Learning Riemannian Manifolds for Geodesic Motion Skills

For robots to work alongside humans and perform in unstructured environments, they must learn new motion skills and adapt them to unseen situations on the fly. This demands learning models that capture relevant motion patterns, while offering enough flexibility to adapt the encoded skills to new req...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Beik-Mohammadi, Hadi, Hauberg, Søren, Arvanitidis, Georgios, Neumann, Gerhard, Rozo, Leonel
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Beik-Mohammadi, Hadi
Hauberg, Søren
Arvanitidis, Georgios
Neumann, Gerhard
Rozo, Leonel
description For robots to work alongside humans and perform in unstructured environments, they must learn new motion skills and adapt them to unseen situations on the fly. This demands learning models that capture relevant motion patterns, while offering enough flexibility to adapt the encoded skills to new requirements, such as dynamic obstacle avoidance. We introduce a Riemannian manifold perspective on this problem, and propose to learn a Riemannian manifold from human demonstrations on which geodesics are natural motion skills. We realize this with a variational autoencoder (VAE) over the space of position and orientations of the robot end-effector. Geodesic motion skills let a robot plan movements from and to arbitrary points on the data manifold. They also provide a straightforward method to avoid obstacles by redefining the ambient metric in an online fashion. Moreover, geodesics naturally exploit the manifold resulting from multiple--mode tasks to design motions that were not explicitly demonstrated previously. We test our learning framework using a 7-DoF robotic manipulator, where the robot satisfactorily learns and reproduces realistic skills featuring elaborated motion patterns, avoids previously unseen obstacles, and generates novel movements in multiple-mode settings.
doi_str_mv 10.48550/arxiv.2106.04315
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2106_04315</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2106_04315</sourcerecordid><originalsourceid>FETCH-LOGICAL-a675-d5df404e6756e4c30625abbaa2df54321603e99a49a985f9944c7b0f0119d4f93</originalsourceid><addsrcrecordid>eNotj0FOwzAQRb3pArUcgBW-QMI4HrvxElVQkFJVaruPJrGNRqQ2chCC2wOF1furp_-EuFFQY2sM3FH55I-6UWBrQK3MlWi7QCVxepEHDmdKiSnJHSWOefKzjLnIbcg-zDzKXX7nnOTxladpXolFpGkO1_9citPjw2nzVHX77fPmvqvIrk3ljY8IGH62DThqsI2hYSBqfDSoG2VBB-cIHbnWROcQx_UAEZRyHqPTS3H7p71c798Kn6l89b8J_SVBfwNmlUA6</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Learning Riemannian Manifolds for Geodesic Motion Skills</title><source>arXiv.org</source><creator>Beik-Mohammadi, Hadi ; Hauberg, Søren ; Arvanitidis, Georgios ; Neumann, Gerhard ; Rozo, Leonel</creator><creatorcontrib>Beik-Mohammadi, Hadi ; Hauberg, Søren ; Arvanitidis, Georgios ; Neumann, Gerhard ; Rozo, Leonel</creatorcontrib><description>For robots to work alongside humans and perform in unstructured environments, they must learn new motion skills and adapt them to unseen situations on the fly. This demands learning models that capture relevant motion patterns, while offering enough flexibility to adapt the encoded skills to new requirements, such as dynamic obstacle avoidance. We introduce a Riemannian manifold perspective on this problem, and propose to learn a Riemannian manifold from human demonstrations on which geodesics are natural motion skills. We realize this with a variational autoencoder (VAE) over the space of position and orientations of the robot end-effector. Geodesic motion skills let a robot plan movements from and to arbitrary points on the data manifold. They also provide a straightforward method to avoid obstacles by redefining the ambient metric in an online fashion. Moreover, geodesics naturally exploit the manifold resulting from multiple--mode tasks to design motions that were not explicitly demonstrated previously. We test our learning framework using a 7-DoF robotic manipulator, where the robot satisfactorily learns and reproduces realistic skills featuring elaborated motion patterns, avoids previously unseen obstacles, and generates novel movements in multiple-mode settings.</description><identifier>DOI: 10.48550/arxiv.2106.04315</identifier><language>eng</language><subject>Computer Science - Artificial Intelligence ; Computer Science - Learning ; Computer Science - Robotics</subject><creationdate>2021-06</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2106.04315$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2106.04315$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Beik-Mohammadi, Hadi</creatorcontrib><creatorcontrib>Hauberg, Søren</creatorcontrib><creatorcontrib>Arvanitidis, Georgios</creatorcontrib><creatorcontrib>Neumann, Gerhard</creatorcontrib><creatorcontrib>Rozo, Leonel</creatorcontrib><title>Learning Riemannian Manifolds for Geodesic Motion Skills</title><description>For robots to work alongside humans and perform in unstructured environments, they must learn new motion skills and adapt them