{"id":"https://openalex.org/W4415538232","doi":"https://doi.org/10.1145/3746027.3755341","title":"NavigScene: Bridging Local Perception and Global Navigation for Beyond-Visual-Range Autonomous Driving","display_name":"NavigScene: Bridging Local Perception and Global Navigation for Beyond-Visual-Range Autonomous Driving","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538232","doi":"https://doi.org/10.1145/3746027.3755341"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3755341","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755341","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.05227","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030729488","display_name":"Qucheng Peng","orcid":"https://orcid.org/0000-0002-0311-6135"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qucheng Peng","raw_affiliation_strings":["Center for Research in Computer Vision, University of Central Florida, Orlando, Florida, USA"],"raw_orcid":"https://orcid.org/0000-0002-0311-6135","affiliations":[{"raw_affiliation_string":"Center for Research in Computer Vision, University of Central Florida, Orlando, Florida, USA","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100662680","display_name":"Chen Bai","orcid":"https://orcid.org/0000-0003-0194-1358"},"institutions":[{"id":"https://openalex.org/I2801120862","display_name":"General Motors (India)","ror":"https://ror.org/05g5nrw43","country_code":"IN","type":"company","lineage":["https://openalex.org/I118136607","https://openalex.org/I2801120862"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Chen Bai","raw_affiliation_strings":["Xpeng Motors, Santa Clara, California, USA"],"raw_orcid":"https://orcid.org/0000-0003-0194-1358","affiliations":[{"raw_affiliation_string":"Xpeng Motors, Santa Clara, California, USA","institution_ids":["https://openalex.org/I2801120862"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102100681","display_name":"G. Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I2801120862","display_name":"General Motors (India)","ror":"https://ror.org/05g5nrw43","country_code":"IN","type":"company","lineage":["https://openalex.org/I118136607","https://openalex.org/I2801120862"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Guoxiang Zhang","raw_affiliation_strings":["Xpeng Motors, Santa Clara, California, USA"],"raw_orcid":"https://orcid.org/0009-0005-0612-3823","affiliations":[{"raw_affiliation_string":"Xpeng Motors, Santa Clara, California, USA","institution_ids":["https://openalex.org/I2801120862"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065635207","display_name":"Bo Xu","orcid":"https://orcid.org/0000-0001-6379-7617"},"institutions":[{"id":"https://openalex.org/I2801120862","display_name":"General Motors (India)","ror":"https://ror.org/05g5nrw43","country_code":"IN","type":"company","lineage":["https://openalex.org/I118136607","https://openalex.org/I2801120862"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Bo Xu","raw_affiliation_strings":["Xpeng Motors, Santa Clara, USA"],"raw_orcid":"https://orcid.org/0000-0001-6379-7617","affiliations":[{"raw_affiliation_string":"Xpeng Motors, Santa Clara, USA","institution_ids":["https://openalex.org/I2801120862"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaotong Liu","orcid":"https://orcid.org/0009-0007-8327-1584"},"institutions":[{"id":"https://openalex.org/I2801120862","display_name":"General Motors (India)","ror":"https://ror.org/05g5nrw43","country_code":"IN","type":"company","lineage":["https://openalex.org/I118136607","https://openalex.org/I2801120862"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Xiaotong Liu","raw_affiliation_strings":["Xpeng Motors, Santa Clara, California, USA"],"raw_orcid":"https://orcid.org/0009-0007-8327-1584","affiliations":[{"raw_affiliation_string":"Xpeng Motors, Santa Clara, California, USA","institution_ids":["https://openalex.org/I2801120862"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051070968","display_name":"Xiaoyin Zheng","orcid":"https://orcid.org/0009-0005-9640-0563"},"institutions":[{"id":"https://openalex.org/I2801120862","display_name":"General Motors (India)","ror":"https://ror.org/05g5nrw43","country_code":"IN","type":"company","lineage":["https://openalex.org/I118136607","https://openalex.org/I2801120862"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Xiaoyin Zheng","raw_affiliation_strings":["Xpeng Motors, Santa Clara, California, USA"],"raw_orcid":"https://orcid.org/0009-0005-9640-0563","affiliations":[{"raw_affiliation_string":"Xpeng Motors, Santa Clara, California, USA","institution_ids":["https://openalex.org/I2801120862"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418568","display_name":"Chen Chen","orcid":"https://orcid.org/0000-0003-3957-7061"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen Chen","raw_affiliation_strings":["Center for Research in Computer Vision, University of Central Florida, Orlando, Florida, USA"],"raw_orcid":"https://orcid.org/0000-0003-3957-7061","affiliations":[{"raw_affiliation_string":"Center for Research in Computer Vision, University of Central Florida, Orlando, Florida, USA","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112404880","display_name":"Cheng Lu","orcid":"https://orcid.org/0000-0001-5905-2321"},"institutions":[{"id":"https://openalex.org/I2801120862","display_name":"General Motors (India)","ror":"https://ror.org/05g5nrw43","country_code":"IN","type":"company","lineage":["https://openalex.org/I118136607","https://openalex.org/I2801120862"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Cheng Lu","raw_affiliation_strings":["Xpeng Motors, Santa Clara, California, USA"],"raw_orcid":"https://orcid.org/0000-0001-5905-2321","affiliations":[{"raw_affiliation_string":"Xpeng Motors, Santa