{"id":"https://openalex.org/W7123350997","doi":"https://doi.org/10.1109/cdc57313.2025.11312735","title":"Using Control Barrier Functions for Constrained Reinforcement Learning in Backward Chained Behavior Trees","display_name":"Using Control Barrier Functions for Constrained Reinforcement Learning in Backward Chained Behavior Trees","publication_year":2025,"publication_date":"2025-12-09","ids":{"openalex":"https://openalex.org/W7123350997","doi":"https://doi.org/10.1109/cdc57313.2025.11312735"},"language":null,"primary_location":{"id":"doi:10.1109/cdc57313.2025.11312735","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312735","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 64th Conference on Decision and Control (CDC)","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/A5001360476","display_name":"Mart Karta\u0161ev","orcid":"https://orcid.org/0000-0001-8264-611X"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Mart Karta\u0161ev","raw_affiliation_strings":["Royal Institute of Technology (KTH),Robotics, Perception and Learning Lab., School of Electrical Engineering and Computer Science,Stockholm,Sweden,SE-100 44"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Royal Institute of Technology (KTH),Robotics, Perception and Learning Lab., School of Electrical Engineering and Computer Science,Stockholm,Sweden,SE-100 44","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122904450","display_name":"Jannik Wagner","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Jannik Wagner","raw_affiliation_strings":["Royal Institute of Technology (KTH),Robotics, Perception and Learning Lab., School of Electrical Engineering and Computer Science,Stockholm,Sweden,SE-100 44"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Royal Institute of Technology (KTH),Robotics, Perception and Learning Lab., School of Electrical Engineering and Computer Science,Stockholm,Sweden,SE-100 44","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122867361","display_name":"Petter \u00d6gren","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Petter \u00d6gren","raw_affiliation_strings":["Royal Institute of Technology (KTH),Robotics, Perception and Learning Lab., School of Electrical Engineering and Computer Science,Stockholm,Sweden,SE-100 44"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Royal Institute of Technology (KTH),Robotics, Perception and Learning Lab., School of Electrical Engineering and Computer Science,Stockholm,Sweden,SE-100 44","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.79267238,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3127","last_page":"3134"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7530999779701233,"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":0.7530999779701233,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.09570000320672989,"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":0.015599999576807022,"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/undoing","display_name":"Undoing","score":0.8880000114440918},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.782800018787384},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5440000295639038},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.3091999888420105},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.29919999837875366},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.28999999165534973}],"concepts":[{"id":"https://openalex.org/C2780492140","wikidata":"https://www.wikidata.org/wiki/Q4066779","display_name":"Undoing","level":2,"score":0.8880000114440918},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.782800018787384},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7124999761581421},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5440000295639038},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4018000066280365},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.3091999888420105},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.29919999837875366},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.2768000066280365},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2709999978542328},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc57313.2025.11312735","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312735","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 64th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3,76],"combine":[4],"Reinforcement":[5],"Learning":[6],"(RL),":[7],"Behavior":[8],"Trees":[9],"(BTs),":[10],"and":[11,33,50,61,85,95,116],"Control":[12],"Barrier":[13],"Functions":[14],"(CBFs)":[15],"to":[16,38,55,66,79,112],"create":[17],"controllers":[18,87],"for":[19,70,88],"complex":[20],"tasks.":[21],"Pairwise,":[22],"these":[23],"tools":[24],"have":[25,35,52,63],"been":[26,36,53,64],"combined":[27,37,54],"in":[28],"several":[29],"earlier":[30],"works.":[31],"RL":[32],"BTs":[34,49],"break":[39,80],"down":[40,81],"tasks":[41,82,90],"into":[42,83],"subtasks":[43,84],"that":[44,91,105,107],"are":[45,77,92],"solved":[46],"by":[47],"RL.":[48,71],"CBFs":[51,62],"avoid":[56,96],"undoing":[57,97],"already":[58],"achieved":[59,99],"subtasks,":[60],"used":[65],"provide":[67,102],"safety":[68],"guarantees":[69],"By":[72],"combining":[73],"all":[74],"three,":[75],"able":[78],"learn":[86],"those":[89],"both":[93],"safe":[94],"previously":[98],"subtasks.":[100],"We":[101],"experimental":[103],"results":[104],"show":[106],"the":[108],"proposed":[109],"approach":[110],"leads":[111],"more":[113],"efficient":[114],"training":[115],"shorter":[117],"completion":[118],"times":[119],"of":[120],"missions.":[121]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-01-14T00:00:00"}