{"id":"https://openalex.org/W4416748452","doi":"https://doi.org/10.1109/iros60139.2025.11245660","title":"DGETP: Dynamic Graph Attention Network for Embodied Task Planning","display_name":"DGETP: Dynamic Graph Attention Network for Embodied Task Planning","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416748452","doi":"https://doi.org/10.1109/iros60139.2025.11245660"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11245660","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11245660","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089639140","display_name":"Pengfei Sun","orcid":"https://orcid.org/0000-0003-2361-6767"},"institutions":[{"id":"https://openalex.org/I1456306","display_name":"North China University of Technology","ror":"https://ror.org/01nky7652","country_code":"CN","type":"education","lineage":["https://openalex.org/I1456306"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Pengfei Sun","raw_affiliation_strings":["North China University of Technology,School of Information Science and Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"North China University of Technology,School of Information Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I1456306"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038275409","display_name":"G K Wang","orcid":"https://orcid.org/0009-0000-0255-0098"},"institutions":[{"id":"https://openalex.org/I1456306","display_name":"North China University of Technology","ror":"https://ror.org/01nky7652","country_code":"CN","type":"education","lineage":["https://openalex.org/I1456306"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guiling Wang","raw_affiliation_strings":["North China University of Technology,School of Information Science and Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"North China University of Technology,School of Information Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I1456306"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059444790","display_name":"Xinli Zhang","orcid":"https://orcid.org/0000-0001-9092-9240"},"institutions":[{"id":"https://openalex.org/I1456306","display_name":"North China University of Technology","ror":"https://ror.org/01nky7652","country_code":"CN","type":"education","lineage":["https://openalex.org/I1456306"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinli Zhang","raw_affiliation_strings":["North China University of Technology,School of Information Science and Technology,Beijing,China"],"affiliations":[{"raw_affiliation_string":"North China University of Technology,School of Information Science and Technology,Beijing,China","institution_ids":["https://openalex.org/I1456306"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040342340","display_name":"Jian Yu","orcid":"https://orcid.org/0000-0002-2257-7279"},"institutions":[{"id":"https://openalex.org/I39854758","display_name":"Auckland University of Technology","ror":"https://ror.org/01zvqw119","country_code":"NZ","type":"education","lineage":["https://openalex.org/I39854758"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Jian Yu","raw_affiliation_strings":["Auckland University of Technology,Department of Computer Science,Auckland,New Zealand"],"affiliations":[{"raw_affiliation_string":"Auckland University of Technology,Department of Computer Science,Auckland,New Zealand","institution_ids":["https://openalex.org/I39854758"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5089639140"],"corresponding_institution_ids":["https://openalex.org/I1456306"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.36864342,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"777","last_page":"784"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.3594000041484833,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.3594000041484833,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.12950000166893005,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11431","display_name":"Action Observation and Synchronization","score":0.10530000180006027,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.6804999709129333},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5644000172615051},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5527999997138977},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5356000065803528},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.49079999327659607},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4659999907016754},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4129999876022339},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.39239999651908875},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.38199999928474426}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7293999791145325},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.6804999709129333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5701000094413757},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5644000172615051},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5527999997138977},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5356000065803528},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.49079999327659607},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4659999907016754},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4129999876022339},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.39239999651908875},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.38199999928474426},{"id":"https://openalex.org/C13540734","wikidata":"https://www.wikidata.org/wiki/Q5318996","display_name":"Dynamic network analysis","level":2,"score":0.37279999256134033},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3668000102043152},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.36169999837875366},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35929998755455017},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.3521000146865845},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3319000005722046},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.30979999899864197},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.30239999294281006},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2865999937057495},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.28119999170303345},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.2759999930858612},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.26159998774528503},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.2535000145435333}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11245660","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11245660","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2962991900","https://openalex.org/W3034758614","https://openalex.org/W3183042936","https://openalex.org/W3207057769","https://openalex.org/W3207210614","https://openalex.org/W4207072548","https://openalex.org/W4226236972","https://openalex.org/W4312732547","https://openalex.org/W4385489525","https://openalex.org/W4385570594","https://openalex.org/W4389667254","https://openalex.org/W4392866655","https://openalex.org/W4405787186"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,29,36,97,102,193,205],"development":[2],"of":[3,101,116,204],"embodied":[4,49],"intelligence,":[5],"many":[6],"studies":[7],"have":[8],"made":[9],"progress":[10],"by":[11,87,168],"incorporating":[12],"scene":[13,66],"graphs":[14,71],"and":[15,35,45,69,91,119,132,139,150,174],"GNN":[16],"into":[17],"task":[18,166,207],"planning.":[19],"However,":[20],"most":[21,203],"methods":[22],"still":[23],"face":[24],"challenges":[25],"in":[26,48,111,171,177],"fully":[27],"capturing":[28],"sequential":[30],"relationships":[31],"between":[32,130],"agent":[33],"actions":[34,118,134],"environment,":[37],"making":[38],"it":[39],"difficult":[40],"to":[41,64,95,121,181],"handle":[42],"dynamic":[43,73,98],"changes":[44],"complexity":[46,142],"inherent":[47],"tasks.":[50],"This":[51],"paper":[52],"proposes":[53],"a":[54,80,144],"Dynamic":[55,82],"Graph":[56,83],"Attention":[57,84],"Network":[58],"for":[59,72],"Embodied":[60],"Task":[61],"Planning":[62],"(DGETP)":[63],"process":[65],"graph":[67],"sequences":[68,115],"robot":[70],"environment":[74,195],"perception.":[75],"In":[76,184],"DGETP,":[77],"we":[78],"design":[79],"Hierarchical":[81],"network":[85],"(H-DGAT)":[86],"employing":[88],"both":[89],"structural":[90],"temporal":[92,128],"attention":[93],"mechanisms":[94],"model":[96],"evolution":[99],"feature":[100,159],"scene.":[103],"A":[104],"Dual-branch":[105],"Action-object":[106],"Predictor":[107],"(DAP)":[108],"is":[109],"proposed":[110],"DGETP":[112,164,187,198],"through":[113,135,157],"introducing":[114],"previous":[117],"objects":[120],"efficiently":[122],"aggregate":[123],"historical":[124],"information.":[125],"DAP":[126],"captures":[127],"dependencies":[129],"past":[131],"future":[133],"explicit":[136],"sequence":[137],"modeling,":[138],"reduces":[140],"prediction":[141,152],"via":[143],"dual-branch":[145],"architecture":[146],"that":[147,163,197],"separates":[148],"action":[149],"object":[151],"while":[153],"preserving":[154],"their":[155],"correlations":[156],"targeted":[158],"fusion.":[160],"Experiments":[161],"show":[162],"improves":[165],"accuracy":[167],"over":[169,175],"30%":[170],"seen":[172],"scenes":[173,179],"15%":[176],"unseen":[178],"compared":[180],"other":[182],"baselines.":[183],"complex":[185],"scenes,":[186],"demonstrates":[188],"strong":[189],"generalization":[190],"ability.":[191],"Finally,":[192],"simulation":[194],"indicates":[196],"achieves":[199],"more":[200],"goals":[201],"than":[202],"advanced":[206],"planning":[208],"method.":[209]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-28T00:00:00"}