{"id":"https://openalex.org/W4416749655","doi":"https://doi.org/10.1109/iros60139.2025.11247213","title":"Domain-Conditioned Scene Graphs for State-Grounded Task Planning","display_name":"Domain-Conditioned Scene Graphs for State-Grounded Task Planning","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416749655","doi":"https://doi.org/10.1109/iros60139.2025.11247213"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11247213","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247213","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/A5102741251","display_name":"Jonas Herzog","orcid":"https://orcid.org/0009-0002-1682-1500"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jonas Herzog","raw_affiliation_strings":["Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059914098","display_name":"Jiangpin Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangpin Liu","raw_affiliation_strings":["Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100372089","display_name":"Yue Wang","orcid":"https://orcid.org/0000-0003-0146-7262"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Wang","raw_affiliation_strings":["Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102741251"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37026843,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4142","last_page":"4149"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5263000130653381,"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":0.5263000130653381,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.24210000038146973,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.046300001442432404,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6434999704360962},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.6283000111579895},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.555400013923645},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5198000073432922},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4828999936580658},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4350999891757965},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.3921000063419342}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7225000262260437},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6434999704360962},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6284999847412109},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.6283000111579895},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.555400013923645},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5198000073432922},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4828999936580658},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4350999891757965},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3921000063419342},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.38190001249313354},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.35600000619888306},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.352400004863739},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.31049999594688416},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.30649998784065247},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27149999141693115},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2711000144481659},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.2709999978542328}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11247213","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247213","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":16,"referenced_works":["https://openalex.org/W2161414194","https://openalex.org/W2498525044","https://openalex.org/W3091340437","https://openalex.org/W3201868981","https://openalex.org/W3207057769","https://openalex.org/W4312732547","https://openalex.org/W4390873645","https://openalex.org/W4393160795","https://openalex.org/W4401414715","https://openalex.org/W4401415710","https://openalex.org/W4402716288","https://openalex.org/W4402952458","https://openalex.org/W4402968400","https://openalex.org/W4403888666","https://openalex.org/W4405787186","https://openalex.org/W4415800665"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"robotic":[1],"task":[2,157],"planning":[3,102,158],"frameworks":[4],"have":[5],"integrated":[6],"large":[7],"multimodal":[8],"models":[9],"(LMMs)":[10],"such":[11,19,86,104],"as":[12,79,92,105],"GPT-4o.":[13],"To":[14,61],"address":[15,62],"grounding":[16,32,45,71,119,154],"issues":[17],"of":[18,47,116,140],"models,":[20],"it":[21,93],"has":[22],"been":[23],"suggested":[24],"to":[25,97,162],"split":[26],"the":[27,43,106,122],"pipeline":[28],"into":[29],"perceptional":[30],"state":[31,44,70,100,118,153],"and":[33,156],"subsequent":[34],"state-based":[35],"planning.":[36],"As":[37],"we":[38,65],"show":[39,84],"in":[40,55,90,101],"this":[41,63],"work,":[42],"ability":[46],"LMM-based":[48,163],"approaches":[49],"is":[50,88,94,127],"still":[51],"limited":[52],"by":[53],"weaknesses":[54],"granular,":[56],"structured,":[57],"domain-specific":[58,136],"scene":[59,77,81,124],"understanding.":[60],"shortcoming,":[64],"develop":[66],"a":[67,75,98,130],"more":[68],"structured":[69],"framework":[72,120],"that":[73,85,134],"features":[74],"domain-conditioned":[76,123],"graph":[78,125],"its":[80],"representation.":[82],"We":[83,112],"representation":[87],"actionable":[89],"nature":[91],"directly":[95],"mappable":[96],"symbolic":[99],"languages":[103],"Planning":[107],"Domain":[108],"Definition":[109],"Language":[110],"(PDDL).":[111],"provide":[113],"an":[114],"instantiation":[115],"our":[117,148],"where":[121],"generation":[126],"implemented":[128],"with":[129],"lightweight":[131],"vision-language":[132],"approach":[133,149],"classifies":[135],"predicates":[137],"on":[138],"top":[139],"domain-relevant":[141],"object":[142],"detections.":[143],"Evaluated":[144],"across":[145],"three":[146],"domains,":[147],"achieves":[150],"significantly":[151],"higher":[152],"accuracy":[155],"success":[159],"rates":[160],"compared":[161],"approaches.":[164],"https://github.com/Vision-Kek/DC-SGG":[165]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-28T00:00:00"}