{"id":"https://openalex.org/W4416750350","doi":"https://doi.org/10.1109/iros60139.2025.11246107","title":"AVP Scene Graph: Hierarchical Visual Language Mapping and Navigation for Autonomous Valet Parking","display_name":"AVP Scene Graph: Hierarchical Visual Language Mapping and Navigation for Autonomous Valet Parking","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416750350","doi":"https://doi.org/10.1109/iros60139.2025.11246107"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246107","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246107","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/A5025697219","display_name":"Xiangru Mu","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiangru Mu","raw_affiliation_strings":["Shanghai Jiao Tong University,Global Institute of Future Technology,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Global Institute of Future Technology,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006262240","display_name":"F. Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fengyi Chen","raw_affiliation_strings":["Shanghai Jiao Tong University,Global Institute of Future Technology,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Global Institute of Future Technology,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089903460","display_name":"Runhan Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Runhan Wang","raw_affiliation_strings":["Shanghai Jiao Tong University,Global Institute of Future Technology,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Global Institute of Future Technology,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100429236","display_name":"Siyuan Chen","orcid":"https://orcid.org/0000-0002-5931-5950"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyuan Chen","raw_affiliation_strings":["Shanghai Jiao Tong University,Global Institute of Future Technology,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Global Institute of Future Technology,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078289638","display_name":"Jiyuan Cai","orcid":"https://orcid.org/0000-0001-7092-7504"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiyuan Cai","raw_affiliation_strings":["Shanghai Jiao Tong University,Global Institute of Future Technology,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Global Institute of Future Technology,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100301492","display_name":"Jia Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Cai","raw_affiliation_strings":["Shanghai Jiao Tong University,Global Institute of Future Technology,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Global Institute of Future Technology,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009256880","display_name":"Ming Yang","orcid":"https://orcid.org/0000-0002-8679-9137"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Yang","raw_affiliation_strings":["Shanghai Jiao Tong University,Global Institute of Future Technology,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Global Institute of Future Technology,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082261032","display_name":"Tong Qin","orcid":"https://orcid.org/0000-0002-0994-9816"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Qin","raw_affiliation_strings":["Shanghai Jiao Tong University,Global Institute of Future Technology,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Global Institute of Future Technology,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5025697219"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38739094,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4535","last_page":"4542"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12546","display_name":"Smart Parking Systems Research","score":0.4399000108242035,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"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/T12546","display_name":"Smart Parking Systems Research","score":0.4399000108242035,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"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":0.38429999351501465,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.041099999099969864,"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/graph","display_name":"Graph","score":0.525600016117096},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.423799991607666},{"id":"https://openalex.org/keywords/navigation-system","display_name":"Navigation system","score":0.4185999929904938},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4018000066280365},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.38690000772476196},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.32989999651908875},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.3260999917984009},{"id":"https://openalex.org/keywords/turn-by-turn-navigation","display_name":"Turn-by-turn navigation","score":0.32429999113082886}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7265999913215637},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5591999888420105},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.525600016117096},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4779999852180481},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.423799991607666},{"id":"https://openalex.org/C2777891301","wikidata":"https://www.wikidata.org/wiki/Q3475123","display_name":"Navigation