANSAC and multiframe bundle adjustment? Image and Vision Computing volume, 2017, Vol. 68, pp. 3–13. DOI:

1016/j.imavis.2017.08.002. 6. Cadena C., Carlone L., Carrillo H. et al Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Age, IEEE Transactions on Robotics, 2016, Vol 32, No. 6, pp. 1309–1332. DOI: 10.1109/ TRO.2016.2624754.

Dorian G.-L., Marta S. , Juan D. T., Montiel J.M.M. Real-time

monocular object SLAM, Robotics and Autonomous Systems,

, Vol. 75, І. PB, pp. 435–449. DOI:10.1016/

j.robot.2015.08.009.

Ayoul Th., Buckley T., Crevier F. UAV Navigation above Roads Using Convolutional Neural Networks [Electronic resource], Available from: http://cs231n.stanford.edu/reports/

/pdfs/553.pdf.

Mohanty V. DeepVO : A Deep Learning approach for Monocular Visual Odometry [Electronic resource], Computer Vision and Pattern Recognition, 2016, Available from: https://arxiv.org/pdf/1611.06069.pdf.

Labusch K., Barth E., Martinetz T. Sparse Coding Neural Gas: Learning of Overcomplete Data Representations, Neurocomputting, 2009, Vol. 72, І. 7–9, pp. 1547–1555.

DOI:10.1016/j.neucom.2008.11.027.

Xu H., R. Wang, Wang K. A New SVR Incremental Algorithm

Based on Boundary Vector [Electronic resource], International

Conference on Computational Intelligence and Software Engineering (CiSE 2010), Wuhan, China 10–12 Dec. 2010, proceedings. Zürich, Springer, 2010, pp. 145–149.

DOI: 10.1109/CISE.2010.5676955.

Moskalenko V. V., Korobov A. G. Information-extreme algorithm of the system for recognition of objects on the terrain with optimization parameter feature extraction, Radio Electronics, Computer Science, Control, 2017, No. 2, pp. 38–45. DOI 10.15588/1607-3274-2017-2-7.

Moskalenko V. V., Rizhova A. S., Dovbysh A. S. Intelektual’na systema pidtrymky pryjnjattja rishen’ dlja funkcional’nogo diagnostuvannja na gamma-kameri, Radio Electronics, Computer Science, Control, 2015, No. 4, pp. 52–58. DOI: 10.15588/1607-3274-2015-4-8.

Downloads

How to Cite

Moskalenko, V. V., Moskalenko, A. S., & Korobov, A. G. (2018). MODELS AND METHODS OF INTELLECTUAL INFORMATION TECHNOLOGY OF AUTONOMOUS NAVIGATION FOR COMPACT DRONES. Radio Electronics, Computer Science, Control, (3). https://doi.org/10.15588/1607-3274-2018-3-8

Issue

No. 3 (2018): Radio Electronics, Computer Science, Control

Section

Mathematical and computer modelling

License

Copyright (c) 2018 V. V. Moskalenko, A. S. Moskalenko, A. G. Korobov

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Creative Commons Licensing Notifications in the Copyright Notices

The journal allows the authors to hold the copyright without restrictions and to retain publishing rights without restrictions.

The journal allows readers to read, download, copy, distribute, print, search, or link to the full texts of its articles.

The journal allows to reuse and remixing of its content, in accordance with a Creative Commons license СС BY -SA.

Authors who publish with this journal agree to the following terms:

  • Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License CC BY-SA that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.

  • Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.

  • Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.