Enhanced robot learning using Fuzzy Q-Learning & context-aware middleware

Charles C. Phiri, Zhaojie Ju, Naoyuki Kubota, Honghai Liu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

362 Downloads (Pure)

Abstract

In this paper we continue with previous work by the authors implementing context-aware middleware to accelerate robot learning from demonstration, LfD. Specifically, we apply Fuzzy Q-Learning, FQL, reinforcement learning strategy to enhance the learning experience of the robot. Typically, fuzzy techniques allow the robot to make decisions without the need for an exhaustive map of the world. FQL, approximates the observable configuration space allowing the robot to overcome the high dimension challenge of feature decomposition and navigation in a stochastic environment.
Original languageEnglish
Title of host publication2016 International Symposium on Micro-NanoMechatronics and Human Science (MHS)
PublisherIEEE
ISBN (Electronic)978-1-5090-2785-9
ISBN (Print)978-1-5090-2786-6
DOIs
Publication statusPublished - 19 Jan 2017
Event27th International Symposium on Micro-NanoMechatronics and Human Science: MHS 2016 - Nagoya, Japan
Duration: 28 Nov 201630 Nov 2016
http://www.mein.nagoya-u.ac.jp/MHS/mhs2016-Top.html

Publication series

Name
ISSN (Electronic)2474-3771

Conference

Conference27th International Symposium on Micro-NanoMechatronics and Human Science
Country/TerritoryJapan
CityNagoya
Period28/11/1630/11/16
Internet address

Fingerprint

Dive into the research topics of 'Enhanced robot learning using Fuzzy Q-Learning & context-aware middleware'. Together they form a unique fingerprint.

Cite this