system","level":2,"score":0.4185999929904938},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4018000066280365},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.38690000772476196},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.32989999651908875},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3260999917984009},{"id":"https://openalex.org/C43472768","wikidata":"https://www.wikidata.org/wiki/Q7855620","display_name":"Turn-by-turn navigation","level":5,"score":0.32429999113082886},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.31850001215934753},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.30880001187324524},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2944999933242798},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.28130000829696655},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.2786000072956085},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C26990112","wikidata":"https://www.wikidata.org/wiki/Q6887224","display_name":"Mobile robot navigation","level":5,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246107","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246107","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/F4320309612","display_name":"Natural Science Foundation of Shanghai","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2070405474","https://openalex.org/W2411093439","https://openalex.org/W2938818630","https://openalex.org/W2963800628","https://openalex.org/W2970641574","https://openalex.org/W2990129662","https://openalex.org/W3035154952","https://openalex.org/W3131641033","https://openalex.org/W3179351458","https://openalex.org/W3183042936","https://openalex.org/W3196904463","https://openalex.org/W4200139055","https://openalex.org/W4283332944","https://openalex.org/W4286285589","https://openalex.org/W4312229467","https://openalex.org/W4360823144","https://openalex.org/W4382725382","https://openalex.org/W4383108296","https://openalex.org/W4383108458","https://openalex.org/W4390874160","https://openalex.org/W4399177289","https://openalex.org/W4401414715","https://openalex.org/W4401415207","https://openalex.org/W4401415891","https://openalex.org/W4401691722","https://openalex.org/W4402354022","https://openalex.org/W4402917081","https://openalex.org/W4404612589","https://openalex.org/W4404612908"],"related_works":[],"abstract_inverted_index":{"Autonomous":[0],"valet":[1],"parking":[2,17],"(AVP)":[3],"aims":[4],"to":[5,11,27,36,147],"help":[6],"the":[7,12,16,20,29,37,42,67,121,126,148,154,163,178,182,202,212],"human":[8,103],"drivers":[9],"navigate":[10],"desired":[13],"location":[14],"in":[15,72],"lot.":[18],"Currently,":[19],"AVP":[21,50,71,81,95,198,208],"task":[22],"is":[23,166],"not":[24],"flexible":[25,68],"enough":[26],"perform":[28,206],"open-vocabulary":[30,94,139,207],"navigation":[31,91,100,118,180,183],"tasks":[32,199,209],"such":[33],"as":[34],"\"navigate":[35],"exit\"":[38],"or":[39],"\"park":[40],"near":[41],"elevator\".":[43],"The":[44],"widely":[45],"used":[46],"map":[47],"formats":[48],"for":[49,93],"like":[51],"vectorized":[52],"maps":[53],"have":[54],"some":[55],"limitations":[56],"including":[57],"limited":[58],"semantics,":[59],"high":[60],"cost":[61],"and":[62,90,115,130,144,174],"poor":[63],"human-machine":[64],"interaction,":[65],"restricting":[66],"application":[69],"of":[70,108,150,170],"complex":[73],"scenarios.":[74],"To":[75],"address":[76],"these":[77],"problems,":[78],"we":[79,136],"propose":[80],"Scene":[82],"Graph":[83],"(AVP-SG),":[84],"a":[85,111,116],"hierarchical":[86],"visual":[87],"language":[88],"mapping":[89,113,122],"framework":[92,106],"tasks,":[96],"which":[97],"enables":[98],"autonomous":[99],"from":[101,142],"multi-modal":[102],"instructions.":[104],"Our":[105],"consists":[107],"two":[109],"parts:":[110],"bottom-up":[112,155],"module":[114],"top-down":[117,179],"module.":[119],"In":[120,177],"pipeline,":[123,181],"assisted":[124],"by":[125,153,161,189],"vision-language":[127],"model":[128],"(VLM)":[129],"optical":[131],"character":[132],"recognition":[133],"(OCR)":[134],"model,":[135],"first":[137],"extract":[138],"conceptual":[140],"semantics":[141],"images":[143],"project":[145],"them":[146],"elements":[149],"map.":[151],"Next,":[152],"scheme":[156],"performing":[157],"feature":[158],"fusion":[159],"layer":[160],"layer,":[162],"scene":[164],"graph":[165,192],"built":[167],"hierarchically,":[168],"consisting":[169],"slot,":[171],"lane,":[172],"block,":[173],"garage":[175],"layer.":[176],"goal":[184],"can":[185,205],"be":[186],"efficiently":[187],"found":[188],"an":[190],"LLM-enhanced":[191],"retrieval":[193],"approach.":[194],"Experiments":[195],"on":[196],"real-world":[197],"prove":[200],"that":[201],"self-driving":[203],"vehicle":[204],"successfully":[210],"utilizing":[211],"AVP-SG.":[213]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-28T00:00:00"}