A Hybrid Fuzzy Q-learning algorithm for robot navigation

Sean W. Gordon*, Napoleon H. Reyes, Andre Barczak

*Corresponding author for this work

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

1 Citation (Scopus)

Abstract

In the field of robot navigation, a number of different approaches have been proposed. One of these is Hybrid Fuzzy A* (HFA), which uses the A* algorithm to determine the long term path from the robot to some target, and fuzzy logic to move the robot to each waypoint along the path. This algorithm has been shown to be fast and effective in simulation, however A* is limited in the variables it can consider and the challenges it can be applied to. We propose replacing A* with Q-learning, which does not suffer from these limitations. We demonstrate the ability of Hybrid Fuzzy Q-Learning (HFQL) to navigate a robot to a given target and then apply the algorithm to a different challenge where the robot needs to balance reaching the target quickly against picking up as many subgoals as possible.

Original languageEnglish
Title of host publicationIJCNN 2011 Conference Proceedings
PublisherIEEE
Pages2625-2631
Number of pages7
ISBN (Electronic)978-1-4244-9637-2
ISBN (Print)9781457710865
DOIs
Publication statusPublished - 2011
Externally publishedYes
Event2011 International Joint Conference on Neural Network - San Jose, CA, United States
Duration: 31 Jul 20115 Aug 2011

Publication series

NameProceedings of the International Joint Conference on Neural Networks

Conference

Conference2011 International Joint Conference on Neural Network
Abbreviated titleIJCNN 2011
Country/TerritoryUnited States
CitySan Jose, CA
Period31/07/115/08/11

Fingerprint

Dive into the research topics of 'A Hybrid Fuzzy Q-learning algorithm for robot navigation'. Together they form a unique fingerprint.

Cite this