to unseen situations on the fly. This demands learning models that capture relevant motion patterns, while offering enough flexibility to adapt the encoded skills to new requirements, such as dynamic obstacle avoidance. We introduce a Riemannian manifold perspective on this problem, and propose to learn a Riemannian manifold from human demonstrations on which geodesics are natural motion skills. We realize this with a variational autoencoder (VAE) over the space of position and orientations of the robot end-effector. Geodesic motion skills let a robot plan movements from and to arbitrary points on the data manifold. They also provide a straightforward method to avoid obstacles by redefining the ambient metric in an online fashion. Moreover, geodesics naturally exploit the manifold resulting from multiple--mode tasks to design motions that were not explicitly demonstrated previously. We test our learning framework using a 7-DoF robotic manipulator, where the robot satisfactorily learns and reproduces realistic skills featuring elaborated motion patterns, avoids previously unseen obstacles, and generates novel movements in multiple-mode settings.</description><subject>Computer Science - Artificial Intelligence</subject><subject>Computer Science - Learning</subject><subject>Computer Science - Robotics</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj0FOwzAQRb3pArUcgBW-QMI4HrvxElVQkFJVaruPJrGNRqQ2chCC2wOF1furp_-EuFFQY2sM3FH55I-6UWBrQK3MlWi7QCVxepEHDmdKiSnJHSWOefKzjLnIbcg-zDzKXX7nnOTxladpXolFpGkO1_9citPjw2nzVHX77fPmvqvIrk3ljY8IGH62DThqsI2hYSBqfDSoG2VBB-cIHbnWROcQx_UAEZRyHqPTS3H7p71c798Kn6l89b8J_SVBfwNmlUA6</recordid><startdate>20210608</startdate><enddate>20210608</enddate><creator>Beik-Mohammadi, Hadi</creator><creator>Hauberg, Søren</creator><creator>Arvanitidis, Georgios</creator><creator>Neumann, Gerhard</creator><creator>Rozo, Leonel</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20210608</creationdate><title>Learning Riemannian Manifolds for Geodesic Motion Skills</title><author>Beik-Mohammadi, Hadi ; Hauberg, Søren ; Arvanitidis, Georgios ; Neumann, Gerhard ; Rozo, Leonel</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a675-d5df404e6756e4c30625abbaa2df54321603e99a49a985f9944c7b0f0119d4f93</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Computer Science - Artificial Intelligence</topic><topic>Computer Science - Learning</topic><topic>Computer Science - Robotics</topic><toplevel>online_resources</toplevel><creatorcontrib>Beik-Mohammadi, Hadi</creatorcontrib><creatorcontrib>Hauberg, Søren</creatorcontrib><creatorcontrib>Arvanitidis, Georgios</creatorcontrib><creatorcontrib>Neumann, Gerhard</creatorcontrib><creatorcontrib>Rozo, Leonel</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Beik-Mohammadi, Hadi</au><au>Hauberg, Søren</au><au>Arvanitidis, Georgios</au><au>Neumann, Gerhard</au><au>Rozo, Leonel</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Learning Riemannian Manifolds for Geodesic Motion Skills</atitle><date>2021-06-08</date><risdate>2021</risdate><abstract>For robots to work alongside humans and perform in unstructured environments, they must learn new motion skills and adapt them to unseen situations on the fly. This demands learning models that capture relevant motion patterns, while offering enough flexibility to adapt the encoded skills to new requirements, such as dynamic obstacle avoidance. We introduce a Riemannian manifold perspective on this problem, and propose to learn a Riemannian manifold from human demonstrations on which geodesics are natural motion skills. We realize this with a variational autoencoder (VAE) over the space of position and orientations of the robot end-effector. Geodesic motion skills let a robot plan movements from and to arbitrary points on the data manifold. They also provide a straightforward method to avoid obstacles by redefining the ambient metric in an online fashion. Moreover, geodesics naturally exploit the manifold resulting from multiple--mode tasks to design motions that were not explicitly demonstrated previously. We test our learning framework using a 7-DoF robotic manipulator, where the robot satisfactorily learns and reproduces realistic skills featuring elaborated motion patterns, avoids previously unseen obstacles, and generates novel movements in multiple-mode settings.</abstract><doi>10.48550/arxiv.2106.04315</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2106.04315
ispartof
issn
language eng
recordid cdi_arxiv_primary_2106_04315
source arXiv.org
subjects Computer Science - Artificial Intelligence
Computer Science - Learning
Computer Science - Robotics
title Learning Riemannian Manifolds for Geodesic Motion Skills
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-12T20%3A29%3A02IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Learning%20Riemannian%20Manifolds%20for%20Geodesic%20Motion%20Skills&rft.au=Beik-Mohammadi,%20Hadi&rft.date=2021-06-08&rft_id=info:doi/10.48550/arxiv.2106.04315&rft_dat=%3Carxiv_GOX%3E2106_04315%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true