{"id":"https://openalex.org/W4400645754","doi":"https://doi.org/10.1109/iv55156.2024.10588479","title":"Pix2Planning: End-to-End Planning by Vision-language Model for Autonomous Driving on Carla Simulator","display_name":"Pix2Planning: End-to-End Planning by Vision-language Model for Autonomous Driving on Carla Simulator","publication_year":2024,"publication_date":"2024-06-02","ids":{"openalex":"https://openalex.org/W4400645754","doi":"https://doi.org/10.1109/iv55156.2024.10588479"},"language":"en","primary_location":{"id":"doi:10.1109/iv55156.2024.10588479","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iv55156.2024.10588479","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Intelligent Vehicles Symposium (IV)","raw_type":"proceedings-article"},"type":"conference-paper","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":false,"raw_author_name":"Xiangru Mu","raw_affiliation_strings":["Shanghai Jiao Tong University,Global Institute of Future Technology,Shanghai,China"],"raw_orcid":null,"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/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"],"raw_orcid":null,"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/A5045427668","display_name":"Songan Zhang","orcid":"https://orcid.org/0000-0002-3238-5406"},"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":"Songan Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University,Global Institute of Future Technology,Shanghai,China"],"raw_orcid":null,"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/A5101082712","display_name":"Chunjing Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunjing Xu","raw_affiliation_strings":["Huawei Technologies,IAS BU,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies,IAS BU,Shanghai,China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","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"],"raw_orcid":null,"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":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2383","last_page":"2390"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9909999966621399,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9909999966621399,"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/computer-science","display_name":"Computer science","score":0.7118424773216248},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.5681132674217224},{"id":"https://openalex.org/keywords/driving-simulator","display_name":"Driving simulator","score":0.4491705894470215},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.44660526514053345},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4083622395992279},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.39147114753723145},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.39102548360824585},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3561909794807434}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7118424773216248},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.5681132674217224},{"id":"https://openalex.org/C2780689630","wikidata":"https://www.wikidata.org/wiki/Q2081815","display_name":"Driving simulator","level":2,"score":0.4491705894470215},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.44660526514053345},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4083622395992279},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39147114753723145},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39102548360824585},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3561909794807434}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iv55156.2024.10588479","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iv55156.2024.10588479","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Intelligent Vehicles Symposium (IV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/13","display_name":"Climate action"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W2108598243","https://openalex.org/W2893501195","https://openalex.org/W2905173465","https://openalex.org/W2962894046","https://openalex.org/W2971116204","https://openalex.org/W3009593063","https://openalex.org/W3109395584","https://openalex.org/W3172863135","https://openalex.org/W3198460218","https://openalex.org/W3199245537","https://openalex.org/W4212774754","https://openalex.org/W4225793049","https://openalex.org/W4226203009","https://openalex.org/W4312396550","https://openalex.org/W4312641958","https://openalex.org/W4312862130","https://openalex.org/W4312894406","https://openalex.org/W4382464460","https://openalex.org/W4383097607","https://openalex.org/W4383108807","https://openalex.org/W4385245566","https://openalex.org/W4386066695","https://openalex.org/W4386071479","https://openalex.org/W4386071585","https://openalex.org/W4386076400","https://openalex.org/W4390872706","https://openalex.org/W4401109681","https://openalex.org/W6745935785","https://openalex.org/W6755170904","https://openalex.org/W6762718338","https://openalex.org/W6772033386","https://openalex.org/W6779371956","https://openalex.org/W6801512601","https://openalex.org/W6810393205","https://openalex.org/W6839043673","https://openalex.org/W6839459284","https://openalex.org/W6841094356","https://openalex.org/W6845636941","https://openalex.org/W6853552647"],"related_works":["https://openalex.org/W2258033839","https://openalex.org/W4297884099","https://openalex.org/W3203668668","https://openalex.org/W4391055430","https://openalex.org/W3214769583","https://openalex.org/W2116812645","https://openalex.org/W1980239608","https://openalex.org/W4377157894","https://openalex.org/W2395327451","https://openalex.org/W3108338563"],"abstract_inverted_index":{"The":[0,115],"end-to-end":[1,18,44,98],"neural":[2,92],"network":[3,45],"has":[4],"become":[5],"a":[6,81,106,138,183],"hot":[7],"topic":[8],"in":[9,37],"recent":[10],"years.":[11],"Compared":[12],"with":[13,210],"traditional":[14],"module-based":[15],"solutions,":[16],"the":[17,24,42,55,66,73,76,87,91,102,122,131,142,145,149,154,158,174,179,188],"paradigm":[19],"is":[20,70,79,135],"able":[21],"to":[22,54,62,127,161,186],"reduce":[23],"accumulated":[25],"error":[26],"and":[27,120,157,177,193,203],"avoid":[28],"information":[29,50,176],"loss,":[30],"so":[31],"that":[32],"it":[33],"earns":[34],"great":[35,88],"attention":[36],"autonomous":[38],"driving":[39],"tasks.":[40],"However,":[41],"current":[43],"designs":[46],"easily":[47],"lose":[48],"useful":[49],"during":[51],"training":[52],"due":[53],"complexity":[56],"of":[57,90,144,173],"mapping":[58],"high-dimensional":[59],"visual":[60,212],"observation":[61],"navigation":[63,68,133],"waypoints.":[64,164],"Since":[65],"future":[67],"point":[69,134],"reasoned":[71],"from":[72,125],"former":[74],"one,":[75],"planning":[77,103,180],"task":[78,104,110],"like":[80],"sequence":[82,108,185],"generation":[83,109],"task.":[84],"Inspired":[85],"by":[86],"power":[89],"language":[93,107,184],"model,":[94],"we":[95],"propose":[96],"an":[97],"framework,":[99],"which":[100],"transfers":[101],"as":[105,141,182],"conditioned":[111],"on":[112,200],"pixel":[113],"inputs.":[114],"proposed":[116,167],"method":[117,168],"firstly":[118],"extracts":[119],"transforms":[121],"image":[123],"feature":[124,156],"camera-view":[126],"bird-eye-view":[128],"(BEV).":[129],"Then":[130],"target":[132],"constructed":[136],"into":[137],"text":[139,159],"sequence,":[140],"prompt":[143],"visual-language":[146],"transformer.":[147],"Finally,":[148],"auto-regressive":[150],"transformer":[151],"decoder":[152],"receives":[153],"BEV":[155],"sequences":[160,192],"generate":[162],"sequential":[163],"Overall,":[165],"our":[166,204],"can":[169],"make":[170],"full":[171],"use":[172],"environmental":[175],"express":[178],"trajectory":[181,191],"learn":[187],"correspondence":[189],"between":[190],"images.":[194],"We":[195],"have":[196],"conducted":[197],"extensive":[198],"experiments":[199],"CARLA":[201],"benchmarks":[202],"model":[205],"achieves":[206],"state-of-the-art":[207],"performance":[208],"compared":[209],"other":[211],"methods.":[213]},"counts_by_year":[{"year":2025,"cited_by_count":8}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}