{"id":"https://openalex.org/W4413926024","doi":"https://doi.org/10.1109/icra55743.2025.11127225","title":"Certificated Actor-Critic: Hierarchical Reinforcement Learning with Control Barrier Functions for Safe Navigation","display_name":"Certificated Actor-Critic: Hierarchical Reinforcement Learning with Control Barrier Functions for Safe Navigation","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413926024","doi":"https://doi.org/10.1109/icra55743.2025.11127225"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11127225","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127225","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","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/A5112947307","display_name":"Junjun Xie","orcid":"https://orcid.org/0009-0001-3845-8004"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210157642","display_name":"Institute of Automation","ror":"https://ror.org/056qj1t15","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210157642","https://openalex.org/I78650965"]}],"countries":["CN","DE"],"is_corresponding":false,"raw_author_name":"Junjun Xie","raw_affiliation_strings":["School of Mechanical Engineering and Automation, Harbin Institute of Technology,Department of Automation,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering and Automation, Harbin Institute of Technology,Department of Automation,Shenzhen,China","institution_ids":["https://openalex.org/I204983213","https://openalex.org/I4210157642"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083419460","display_name":"Shuhao Zhao","orcid":"https://orcid.org/0000-0003-1679-0345"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210157642","display_name":"Institute of Automation","ror":"https://ror.org/056qj1t15","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210157642","https://openalex.org/I78650965"]}],"countries":["CN","DE"],"is_corresponding":false,"raw_author_name":"Shuhao Zhao","raw_affiliation_strings":["School of Mechanical Engineering and Automation, Harbin Institute of Technology,Department of Automation,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering and Automation, Harbin Institute of Technology,Department of Automation,Shenzhen,China","institution_ids":["https://openalex.org/I204983213","https://openalex.org/I4210157642"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101462142","display_name":"Hu L","orcid":"https://orcid.org/0000-0002-3955-7530"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210157642","display_name":"Institute of Automation","ror":"https://ror.org/056qj1t15","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210157642","https://openalex.org/I78650965"]}],"countries":["CN","DE"],"is_corresponding":false,"raw_author_name":"Liang Hu","raw_affiliation_strings":["School of Mechanical Engineering and Automation, Harbin Institute of Technology,Department of Automation,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering and Automation, Harbin Institute of Technology,Department of Automation,Shenzhen,China","institution_ids":["https://openalex.org/I204983213","https://openalex.org/I4210157642"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036684787","display_name":"Huijun Gao","orcid":"https://orcid.org/0000-0001-5554-5452"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huijun Gao","raw_affiliation_strings":["Research Institute of Intelligent Control and Systems, Harbin Institute of Technology,Harbin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Institute of Intelligent Control and Systems, Harbin Institute of Technology,Harbin,China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5482","last_page":"5488"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.88919997215271,"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":0.88919997215271,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.8468999862670898,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.8431000113487244,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8165894150733948},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6370856761932373},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5878499746322632},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3933112919330597},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.32402878999710083}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8165894150733948},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6370856761932373},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5878499746322632},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3933112919330597},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32402878999710083}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11127225","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127225","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1980569135","https://openalex.org/W2026616272","https://openalex.org/W2171879251","https://openalex.org/W2560504659","https://openalex.org/W2735010720","https://openalex.org/W2904246096","https://openalex.org/W2966735560","https://openalex.org/W2968945909","https://openalex.org/W3046709980","https://openalex.org/W3048735518","https://openalex.org/W3114626444","https://openalex.org/W3183306336","https://openalex.org/W3186317065","https://openalex.org/W3209325542","https://openalex.org/W4285102565","https://openalex.org/W4293057543","https://openalex.org/W4293255219","https://openalex.org/W4312433875","https://openalex.org/W4360764635","https://openalex.org/W4383108357","https://openalex.org/W4383108702","https://openalex.org/W4383108928","https://openalex.org/W4387350709","https://openalex.org/W4389665353","https://openalex.org/W4401416568"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4306904969","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2138720691","https://openalex.org/W2376932109"],"abstract_inverted_index":{"Control":[0],"Barrier":[1],"Functions":[2],"(CBFs)":[3],"have":[4],"emerged":[5],"as":[6],"a":[7,68,80],"prominent":[8],"approach":[9],"to":[10,31],"designing":[11],"safe":[12,27],"navigation":[13,59],"systems":[14],"of":[15,53,58,99,120],"robots.":[16],"Despite":[17],"their":[18],"popularity,":[19],"current":[20],"CBF-based":[21],"methods":[22,48],"exhibit":[23],"some":[24],"limitations:":[25],"optimization-based":[26],"control":[28],"techniques":[29],"tend":[30],"be":[32],"either":[33],"myopic":[34],"or":[35],"computationally":[36],"intensive,":[37],"and":[38,61,85,97,102],"they":[39],"rely":[40],"on":[41],"simplified":[42],"system":[43],"models;":[44],"conversely,":[45],"the":[46,51,118],"learning-based":[47],"suffer":[49],"from":[50,90],"lack":[52],"quantitative":[54],"indication":[55],"in":[56,106],"terms":[57],"performance":[60],"safety.":[62],"In":[63],"this":[64],"paper,":[65],"we":[66],"present":[67],"new":[69],"model-free":[70],"reinforcement":[71,82],"learning":[72,83],"algorithm":[73,107],"called":[74],"Certificated":[75],"Actor-Critic":[76],"(CAC),":[77],"which":[78],"introduces":[79],"hierarchical":[81],"framework":[84],"well-defined":[86],"reward":[87],"functions":[88],"derived":[89],"CBFs.":[91],"We":[92],"carry":[93],"out":[94],"theoretical":[95],"analysis":[96,110],"proof":[98],"our":[100,121],"algorithm,":[101],"propose":[103],"several":[104],"improvements":[105],"implementation.":[108],"Our":[109],"is":[111],"validated":[112],"by":[113],"two":[114],"simulation":[115],"experiments,":[116],"showing":[117],"effectiveness":[119],"proposed":[122],"CAC":[123],"algorithm.":[124]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}