{"id":"https://openalex.org/W7138156399","doi":"https://doi.org/10.1609/aaai.v40i22.38947","title":"Grounding Actions in Camera Space: Observation-Centric Vision-Language-Action Policy","display_name":"Grounding Actions in Camera Space: Observation-Centric Vision-Language-Action Policy","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138156399","doi":"https://doi.org/10.1609/aaai.v40i22.38947"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i22.38947","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i22.38947","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.v40i22.38947","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129690811","display_name":"Tianyi Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianyi Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129664535","display_name":"Haonan Duan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haonan Duan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114337935","display_name":"Haoran Hao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haoran Hao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129656005","display_name":"Yu Qiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Qiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129694053","display_name":"Jifeng Dai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jifeng Dai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129733807","display_name":"Zhi Hou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhi Hou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.2175772,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"22","first_page":"18782","last_page":"18790"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.3483999967575073,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.3483999967575073,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.29440000653266907,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.061000000685453415,"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/task","display_name":"Task (project management)","score":0.6419000029563904},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5498999953269958},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.532800018787384},{"id":"https://openalex.org/keywords/base","display_name":"Base (topology)","score":0.48730000853538513},{"id":"https://openalex.org/keywords/resilience","display_name":"Resilience (materials science)","score":0.4562999904155731},{"id":"https://openalex.org/keywords/coordinate-system","display_name":"Coordinate system","score":0.4458000063896179},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.43630000948905945}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6434000134468079},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6419000029563904},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6406000256538391},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5913000106811523},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5498999953269958},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.532800018787384},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.48730000853538513},{"id":"https://openalex.org/C2779585090","wikidata":"https://www.wikidata.org/wiki/Q3457762","display_name":"Resilience (materials science)","level":2,"score":0.4562999904155731},{"id":"https://openalex.org/C80551277","wikidata":"https://www.wikidata.org/wiki/Q11210","display_name":"Coordinate system","level":2,"score":0.4458000063896179},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.43630000948905945},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.40860000252723694},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3628000020980835},{"id":"https://openalex.org/C110898773","wikidata":"https://www.wikidata.org/wiki/Q2933935","display_name":"Camera resectioning","level":2,"score":0.35089999437332153},{"id":"https://openalex.org/C94816000","wikidata":"https://www.wikidata.org/wiki/Q5026006","display_name":"Camera auto-calibration","level":3,"score":0.34299999475479126},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33230000734329224},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3125999867916107},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3107999861240387},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27880001068115234}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i22.38947","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i22.38947","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.v40i22.38947","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i22.38947","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],"(VLA)":[1],"models":[2,30],"frequently":[3],"encounter":[4],"challenges":[5],"in":[6,42,61],"generalizing":[7],"to":[8,12,109],"real-world":[9,133],"environments":[10],"due":[11],"inherent":[13],"discrepancies":[14],"between":[15,101],"observation":[16,64],"and":[17,103,132,146],"action":[18,58],"spaces.":[19],"Although":[20],"training":[21],"data":[22],"are":[23],"collected":[24],"from":[25,76],"diverse":[26],"camera":[27,63,84,110],"perspectives,":[28],"the":[29,36,51,62,67,77,83],"typically":[31],"predict":[32],"end-effector":[33,74],"poses":[34,75],"within":[35],"robot":[37,78],"base":[38,79],"coordinate":[39,80,85],"frame,":[40],"resulting":[41],"spatial":[43],"inconsistencies.":[44],"To":[45],"mitigate":[46],"this":[47],"limitation,":[48],"we":[49],"introduce":[50],"Observation-Centric":[52],"VLA":[53,121],"(OC-VLA)":[54],"framework,":[55],"which":[56],"grounds":[57],"predictions":[59],"directly":[60],"space.":[65],"Leveraging":[66],"camera\u2019s":[68],"extrinsic":[69],"calibration":[70],"matrix,":[71],"OC-VLA":[72,139],"transforms":[73],"system":[81],"into":[82],"system,":[86],"thereby":[87],"unifying":[88],"prediction":[89],"targets":[90],"across":[91],"heterogeneous":[92],"viewpoints.":[93],"This":[94],"lightweight,":[95],"plug-and-play":[96],"strategy":[97],"ensures":[98],"robust":[99],"alignment":[100],"perception":[102],"action,":[104],"substantially":[105],"improving":[106],"model":[107],"resilience":[108],"viewpoint":[111],"variations.":[112],"The":[113],"proposed":[114],"approach":[115],"is":[116],"readily":[117],"compatible":[118],"with":[119],"existing":[120],"architectures,":[122],"requiring":[123],"no":[124],"substantial":[125],"modifications.":[126],"Comprehensive":[127],"evaluations":[128],"on":[129],"both":[130],"simulated":[131],"robotic":[134],"manipulation":[135],"tasks":[136],"demonstrate":[137],"that":[138],"accelerates":[140],"convergence,":[141],"enhances":[142],"task":[143],"success":[144],"rates,":[145],"improves":[147],"cross-view":[148],"generalization.":[149]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-03-18T00:00:00"}
