Optical Flow-Hermite and Fuzzy Q-Learning Based Robotic Navigation Approach

Ernesto Moya-Albor, Jorge Brieva, Hiram Ponce, Sandra L. Gomez-Coronel

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

Abstract

The present paper presents a bio-inspired optical flow approach to autonomous robotics navigation. It uses a Fuzzy Q-Learning (FQL) method to take decisions in an unknown environment through a reinforcement signal. The proposed method was implemented in a virtual robotics system using the V-REP software and in communication con MATLAB. The preliminary results show that the robot was able to navigate successfully in unknown environments.

Original languageEnglish
Title of host publicationProceedings - 2021 International Conference on Mechatronics, Electronics and Automotive Engineering, ICMEAE 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages26-31
Number of pages6
ISBN (Electronic)9781665495400
DOIs
StatePublished - 2021
Event2021 International Conference on Mechatronics, Electronics and Automotive Engineering, ICMEAE 2021 - Virtual, Online, Mexico
Duration: 22 Nov 202126 Nov 2021

Publication series

NameProceedings - 2021 International Conference on Mechatronics, Electronics and Automotive Engineering, ICMEAE 2021

Conference

Conference2021 International Conference on Mechatronics, Electronics and Automotive Engineering, ICMEAE 2021
Country/TerritoryMexico
CityVirtual, Online
Period22/11/2126/11/21

Keywords

  • Hermite transform
  • V-REP
  • fuzzy Q-learning
  • optical flow
  • reinforcement signal
  • vision-based control navigation

Fingerprint

Dive into the research topics of 'Optical Flow-Hermite and Fuzzy Q-Learning Based Robotic Navigation Approach'. Together they form a unique fingerprint.

Cite this