No Cover Image

Journal article 64 views 9 downloads

Segmentation and generalisation for writing skills transfer from humans to robots / Cinzia, Giannetti

Cognitive Computation and Systems, Volume: 1, Issue: 1, Pages: 20 - 25

Swansea University Author: Cinzia, Giannetti

Check full text

DOI (Published version): 10.1049/ccs.2018.0005

Abstract

In this study, the authors present an enhanced generalised teaching by demonstration technique for a KUKA iiwa robot. Movements are recorded from a human operator, and then the recorded data are sent to be segmented via MATLAB by using the difference method (DV). The outputted trajectories data are...

Full description

Published in: Cognitive Computation and Systems
ISSN: 2517-7567
Published: 2019
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa50754
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2019-06-07T20:57:29Z
last_indexed 2019-07-03T14:55:17Z
id cronfa50754
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2019-07-03T12:47:57.2928501</datestamp><bib-version>v2</bib-version><id>50754</id><entry>2019-06-07</entry><title>Segmentation and generalisation for writing skills transfer from humans to robots</title><swanseaauthors><author><sid>a8d947a38cb58a8d2dfe6f50cb7eb1c6</sid><ORCID>0000-0003-0339-5872</ORCID><firstname>Cinzia</firstname><surname>Giannetti</surname><name>Cinzia Giannetti</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2019-06-07</date><deptcode>EEN</deptcode><abstract>In this study, the authors present an enhanced generalised teaching by demonstration technique for a KUKA iiwa robot. Movements are recorded from a human operator, and then the recorded data are sent to be segmented via MATLAB by using the difference method (DV). The outputted trajectories data are used to model a non-linear system named dynamic movement primitive (DMP). For the purpose of learning from multiple demonstrations correctly and accurately, the Gaussian mixture model is employed for the evaluation of the DMP in order to modelling multiple trajectories by the teaching of demonstrator. Furthermore, a synthesised trajectory with smaller position errors in 3D space has been successfully generated by the usage of the Gaussian mixture regression algorithm. The proposed approach has been tested and demonstrated by performing a Chinese characters writing task with a KUKA iiwa robot.</abstract><type>Journal Article</type><journal>Cognitive Computation and Systems</journal><volume>1</volume><journalNumber>1</journalNumber><paginationStart>20</paginationStart><paginationEnd>25</paginationEnd><publisher/><issnElectronic>2517-7567</issnElectronic><keywords/><publishedDay>22</publishedDay><publishedMonth>4</publishedMonth><publishedYear>2019</publishedYear><publishedDate>2019-04-22</publishedDate><doi>10.1049/ccs.2018.0005</doi><url/><notes/><college>COLLEGE NANME</college><department>Engineering</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>EEN</DepartmentCode><institution>Swansea University</institution><lastEdited>2019-07-03T12:47:57.2928501</lastEdited><Created>2019-06-07T14:54:49.2991375</Created><path><level id="1">College of Engineering</level><level id="2">Engineering</level></path><authors><author><firstname>Chunxu</firstname><surname>Li</surname><order>1</order></author><author><firstname>Chenguang</firstname><surname>Yang</surname><order>2</order></author><author><firstname>Cinzia</firstname><surname>Giannetti</surname><orcid>0000-0003-0339-5872</orcid><order>3</order></author></authors><documents><document><filename>0050754-07062019145912.pdf</filename><originalFilename>Segmentationandgeneralisationforwriting.pdf</originalFilename><uploaded>2019-06-07T14:59:12.4870000</uploaded><type>Output</type><contentLength>2199374</contentLength><contentType>application/pdf</contentType><version>Accepted Manuscript</version><cronfaStatus>true</cronfaStatus><action/><embargoDate>2019-06-07T00:00:00.0000000</embargoDate><copyrightCorrect>false</copyrightCorrect><language>eng</language></document></documents></rfc1807>
