Revko Anatolii, Chernihiv National University of Technology (95 Shevchenka Str., 14027 Chernihiv, Ukraine)

Fesenko Artem, Chernihiv National University of Technology (95 Shevchenka Str., 14027 Chernihiv, Ukraine)

Language: ukrainian


The article discusses the possibility of creating the electronic system of pattern recognition for partly autonomous control mobile platform on Bengt Ilon. It is proposed using artificial neuron system for pattern recognition. It allowing the platform maneuvers partly autonomous orient on the environment. Command can also be obtained from the environment in the form of graphic images. The devices moving on mechanum wheels different from other similar devices to perform quite complex maneuvers in confined spaces. This property makes them extremely promising for use in many industries, storage and transport goods military field, wherever there is a need to move in a confined space to perform complex turns, platforms inaccessible to conventional wheels.

Key words:

pattern recognition, artificial neuron system, perceptron, mechanum wheels


1. Diegel, O., Badve, A., Bright, G., Potgieter, J., Tlale, S. (2002). “Improved Mecanum Wheel Design for Omni- directional Robots”, Proc. Australasian Conference on Robotics and Automation (Auckland, November 27-29, 2002), Auckland, pp. 117-121.

2. Uossermen, F. (1992). Neirokompiuternaia tekhnika: Teoriia i praktika [Neurocomputing equipment: Theory and Practice]. Moscow: Mir, 184 p. (in Russian).

3. Achint, A., Kirchner, F. (2014). Object Recognition and Localization: The Role of Tactile Sensors. In Sensors - Open Access JournalMDPI AG. Basel, Switzerland, volume Special Issue on Tactile Sensors and Sensing Systems, pp. 3227-3266.

4. Tassov, K. L. (2012). Primenenie iskusstvennoi neironnoi seti neokognitron dlia raspoznavaniia gosudarstvennykh registratcionnykh znakov [Application of artificial neural network to recognize neocognitron state registration signs]. Vestnik MGTU im. N. E. Baumana. Ser. «Priborostroenie» - Herald of the Bauman Moscow State Technical University. Series Instrument Engineering, special issue 2: Software engineering, pp. 189–199 (in Russian).

5. Sova, A. A., Fediaev, O. I. (2011). Matematicheskaia model raspoznavaniia i obucheniia neokognitrona [The mathematical model of pattern recognition and learning neocognitron]. Informatika i kompiuternye tekhnologii: VII Mezhdunarodnaia nauchno-tekhnicheskaia konferentciia studentov, aspirantov i molodykh nauchnykh rabotnikov – Informatics and computer technology. Conference proceedings of the VII international scientific-technical conference of students, postgraduates and young researchers. (Donetck, 2011), pp. 164–168 (in Ukrainіan).

6. Won Oh Lee, Yeong Gon Kim, Hyung Gil Hong and Kang Ryoung Park (2014). Face Recognition System for Set-Top Box-Based Intelligent TV. Sensors 2014, issue 14, pp. 21726–21749. doi:10.3390/s141121726.

7. Neural network toolboxRetrieved from: http://www.mathworks.com/help/nnet/index.html.

8. Lemish, S. V., Husev, O. O., Revko, A. S. (2013). Zavadostiika systema peredachi danykh dlia sylovoho peretvoriuvacha [Anti-interference data transmission system for power converter]. Visnyk Chernihivskoho derzhavnoho tekhnolohichnoho universytetu – Journal of Chernihiv state technological university. Series «Engineering science". Chernihiv: ChDTU, 2013. № 1 (63). – S. 192–199 (in Ukrainіan).

9.Denisov, Iu. O., Revko, A. S. (2005). Reversivnyi kvazirezonansnyi impulsnyi preobrazovatel s tcifrovoi sistemoi upravleniia [Reversible switching quasi-resonant converter with a digital control system]Tekhnichna elektrodynamika, tematychnyi vypusk: sylova elektronika ta enerhoefektyvnist» -Technical Electrodynamics, thematic issue: Power electronics and energy efficiency, part 4, pp. 50-53 (in Russian).