E.A. Ivashina
Kaluga Branch of Bauman Moscow State University, Post-graduate Student, 2, Bazhenova str., Kaluga, 248000, Russia, tel.: +7(910)913-68-24, This email address is being protected from spambots. You need JavaScript enabled to view it.
M.O. Korlyakova
PhD in Technical Sciences, Kaluga Branch of Bauman Moscow State University, Assistant Professor, 2, Bazhenova str., Kaluga, 248000, Russia, tel.: +7(910)913-68-24, This email address is being protected from spambots. You need JavaScript enabled to view it.
A.Yu. Pilipenko
Sosensky Instrument Engineering Plant - Branch of Research and Development Center of Automation and Instrument Engineering n.a. academician N.A. Pilyugin, Engineer, 1, I Zavodskoy proezd, Sosensky, Kozelsky r-n, Kaluzhskaya obl., 249711, Russia, tel.: +7(910)913-68-24, This email address is being protected from spambots. You need JavaScript enabled to view it.
A.A. Filimonkov
PhD in Technical Sciences, Sosensky Instrument Engineering Plant - Branch of Research and Development Center of Automation and Instrument Engineering n.a. academician N.A. Pilyugin, Chief Designer, 1, I Zavodskoy proezd, Sosensky, Kozelsky r-n, Kaluzhskaya obl., 249711, Russia, tel.: +7(910)913-68-24, This email address is being protected from spambots. You need JavaScript enabled to view it.
Abstract
The article considers the possibilities of unmanned vehicles control systems intellectualization by the means of computer vision systems, based on neural network approach. The basic learning rules were stated and the motion simulation with learning and without learning was carried out. It is shown that periodic self-learning of neural network, performed on board of autonomous unmanned system during motion, allows improving of computing accuracy for covered distance and space coordinates by constant adaptation to the changing environmental conditions.
Key words
Neural networks, computer vision systems.
Year 2015 Issue number 4 Consecutive issue number 9 Pages 25-29
UDC identifier: 004.93'1:004.032.26
