1. AMM
  2. All Volumes and Issues
  3. Volume 2, Number 1(2), 2020
  4. Using Neural Networks for Developing a System to Avoid Road Obstacles

Using Neural Networks for Developing a System to Avoid Road Obstacles

AMM.
2020;
Volume 2, Number 1(2)
: pp. 24 - 33
https://doi.org/10.23939/amm2020.01.024
Authors:
  1. U. Dzelendziak
  2. M. Vyhrynovskyi
1
Lviv Polytechnic National University
2
Lviv Polytechnic National University

The possibility of using a neural network to implement a system of avoidance of obstacles on the road has been investigated. The algorithms based on which such a system can work has been reviewed, also the principle of learning of the neural network has been considered. In order to implement investigation the simulator based on Unity and ML Agents has been developed. Using simulator the efficiency of education and this neural network in different configurations has been investigated.

neural network
autopilot
obstacle avoidance
road simulator
scene editor
Unity ML Agents plugin
  1. Korotka L.I., Naumenko N.Yu. Rozrobka neiromerezhevogo programnogo modulia planuvannia traiektorii ruhu obiektu na ploschyni./ Inzhenerni ta osvitni tekhnologii № 2 (10), 2015, — S.28-35.
  2. Lysenko V.P., Shvorov S.A., Komarchuk D.S., Chyrchenko D.V. Metod rozpiznavannia pereshkod na shliakhu ruhu robotyzovanoi zbyralnoi tekhniky / Tekhnika ta energetyka № 256, 2016, — S.79-87.
  3. Svatiuk D.R., Svatiuk O.R., Belei O. I. Zastosuvannia zgortkovykh neironnykh merezh dlia bezpeky rozpiznavannia obiektiv u videopototsi. / Kiberbezpeka: osvita, nauka, tekhnika № 4 (8), 2020, — S. 97-112.
  4. Rashyd T. Sozdaiom neironnuyu set. SPb.: Alfa-kniga, 2017. — 274 s.
  5. S. Semenov, О. Lipchanska, M. Lipchanskyi. Adapted neural network of information support subsystem. / Nauka i tekhnika Povitrianykh Syl Zbroinykh Syl Ukrainy № 1 (34), 2019, — S. 102-106.