Motion Adaptation Based on Learning the Manifold of Task and Dynamic Movement Primitive Parameters

Dynamic movement primitives (DMP) are motion building blocks suitable for real-world tasks. We suggest a methodology for learning the manifold of task and DMP parameters, which facilitates runtime adaptation to changes in task requirements while ensuring predictable and robust performance. For effic...

Full description

Saved in:
Bibliographic Details
Published in:Robotica 2021-07, Vol.39 (7), p.1299-1315
Main Authors: Cohen, Yosef, Bar-Shira, Or, Berman, Sigal
Format: Article
Language:English
Subjects:
Adaptation
Artificial neural networks
Kernels
Machine learning
Manifolds (mathematics)
Movement
Parameters
Principal components analysis
Teaching methods
Throwing
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c360t-91ddd778f58182a2d891e2e0857fb0f3229d9b9b541c2d33d7e29b9b1448c7cd3
cites cdi_FETCH-LOGICAL-c360t-91ddd778f58182a2d891e2e0857fb0f3229d9b9b541c2d33d7e29b9b1448c7cd3
container_end_page 1315
container_issue 7
container_start_page 1299
container_title Robotica
container_volume 39
creator Cohen, Yosef
Bar-Shira, Or
Berman, Sigal
description Dynamic movement primitives (DMP) are motion building blocks suitable for real-world tasks. We suggest a methodology for learning the manifold of task and DMP parameters, which facilitates runtime adaptation to changes in task requirements while ensuring predictable and robust performance. For efficient learning, the parameter space is analyzed using principal component analysis and locally linear embedding. Two manifold learning methods: kernel estimation and deep neural networks, are investigated for a ball throwing task in simulation and in a physical environment. Low runtime estimation errors are obtained for both learning methods, with an advantage to kernel estimation when data sets are small.
doi_str_mv 10.1017/S0263574720001186
format article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2537907901</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><cupid>10_1017_S0263574720001186</cupid><sourcerecordid>2537907901</sourcerecordid><originalsourceid>FETCH-LOGICAL-c360t-91ddd778f58182a2d891e2e0857fb0f3229d9b9b541c2d33d7e29b9b1448c7cd3</originalsourceid><addsrcrecordid>eNp1UN9LwzAQDqLgnP4BvgV8ruaStkkf53QqbDhwPpe0SWfmms4kG-y_N3UDH0Q4uDu-H3d8CF0DuQUC_O6N0JxlPOWUEAIg8hM0gDQvEpHn4hQNejjp8XN04f0qchikfICqWRdMZ_FIyU2QP-O99FrhOEy1dNbYJQ4fGs-kNU23jkCDF9J_YmkVfthb2Zoaz7qdbrUNeO5Ma4LZaTyXTrY6aOcv0Vkj115fHfsQvU8eF-PnZPr69DIeTZOa5SQkBSilOBdNJkBQSZUoQFNNRMabijSM0kIVVVFlKdRUMaa4pv0OaSpqXis2RDcH343rvrbah3LVbZ2NJ0uaMV6QWBBZcGDVrvPe6abcxJ-l25dAyj7K8k-UUcOOGtlWzqil_rX-X_UN2hB1Kg</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2537907901</pqid></control><display><type>article</type><title>Motion Adaptation Based on Learning the Manifold of Task and Dynamic Movement Primitive Parameters</title><source>Cambridge Journals Online</source><creator>Cohen, Yosef ; Bar-Shira, Or ; Berman, Sigal</creator><creatorcontrib>Cohen, Yosef ; Bar-Shira, Or ; Berman, Sigal</creatorcontrib><description>Dynamic movement primitives (DMP) are motion building blocks suitable for real-world tasks. We suggest a methodology for learning the manifold of task and DMP parameters, which facilitates runtime adaptation to changes in task requirements while ensuring predictable and robust performance. For efficient learning, the parameter space is analyzed using principal component analysis and locally linear embedding. Two manifold learning methods: kernel estimation and deep neural networks, are investigated for a ball throwing task in simulation and in a physical environment. Low runtime estimation errors are obtained for both learning methods, with an advantage to kernel estimation when data sets are small.</description><identifier>ISSN: 0263-5747</identifier><identifier>EISSN: 1469-8668</identifier><identifier>DOI: 10.1017/S0263574720001186</identifier><language>eng</language><publisher>Cambridge, UK: Cambridge University Press</publisher><subject>Adaptation ; Artificial neural networks ; Kernels ; Machine learning ; Manifolds (mathematics) ; Movement ; Parameters ; Principal components analysis ; Teaching methods ; Throwing</subject><ispartof>Robotica, 2021-07, Vol.39 (7), p.1299-1315</ispartof><rights>The Author(s), 2020. Published by Cambridge University Press</rights><rights>The Author(s), 2020. Published by Cambridge University Press. This is an Open Access article, distributed under the terms of the Creative Commons Attribution licence (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted re-use, distribution, and reproduction in any medium, provided the original work is properly cited. Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the associated terms available at: https://uk.sagepub.com/en-gb/eur/reusing-open-access-and-sage-choice-content</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c360t-91ddd778f58182a2d891e2e0857fb0f3229d9b9b541c2d33d7e29b9b1448c7cd3</citedby><cites>FETCH-LOGICAL-c360t-91ddd778f58182a2d891e2e0857fb0f3229d9b9b541c2d33d7e29b9b1448c7cd3</cites><orcidid>0000-0001-7717-7259</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.cambridge.org/core/product/identifier/S0263574720001186/type/journal_article$$EHTML$$P50$$Gcambridge$$Hfree_for_read</linktohtml><link.rule.ids>314,780,784,27924,27925,72832</link.rule.ids></links><search><creatorcontrib>Cohen, Yosef</creatorcontrib><creatorcontrib>Bar-Shira, Or</creatorcontrib><creatorcontrib>Berman, Sigal</creatorcontrib><title>Motion Adaptation Based on Learning the Manifold of Task and Dynamic Movement Primitive Parameters</title><title>Robotica</title><addtitle>Robotica</addtitle><description>Dynamic movement primitives (DMP) are motion building blocks suitable for real-world tasks. We suggest a methodology for learning the manifold of task and DMP parameters, which facilitates runtime adaptation to changes in task requirements while ensuring predictable and robust performance. For efficient learning, the parameter space is analyzed using principal component analysis and locally linear embedding. Two manifold learning methods: kernel estimation and deep neural networks, are investigated for a ball throwing task in simulation and in a physical environment. Low runtime estimation errors are obtained for both learning methods, with an advantage to kernel estimation when data sets are small.</description><subject>Adaptation</subject><subject>Artificial neural networks</subject><subject>Kernels</subject><subject>Machine learning</subject><subject>Manifolds (mathematics)</subject><subject>Movement</subject><subject>Parameters</subject><subject>Principal components analysis</subject><subject>Teaching methods</subject><subject>Throwing</subject><issn>0263-5747</issn><issn>1469-8668</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><recordid>eNp1UN9LwzAQDqLgnP4BvgV8ruaStkkf53QqbDhwPpe0SWfmms4kG-y_N3UDH0Q4uDu-H3d8CF0DuQUC_O6N0JxlPOWUEAIg8hM0gDQvEpHn4hQNejjp8XN04f0qchikfICqWRdMZ_FIyU2QP-O99FrhOEy1dNbYJQ4fGs-kNU23jkCDF9J_YmkVfthb2Zoaz7qdbrUNeO5Ma4LZaTyXTrY6aOcv0Vkj115fHfsQvU8eF-PnZPr69DIeTZOa5SQkBSilOBdNJkBQSZUoQFNNRMabijSM0kIVVVFlKdRUMaa4pv0OaSpqXis2RDcH343rvrbah3LVbZ2NJ0uaMV6QWBBZcGDVrvPe6abcxJ-l25dAyj7K8k-UUcOOGtlWzqil_rX-X_UN2hB1Kg</recordid><startdate>202107</startdate><enddate>202107</enddate><creator>Cohen, Yosef</creator><creator>Bar-Shira, Or</creator><creator>Berman, Sigal</creator><general>Cambridge University Press</general><scope>IKXGN</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>3V.</scope><scope>7SC</scope><scope>7SP</scope><scope>7TB</scope><scope>7XB</scope><scope>8AL</scope><scope>8FD</scope><scope>8FE</scope><scope>8FG</scope><scope>8FK</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>ARAPS</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>F28</scope><scope>FR3</scope><scope>GNUQQ</scope><scope>HCIFZ</scope><scope>JQ2</scope><scope>K7-</scope><scope>L6V</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>M0N</scope><scope>M7S</scope><scope>P5Z</scope><scope>P62</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PTHSS</scope><scope>Q9U</scope><orcidid>https://orcid.org/0000-0001-7717-7259</orcidid></search><sort><creationdate>202107</creationdate><title>Motion Adaptation Based on Learning the Manifold of Task and Dynamic Movement Primitive Parameters</title><author>Cohen, Yosef ; Bar-Shira, Or ; Berman, Sigal</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c360t-91ddd778f58182a2d891e2e0857fb0f3229d9b9b541c2d33d7e29b9b1448c7cd3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Adaptation</topic><topic>Artificial neural networks</topic><topic>Kernels</topic><topic>Machine learning</topic><topic>Manifolds (mathematics)</topic><topic>Movement</topic><topic>Parameters</topic><topic>Principal