Skip to main navigation Skip to search Skip to main content

A Deep Learning-based Visual Perception Approach for Mobile Robots

  • Beihang University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In this work, a deep learning-based approach was developed for the visual path perception of mobile robots, combined with computer vision technology. An experimental platform of differential wheeled mobile robots and a LabViewupper computing platform to realize the basic motion control and test the actual effect of the pre-trained DNN(Deep Neural Network) model was built. The training method of DNN, including the acquisition of data set, Deep Neural Network structure and training program was given out. Experimental results demonstrate the feasibility of applying deep learning to mobile robot's visual perception of path. It has a reference significance for improving the intelligent level of mobile robots.

Original languageEnglish
Title of host publicationProceedings 2018 Chinese Automation Congress, CAC 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages825-829
Number of pages5
ISBN (Electronic)9781728113128
DOIs
StatePublished - 2 Jul 2018
Event2018 Chinese Automation Congress, CAC 2018 - Xi'an, China
Duration: 30 Nov 20182 Dec 2018

Publication series

NameProceedings 2018 Chinese Automation Congress, CAC 2018

Conference

Conference2018 Chinese Automation Congress, CAC 2018
Country/TerritoryChina
CityXi'an
Period30/11/182/12/18

Keywords

  • Deep learning
  • Mobile robots
  • visual perception

Fingerprint

Dive into the research topics of 'A Deep Learning-based Visual Perception Approach for Mobile Robots'. Together they form a unique fingerprint.

Cite this