{"id":"https://openalex.org/W4413018168","doi":"https://doi.org/10.1109/iv64158.2025.11097749","title":"Distributional Soft Actor-Critic with Harmonic Gradient for Safe and Efficient Autonomous Driving in Multi-Lane Scenarios","display_name":"Distributional Soft Actor-Critic with Harmonic Gradient for Safe and Efficient Autonomous Driving in Multi-Lane Scenarios","publication_year":2025,"publication_date":"2025-06-22","ids":{"openalex":"https://openalex.org/W4413018168","doi":"https://doi.org/10.1109/iv64158.2025.11097749"},"language":"en","primary_location":{"id":"doi:10.1109/iv64158.2025.11097749","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iv64158.2025.11097749","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Intelligent Vehicles Symposium (IV)","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/A5055209635","display_name":"Feihong Zhang","orcid":"https://orcid.org/0000-0003-4962-6963"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Feihong Zhang","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029301375","display_name":"Guojian Zhan","orcid":"https://orcid.org/0000-0002-1246-4860"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guojian Zhan","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112660869","display_name":"Bin Shuai","orcid":"https://orcid.org/0009-0004-3616-1532"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Shuai","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tianyi Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyi Zhang","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067909017","display_name":"Jingliang Duan","orcid":"https://orcid.org/0000-0002-3697-1576"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingliang Duan","raw_affiliation_strings":["School of Mechanical Engineering, University of Science and Technology Beijing,Beijing,China,100083"],"affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, University of Science and Technology Beijing,Beijing,China,100083","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100747108","display_name":"Shengbo Eben Li","orcid":"https://orcid.org/0000-0003-4923-3633"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengbo Eben Li","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5055209635"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09800859,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1964","last_page":"1970"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9927999973297119,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9927999973297119,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9498000144958496,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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":0.9266999959945679,"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":0.6423932313919067},{"id":"https://openalex.org/keywords/harmonic","display_name":"Harmonic","score":0.47156354784965515},{"id":"https://openalex.org/keywords/soft-robotics","display_name":"Soft robotics","score":0.43087077140808105},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34155935049057007},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3138398230075836},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2498829960823059},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.15602976083755493},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12727385759353638}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6423932313919067},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.47156354784965515},{"id":"https://openalex.org/C2776058767","wikidata":"https://www.wikidata.org/wiki/Q24327151","display_name":"Soft robotics","level":3,"score":0.43087077140808105},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34155935049057007},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3138398230075836},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2498829960823059},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.15602976083755493},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12727385759353638}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iv64158.2025.11097749","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iv64158.2025.11097749","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Intelligent Vehicles Symposium (IV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G166390454","display_name":null,"funder_award_id":"U20A20334","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2968983352","https://openalex.org/W3002044607","https://openalex.org/W3011338904","https://openalex.org/W3015082424","https://openalex.org/W3135239772","https://openalex.org/W3198163207","https://openalex.org/W3211345831","https://openalex.org/W3213557649","https://openalex.org/W4224216677","https://openalex.org/W4286285538","https://openalex.org/W4362650413","https://openalex.org/W4366158867","https://openalex.org/W4388878609","https://openalex.org/W4388903439","https://openalex.org/W4390933328","https://openalex.org/W4392908297","https://openalex.org/W4394006698","https://openalex.org/W4406983280","https://openalex.org/W6780587392","https://openalex.org/W6796690604"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"(RL),":[2],"known":[3],"for":[4,25,72],"its":[5],"self-evolution":[6],"capability,":[7],"offers":[8],"a":[9,22,38,67,84,109],"promising":[10],"approach":[11],"to":[12,107],"training":[13,41,89],"high-level":[14],"autonomous":[15],"driving":[16,61,125],"systems.":[17],"However,":[18],"handling":[19],"constraints":[20],"remains":[21],"significant":[23],"challenge":[24],"existing":[26],"RL":[27,50,112],"algorithms,":[28],"particularly":[29],"in":[30,117],"real-world":[31],"applications.":[32],"In":[33],"this":[34],"paper,":[35],"we":[36,92],"propose":[37],"new":[39,110],"safety-oriented":[40],"technique":[42],"called":[43],"harmonic":[44,68],"policy":[45,56,73],"iteration":[46],"(HPI).":[47],"At":[48],"each":[49],"iteration,":[51],"it":[52,103],"first":[53],"calculates":[54],"two":[55,79],"gradients":[57,80],"associated":[58],"with":[59,104,127],"efficient":[60,124],"and":[62,81,87,101],"safety":[63,129],"constraints,":[64],"respectively.":[65],"Then,":[66],"gradient":[69],"is":[70],"derived":[71],"updating,":[74],"minimizing":[75],"conflicts":[76],"between":[77],"the":[78,94,99],"consequently":[82],"enabling":[83],"more":[85],"balanced":[86],"stable":[88],"process.":[90],"Furthermore,":[91],"adopt":[93],"state-of-the-art":[95],"DSAC":[96],"algorithm":[97],"as":[98],"backbone":[100],"integrate":[102],"our":[105],"HPI":[106],"develop":[108],"safe":[111],"algorithm,":[113],"DSAC-H.":[114],"Extensive":[115],"simulations":[116],"multi-lane":[118],"scenarios":[119],"demonstrate":[120],"that":[121],"DSAC-H":[122],"achieves":[123],"performance":[126],"near-zero":[128],"constraint":[130],"violations.":[131]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}