{"id":"https://openalex.org/W7138009379","doi":"https://doi.org/10.1609/aaai.v40i22.38896","title":"GraphCoT-VLA: A 3D Spatial-Aware Reasoning Vision-Language-Action Model for Robotic Manipulation with Ambiguous Instructions","display_name":"GraphCoT-VLA: A 3D Spatial-Aware Reasoning Vision-Language-Action Model for Robotic Manipulation with Ambiguous Instructions","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138009379","doi":"https://doi.org/10.1609/aaai.v40i22.38896"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i22.38896","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i22.38896","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i22.38896","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005127901","display_name":"Helong Huang","orcid":"https://orcid.org/0009-0002-5134-3911"},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Helong Huang","raw_affiliation_strings":["Huawei Technologies Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Ltd","institution_ids":["https://openalex.org/I4210160618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008865302","display_name":"Min Cen","orcid":"https://orcid.org/0000-0003-1253-5646"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Cen","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129646268","display_name":"Kai Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kai Tan","raw_affiliation_strings":["Huawei Technologies Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Ltd","institution_ids":["https://openalex.org/I4210160618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129649178","display_name":"Xingyue Quan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210146936","display_name":"Huawei Technologies (United States)","ror":"https://ror.org/03jyqk712","country_code":"US","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210146936"]},{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Xingyue Quan","raw_affiliation_strings":["Huawei Technologies Ltd.c"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Ltd.c","institution_ids":["https://openalex.org/I4210146936","https://openalex.org/I4210160618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129714562","display_name":"Guowei Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Guowei Huang","raw_affiliation_strings":["Huawei Technologies Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Ltd","institution_ids":["https://openalex.org/I4210160618"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129650162","display_name":"Hong Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Zhang","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"22","first_page":"18324","last_page":"18332"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9039000272750854,"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":0.9039000272750854,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.019500000402331352,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.006899999920278788,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6985999941825867},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6118999719619751},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5002999901771545},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4855000078678131},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4713999927043915},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.44690001010894775},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4345000088214874},{"id":"https://openalex.org/keywords/cognitive-robotics","display_name":"Cognitive robotics","score":0.4043000042438507}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7511000037193298},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6985999941825867},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6363000273704529},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6118999719619751},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5163999795913696},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5002999901771545},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4855000078678131},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4713999927043915},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.44690001010894775},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4345000088214874},{"id":"https://openalex.org/C192327766","wikidata":"https://www.wikidata.org/wiki/Q1038799","display_name":"Cognitive robotics","level":3,"score":0.4043000042438507},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3896999955177307},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.3481999933719635},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3465999960899353},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3075999915599823},{"id":"https://openalex.org/C17511633","wikidata":"https://www.wikidata.org/wiki/Q830694","display_name":"SMT placement equipment","level":3,"score":0.2957000136375427},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2736999988555908},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C2775960376","wikidata":"https://www.wikidata.org/wiki/Q1435859","display_name":"Grippers","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C2985527887","wikidata":"https://www.wikidata.org/wiki/Q1587588","display_name":"Robot manipulator","level":3,"score":0.25949999690055847},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.25029999017715454},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i22.38896","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i22.38896","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i22.38896","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i22.38896","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-language-action":[0],"models":[1,14],"have":[2],"emerged":[3],"as":[4],"a":[5,77,106,142],"crucial":[6],"paradigm":[7],"in":[8,18,126,166,180],"robotic":[9,157],"manipulation.":[10],"However,":[11],"existing":[12,164],"VLA":[13],"exhibit":[15],"notable":[16],"limitations":[17],"handling":[19],"ambiguous":[20,69],"language":[21],"instructions":[22,70],"and":[23,47,71,87,92,100,120,135,172,178,183],"unknown":[24],"environmental":[25],"states.":[26],"Furthermore,":[27],"their":[28,137],"perception":[29],"is":[30],"largely":[31],"constrained":[32],"to":[33,40,67,132,147],"static":[34],"two-dimensional":[35],"observations,":[36],"lacking":[37],"the":[38,45,64,114,121,130],"capability":[39],"model":[41,131],"three-dimensional":[42],"interactions":[43],"between":[44,124],"robot":[46,101,118],"its":[48],"environment.":[49],"To":[50,62],"address":[51],"these":[52],"challenges,":[53],"this":[54],"paper":[55],"proposes":[56],"GraphCoT-VLA,":[57],"an":[58],"efficient":[59,149],"end-to-end":[60],"model.":[61],"enhance":[63],"model's":[65],"ability":[66],"interpret":[68],"improve":[72],"task":[73,85,90,169],"planning,":[74,88],"we":[75,104],"design":[76],"structured":[78],"Chain-of-Thought":[79],"reasoning":[80,95,145],"module":[81],"that":[82,160],"integrates":[83,141],"high-level":[84],"understanding":[86],"failed":[89],"feedback,":[91],"low-level":[93],"imaginative":[94],"about":[96],"future":[97],"object":[98],"positions":[99],"actions.":[102],"Additionally,":[103],"construct":[105],"real-time":[107],"updatable":[108],"3D":[109,127],"Pose-Object":[110],"graph,":[111],"which":[112],"captures":[113],"spatial":[115],"configuration":[116],"of":[117,168],"joints":[119],"topological":[122],"relationships":[123],"objects":[125],"space,":[128],"enabling":[129],"better":[133],"understand":[134],"manipulate":[136],"interactions.":[138],"We":[139],"further":[140],"dropout":[143],"hybrid":[144],"strategy":[146],"achieve":[148],"control":[150],"outputs.":[151],"Experimental":[152],"results":[153],"across":[154],"multiple":[155],"real-world":[156],"tasks":[158],"demonstrate":[159],"GraphCoT-VLA":[161],"significantly":[162],"outperforms":[163],"methods":[165],"terms":[167],"success":[170],"rate":[171],"response":[173],"speed,":[174],"exhibiting":[175],"strong":[176],"generalization":[177],"robustness":[179],"open":[181],"environments":[182],"under":[184],"uncertain":[185],"instructions.":[186]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-03-18T00:00:00"}
