Loughborough University
Leicestershire, UK
LE11 3TU
+44 (0)1509 263171
Loughborough University

Loughborough University Institutional Repository

Please use this identifier to cite or link to this item: https://dspace.lboro.ac.uk/2134/34769

Title: S.A.R.A.H.: The bipedal robot with machine learning step decision making
Authors: Kouppas, Christos
Meng, Qinggang
King, Mark A.
Majoe, Dennis
Issue Date: 2018
Publisher: © IJMERR
Citation: KOUPPAS, C. ... et al, 2018. S.A.R.A.H.: The bipedal robot with machine learning step decision making. International Journal of Mechanical Engineering and Robotics Research, 7 (4), pp.379-384.
Abstract: Herein, we describe a custom-made bipedal robot that uses electromagnets for performing movements as opposed to conventional DC motors. The robot uses machine learning to stabilize its self by taking steps. The results of several machine learning techniques for step decision are described. The robot does not use electric motors as actuators. As a result, it makes imprecise movements and is inherently unstable. To maintain stability, it must take steps. Classifiers are required to learn from users about when and which leg to move to maintain stability and locomotion. Classifiers such as Decision tree, Linear/Quadratic Discriminant, Support Vector Machine, K-Nearest Neighbor, and Neural Networks are trained and compared. Their performance/accuracy is noted.
Description: This is an Open Access Article. It is published by IJMERR under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International Licence (CC BY-NC-ND). Full details of this licence are available at: http://creativecommons.org/licenses/by-nc-nd/4.0/
Sponsor: The project is partially funded from Innovate UK’s scheme “Emerging and Enabling Technologies” and Center of Doctoral Training of Embedded Intelligence (CDT-EI) funded from “Engineering and Physical Sciences Research Council” of UK.
Version: Published
DOI: 10.18178/ijmerr.7.4.379-384
URI: https://dspace.lboro.ac.uk/2134/34769
Publisher Link: https://doi.org/10.18178/ijmerr.7.4.379-384
ISSN: 2278-0149
Appears in Collections:Published Articles (Sport, Exercise and Health Sciences)
Published Articles (Computer Science)

Files associated with this item:

File Description SizeFormat
IJMERR.pdfPublished version1.38 MBAdobe PDFView/Open


SFX Query

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.