spelling 2019-07-03T12:47:57.2928501 v2 50754 2019-06-07 Segmentation and generalisation for writing skills transfer from humans to robots a8d947a38cb58a8d2dfe6f50cb7eb1c6 0000-0003-0339-5872 Cinzia Giannetti Cinzia Giannetti true false 2019-06-07 EEN In this study, the authors present an enhanced generalised teaching by demonstration technique for a KUKA iiwa robot. Movements are recorded from a human operator, and then the recorded data are sent to be segmented via MATLAB by using the difference method (DV). The outputted trajectories data are used to model a non-linear system named dynamic movement primitive (DMP). For the purpose of learning from multiple demonstrations correctly and accurately, the Gaussian mixture model is employed for the evaluation of the DMP in order to modelling multiple trajectories by the teaching of demonstrator. Furthermore, a synthesised trajectory with smaller position errors in 3D space has been successfully generated by the usage of the Gaussian mixture regression algorithm. The proposed approach has been tested and demonstrated by performing a Chinese characters writing task with a KUKA iiwa robot. Journal Article Cognitive Computation and Systems 1 1 20 25 2517-7567 22 4 2019 2019-04-22 10.1049/ccs.2018.0005 COLLEGE NANME Engineering COLLEGE CODE EEN Swansea University 2019-07-03T12:47:57.2928501 2019-06-07T14:54:49.2991375 College of Engineering Engineering Chunxu Li 1 Chenguang Yang 2 Cinzia Giannetti 0000-0003-0339-5872 3 0050754-07062019145912.pdf Segmentationandgeneralisationforwriting.pdf 2019-06-07T14:59:12.4870000 Output 2199374 application/pdf Accepted Manuscript true 2019-06-07T00:00:00.0000000 false eng
title Segmentation and generalisation for writing skills transfer from humans to robots
spellingShingle Segmentation and generalisation for writing skills transfer from humans to robots
Cinzia, Giannetti
title_short Segmentation and generalisation for writing skills transfer from humans to robots
title_full Segmentation and generalisation for writing skills transfer from humans to robots
title_fullStr Segmentation and generalisation for writing skills transfer from humans to robots
title_full_unstemmed Segmentation and generalisation for writing skills transfer from humans to robots
title_sort Segmentation and generalisation for writing skills transfer from humans to robots
author_id_str_mv a8d947a38cb58a8d2dfe6f50cb7eb1c6
author_id_fullname_str_mv a8d947a38cb58a8d2dfe6f50cb7eb1c6_***_Cinzia, Giannetti
author Cinzia, Giannetti
format Journal article
container_title Cognitive Computation and Systems
container_volume 1
container_issue 1
container_start_page 20
publishDate 2019
institution Swansea University
issn 2517-7567
doi_str_mv 10.1049/ccs.2018.0005
college_str College of Engineering
hierarchytype
hierarchy_top_id collegeofengineering
hierarchy_top_title College of Engineering
hierarchy_parent_id collegeofengineering
hierarchy_parent_title College of Engineering
department_str Engineering{{{_:::_}}}College of Engineering{{{_:::_}}}Engineering
document_store_str 1
active_str 0
description In this study, the authors present an enhanced generalised teaching by demonstration technique for a KUKA iiwa robot. Movements are recorded from a human operator, and then the recorded data are sent to be segmented via MATLAB by using the difference method (DV). The outputted trajectories data are used to model a non-linear system named dynamic movement primitive (DMP). For the purpose of learning from multiple demonstrations correctly and accurately, the Gaussian mixture model is employed for the evaluation of the DMP in order to modelling multiple trajectories by the teaching of demonstrator. Furthermore, a synthesised trajectory with smaller position errors in 3D space has been successfully generated by the usage of the Gaussian mixture regression algorithm. The proposed approach has been tested and demonstrated by performing a Chinese characters writing task with a KUKA iiwa robot.
published_date 2019-04-22T19:12:58Z
_version_ 1652561205721563136
score 10.873003