GRAPH NEURAL NETWORKS REPRESENTING PHYSICAL SYSTEMS

A graph neural network system implementing a learnable physics engine for understanding and controlling a physical system. The physical system is considered to be composed of bodies coupled by joints and is represented by static and dynamic graphs. A graph processing neural network processes an inpu...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	HADSELL, Raia Thais, SPRINGENBERG, Jost, RIEDMILLER, Martin, SANCHEZ, Alvaro, HEESS, Nicolas Manfred Otto, BATTAGLIA, Peter William, MEREL, Joshua
Format:	Patent
Sprache:	eng ; fre ; ger
Schlagworte:	CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING PHYSICS
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	HADSELL, Raia Thais SPRINGENBERG, Jost RIEDMILLER, Martin SANCHEZ, Alvaro HEESS, Nicolas Manfred Otto BATTAGLIA, Peter William MEREL, Joshua
description	A graph neural network system implementing a learnable physics engine for understanding and controlling a physical system. The physical system is considered to be composed of bodies coupled by joints and is represented by static and dynamic graphs. A graph processing neural network processes an input graph e.g. the static and dynamic graphs, to provide an output graph, e.g. a predicted dynamic graph. The graph processing neural network is differentiable and may be used for control and/or reinforcement learning. The trained graph neural network system can be applied to physical systems with similar but new graph structures (zero-shot learning).
format	Patent
fullrecord	<record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_EP3756139B1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>EP3756139B1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_EP3756139B13</originalsourceid><addsrcrecordid>eNrjZDB2D3IM8FDwcw0NcvQBUiHh_kHewQpBrgFBrsGufiGefu4KAR6RwZ7OQOngyOAQV99gHgbWtMSc4lReKM3NoODmGuLsoZtakB-fWlyQmJyal1oS7xpgbG5qZmhs6WRoTIQSAIx2J0k</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>GRAPH NEURAL NETWORKS REPRESENTING PHYSICAL SYSTEMS</title><source>esp@cenet</source><creator>HADSELL, Raia Thais ; SPRINGENBERG, Jost ; RIEDMILLER, Martin ; SANCHEZ, Alvaro ; HEESS, Nicolas Manfred Otto ; BATTAGLIA, Peter William ; MEREL, Joshua</creator><creatorcontrib>HADSELL, Raia Thais ; SPRINGENBERG, Jost ; RIEDMILLER, Martin ; SANCHEZ, Alvaro ; HEESS, Nicolas Manfred Otto ; BATTAGLIA, Peter William ; MEREL, Joshua</creatorcontrib><description>A graph neural network system implementing a learnable physics engine for understanding and controlling a physical system. The physical system is considered to be composed of bodies coupled by joints and is represented by static and dynamic graphs. A graph processing neural network processes an input graph e.g. the static and dynamic graphs, to provide an output graph, e.g. a predicted dynamic graph. The graph processing neural network is differentiable and may be used for control and/or reinforcement learning. The trained graph neural network system can be applied to physical systems with similar but new graph structures (zero-shot learning).</description><language>eng ; fre ; ger</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>2024</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240918&DB=EPODOC&CC=EP&NR=3756139B1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240918&DB=EPODOC&CC=EP&NR=3756139B1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>HADSELL, Raia Thais</creatorcontrib><creatorcontrib>SPRINGENBERG, Jost</creatorcontrib><creatorcontrib>RIEDMILLER, Martin</creatorcontrib><creatorcontrib>SANCHEZ, Alvaro</creatorcontrib><creatorcontrib>HEESS, Nicolas Manfred Otto</creatorcontrib><creatorcontrib>BATTAGLIA, Peter William</creatorcontrib><creatorcontrib>MEREL, Joshua</creatorcontrib><title>GRAPH NEURAL NETWORKS REPRESENTING PHYSICAL SYSTEMS</title><description>A graph neural network system implementing a learnable physics engine for understanding and controlling a physical system. The physical system is considered to be composed of bodies coupled by joints and is represented by static and dynamic graphs. A graph processing neural network processes an input graph e.g. the static and dynamic graphs, to provide an output graph, e.g. a predicted dynamic graph. The graph processing neural network is differentiable and may be used for control and/or reinforcement learning. The trained graph neural network system can be applied to physical systems with similar but new graph structures (zero-shot learning).</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2024</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZDB2D3IM8FDwcw0NcvQBUiHh_kHewQpBrgFBrsGufiGefu4KAR6RwZ7OQOngyOAQV99gHgbWtMSc4lReKM3NoODmGuLsoZtakB-fWlyQmJyal1oS7xpgbG5qZmhs6WRoTIQSAIx2J0k</recordid><startdate>20240918</startdate><enddate>20240918</enddate><creator>HADSELL, Raia Thais</creator><creator>SPRINGENBERG, Jost</creator><creator>RIEDMILLER, Martin</creator><creator>SANCHEZ, Alvaro</creator><creator>HEESS, Nicolas Manfred Otto</creator><creator>BATTAGLIA, Peter William</creator><creator>MEREL, Joshua</creator><scope>EVB</scope></search><sort><creationdate>20240918</creationdate><title>GRAPH NEURAL NETWORKS REPRESENTING PHYSICAL SYSTEMS</title><author>HADSELL, Raia Thais ; SPRINGENBERG, Jost ; RIEDMILLER, Martin ; SANCHEZ, Alvaro ; HEESS, Nicolas Manfred Otto ; BATTAGLIA, Peter William ; MEREL, Joshua</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_EP3756139B13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng ; fre ; ger</language><creationdate>2024</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>HADSELL, Raia Thais</creatorcontrib><creatorcontrib>SPRINGENBERG, Jost</creatorcontrib><creatorcontrib>RIEDMILLER, Martin</creatorcontrib><creatorcontrib>SANCHEZ, Alvaro</creatorcontrib><creatorcontrib>HEESS, Nicolas Manfred Otto</creatorcontrib><creatorcontrib>BATTAGLIA, Peter William</creatorcontrib><creatorcontrib>MEREL, Joshua</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>HADSELL, Raia Thais</au><au>SPRINGENBERG, Jost</au><au>RIEDMILLER, Martin</au><au>SANCHEZ, Alvaro</au><au>HEESS, Nicolas Manfred Otto</au><au>BATTAGLIA, Peter William</au><au>MEREL, Joshua</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>GRAPH NEURAL NETWORKS REPRESENTING PHYSICAL SYSTEMS</title><date>2024-09-18</date><risdate>2024</risdate><abstract>A graph neural network system implementing a learnable physics engine for understanding and controlling a physical system. The physical system is considered to be composed of bodies coupled by joints and is represented by static and dynamic graphs. A graph processing neural network processes an input graph e.g. the static and dynamic graphs, to provide an output graph, e.g. a predicted dynamic graph. The graph processing neural network is differentiable and may be used for control and/or reinforcement learning. The trained graph neural network system can be applied to physical systems with similar but new graph structures (zero-shot learning).</abstract><oa>free_for_read</oa></addata></record>
fulltext	fulltext_linktorsrc
identifier
ispartof
issn
language	eng ; fre ; ger
recordid	cdi_epo_espacenet_EP3756139B1
source	esp@cenet
subjects	CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING PHYSICS
title	GRAPH NEURAL NETWORKS REPRESENTING PHYSICAL SYSTEMS
url	https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-28T15%3A17%3A20IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=HADSELL,%20Raia%20Thais&rft.date=2024-09-18&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EEP3756139B1%3C/epo_EVB%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