Skip to the main content

Original scientific paper

https://doi.org/10.17559/TV-20200727095821

Neural Network Driven Automated Guided Vehicle Platform Development for Industry 4.0 Environment

János Simon orcid id orcid.org/0000-0003-2870-5718 ; Department of Technology, Faculty of Engineering, University of Szeged, 6724 Szeged, Hungary
Monika Trojanová* orcid id orcid.org/0000-0002-3317-6649 ; Department of Industrial Engineering and Informatics, Faculty of Manufacturing Technologies with a Seat in Prešov, Technical University of Košice, Bayerova 1, 080 01 Prešov, Slovakia
Alexander Hošovský ; Department of Industrial Engineering and Informatics, Faculty of Manufacturing Technologies with a Seat in Prešov, Technical University of Košice, Bayerova 1, 080 01 Prešov, Slovakia
József Sárosi ; Department of Technology, Faculty of Engineering, University of Szeged, 6724 Szeged, Hungary


Full text: english pdf 1.798 Kb

page 1936-1942

downloads: 705

cite


Abstract

This work presents the development of a new "Two Wheel" Automated Guided Vehicle (AGV) platform for education, competition, and research that is based on sensor fusion and neural networks (NN) with machine learning for Industry 4.0 applications. The method that is described in the paper deals with intelligent path planning and navigation of an AGV that should move safely in an unknown environment. The unknown environment may have obstacles of arbitrary shape and size that can move. Also is described the approach to solving the navigation problem in AGV navigation using a neural networks-based technique based on various types of input sensors. The neural network determines the safe direction for the next point section of the path in the environment while avoiding the nearby obstacles. Simulation examples of the generated path with proposed techniques will be presented.

Keywords

Automated Guided Vehicle (AGV); Industry 4.0; Machine learning; Neural networks (NN); Sensor fusion

Hrčak ID:

264052

URI

https://hrcak.srce.hr/264052

Publication date:

7.11.2021.

Visits: 1.681 *