Application of algorithms for object recognition based on deep convolutional neural networks for visual navigation of a mobile robot

In this paper, we present the results of an analysis of state-of-the-art approaches in the field of object recognition in an image based on deep convolutional neural networks. The purpose of the review is to assess the possibility of applying these approaches in solving problems of visual navigation a mobile robot.

I. Introduction

One of the current trends in the development of ground mobile robotics is the improvement of the autonomous control of mobile robots. A promising way of such control is based on using of visual information about the external environment. This approach is called visual navigation.