Clara, California, USA","institution_ids":["https://openalex.org/I2801120862"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7872,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.76901148,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4193","last_page":"4202"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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":0.9997000098228455,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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":0.9987999796867371,"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/leverage","display_name":"Leverage (statistics)","score":0.6355000138282776},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.5910000205039978},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.423799991607666},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4196000099182129},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.41929998993873596},{"id":"https://openalex.org/keywords/spatial-contextual-awareness","display_name":"Spatial contextual awareness","score":0.35089999437332153},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.3057999908924103},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.29190000891685486}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6355000138282776},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6226000189781189},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.5910000205039978},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4823000133037567},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4772999882698059},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.423799991607666},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4196000099182129},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.41929998993873596},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.35089999437332153},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.3057999908924103},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.29190000891685486},{"id":"https://openalex.org/C87833898","wikidata":"https://www.wikidata.org/wiki/Q1060280","display_name":"Advanced driver assistance systems","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2743000090122223},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.26759999990463257},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.2549000084400177},{"id":"https://openalex.org/C3017944768","wikidata":"https://www.wikidata.org/wiki/Q1450463","display_name":"Poison control","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.251800000667572}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3755341","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755341","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.05227","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.05227","pdf_url":"https://arxiv.org/pdf/2507.05227","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.05227","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.05227","pdf_url":"https://arxiv.org/pdf/2507.05227","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1956340063","https://openalex.org/W3035574168","https://openalex.org/W4379415663","https://openalex.org/W4386076400","https://openalex.org/W4386918877","https://openalex.org/W4390872423","https://openalex.org/W4393148430","https://openalex.org/W4393160572","https://openalex.org/W4403791964","https://openalex.org/W4403843558","https://openalex.org/W4413018544"],"related_works":[],"abstract_inverted_index":{"Autonomous":[0],"driving":[1,57,61,126,159,171],"systems":[2,172],"have":[3],"made":[4],"significant":[5,165],"advances":[6],"in":[7],"Q&A,":[8],"perception,":[9,141],"prediction,":[10,142],"and":[11,40,112,121,144,154,182],"planning":[12],"based":[13],"on":[14],"local":[15,37],"visual":[16,152],"information,":[17],"yet":[18],"they":[19],"struggle":[20],"to":[21,69,100,157],"incorporate":[22],"broader":[23],"navigational":[24],"context":[25,82],"that":[26,53,95,134],"human":[27],"drivers":[28],"routinely":[29],"utilize.":[30],"We":[31],"address":[32],"this":[33],"critical":[34],"gap":[35],"between":[36],"sensor":[38],"data":[39],"global":[41],"navigation":[42,81,119],"information":[43],"by":[44,79,105,147],"proposing":[45],"NavigScene,":[46],"an":[47],"auxiliary":[48],"navigation-guided":[49],"natural":[50],"language":[51],"dataset":[52],"simulates":[54],"a":[55,91,164],"human-like":[56],"environment":[58],"within":[59],"autonomous":[60,170],"systems.":[62],"Moreover,":[63],"we":[64],"develop":[65],"three":[66],"complementary":[67],"paradigms":[68],"leverage":[70],"NavigScene:":[71],"(1)":[72],"Navigation-guided":[73,88,114],"Reasoning,":[74],"which":[75,117],"enhances":[76],"vision-language":[77,102,122],"models":[78,123,127],"incorporating":[80],"into":[83],"the":[84],"prompting":[85],"approach;":[86],"(2)":[87],"Preference":[89,98],"Optimization,":[90],"reinforcement":[92],"learning":[93],"method":[94],"extends":[96],"Direct":[97],"Optimization":[99],"improve":[101,138],"model":[103],"responses":[104],"establishing":[106],"preferences":[107],"for":[108],"navigation-relevant":[109],"summarized":[110],"information;":[111],"(3)":[113],"Vision-Language-Action":[115],"model,":[116],"integrates":[118],"guidance":[120],"with":[124,179],"conventional":[125],"through":[128],"feature":[129],"fusion.":[130],"Extensive":[131],"experiments":[132],"demonstrate":[133],"our":[135],"approaches":[136],"significantly":[137],"performance":[139],"across":[140],"planning,":[143],"question-answering":[145],"tasks":[146],"enabling":[148],"reasoning":[149],"capabilities":[150],"beyond":[151],"range":[153],"improving":[155],"generalization":[156],"diverse":[158],"scenarios.":[160],"This":[161],"work":[162],"represents":[163],"step":[166],"toward":[167],"more":[168],"comprehensive":[169],"capable":[173],"of":[174],"navigating":[175],"complex,":[176],"unfamiliar":[177],"environments":[178],"greater":[180],"reliability":[181],"safety.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-04T07:58:01.006859","created_date":"2025-10-10T00:00:00"}