components analysis</topic><topic>Teaching methods</topic><topic>Throwing</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Cohen, Yosef</creatorcontrib><creatorcontrib>Bar-Shira, Or</creatorcontrib><creatorcontrib>Berman, Sigal</creatorcontrib><collection>CUP_剑桥大学出版社OA刊</collection><collection>CrossRef</collection><collection>ProQuest Central (Corporate)</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics &amp; Communications Abstracts</collection><collection>Mechanical &amp; Transportation Engineering Abstracts</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>Computing Database (Alumni Edition)</collection><collection>Technology Research Database</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>Advanced Technologies &amp; Aerospace Collection</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</collection><collection>ANTE: Abstracts in New Technology &amp; Engineering</collection><collection>Engineering Research Database</collection><collection>ProQuest Central Student</collection><collection>SciTech Premium Collection (Proquest) (PQ_SDU_P3)</collection><collection>ProQuest Computer Science Collection</collection><collection>Computer Science Database</collection><collection>ProQuest Engineering Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts – Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>Computing Database</collection><collection>Engineering Database</collection><collection>ProQuest Advanced Technologies &amp; Aerospace Database</collection><collection>ProQuest Advanced Technologies &amp; Aerospace Collection</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>Engineering Collection</collection><collection>ProQuest Central Basic</collection><jtitle>Robotica</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Cohen, Yosef</au><au>Bar-Shira, Or</au><au>Berman, Sigal</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Motion Adaptation Based on Learning the Manifold of Task and Dynamic Movement Primitive Parameters</atitle><jtitle>Robotica</jtitle><addtitle>Robotica</addtitle><date>2021-07</date><risdate>2021</risdate><volume>39</volume><issue>7</issue><spage>1299</spage><epage>1315</epage><pages>1299-1315</pages><issn>0263-5747</issn><eissn>1469-8668</eissn><abstract>Dynamic movement primitives (DMP) are motion building blocks suitable for real-world tasks. We suggest a methodology for learning the manifold of task and DMP parameters, which facilitates runtime adaptation to changes in task requirements while ensuring predictable and robust performance. For efficient learning, the parameter space is analyzed using principal component analysis and locally linear embedding. Two manifold learning methods: kernel estimation and deep neural networks, are investigated for a ball throwing task in simulation and in a physical environment. Low runtime estimation errors are obtained for both learning methods, with an advantage to kernel estimation when data sets are small.</abstract><cop>Cambridge, UK</cop><pub>Cambridge University Press</pub><doi>10.1017/S0263574720001186</doi><tpages>17</tpages><orcidid>https://orcid.org/0000-0001-7717-7259</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 0263-5747
ispartof Robotica, 2021-07, Vol.39 (7), p.1299-1315
issn 0263-5747
1469-8668
language eng
recordid cdi_proquest_journals_2537907901
source Cambridge Journals Online
subjects Adaptation
Artificial neural networks
Kernels
Machine learning
Manifolds (mathematics)
Movement
Parameters
Principal components analysis
Teaching methods
Throwing
title Motion Adaptation Based on Learning the Manifold of Task and Dynamic Movement Primitive Parameters
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-07T15%3A11%3A06IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Motion%20Adaptation%20Based%20on%20Learning%20the%20Manifold%20of%20Task%20and%20Dynamic%20Movement%20Primitive%20Parameters&rft.jtitle=Robotica&rft.au=Cohen,%20Yosef&rft.date=2021-07&rft.volume=39&rft.issue=7&rft.spage=1299&rft.epage=1315&rft.pages=1299-1315&rft.issn=0263-5747&rft.eissn=1469-8668&rft_id=info:doi/10.1017/S0263574720001186&rft_dat=%3Cproquest_cross%3E2537907901%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c360t-91ddd778f58182a2d891e2e0857fb0f3229d9b9b541c2d33d7e29b9b1448c7cd3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2537907901&rft_id=info:pmid/&rft_cupid=10_1017_S0263574720001186&rfr_iscdi=true