{"id":"https://openalex.org/W4383108928","doi":"https://doi.org/10.1109/icra48891.2023.10160991","title":"Reinforcement Learning for Safe Robot Control using Control Lyapunov Barrier Functions","display_name":"Reinforcement Learning for Safe Robot Control using Control Lyapunov Barrier Functions","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383108928","doi":"https://doi.org/10.1109/icra48891.2023.10160991"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10160991","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160991","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://repository.tudelft.nl/file/File_437fd0a0-7953-41ff-b285-177a7f2bc644","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114051149","display_name":"Desong Du","orcid":null},"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/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["CN","NL"],"is_corresponding":true,"raw_author_name":"Desong Du","raw_affiliation_strings":["School of Astronautics, Harbin Institute of Technology,China","Department of Cognitive Robotics, Delft University of Technology, Netherlands","School of Astronautics, Harbin Institute of Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Astronautics, Harbin Institute of Technology,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Department of Cognitive Robotics, Delft University of Technology, Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"School of Astronautics, Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057180094","display_name":"Shaohang Han","orcid":"https://orcid.org/0000-0002-3294-8002"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Shaohang Han","raw_affiliation_strings":["Delft University of Technology,Department of Cognitive Robotics,Netherlands","Department of Cognitive Robotics, Delft University of Technology, Netherlands"],"affiliations":[{"raw_affiliation_string":"Delft University of Technology,Department of Cognitive Robotics,Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Department of Cognitive Robotics, Delft University of Technology, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062219425","display_name":"Naiming Qi","orcid":"https://orcid.org/0000-0003-0401-5616"},"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":"Naiming Qi","raw_affiliation_strings":["School of Astronautics, Harbin Institute of Technology,China","School of Astronautics, Harbin Institute of Technology, China"],"affiliations":[{"raw_affiliation_string":"School of Astronautics, Harbin Institute of Technology,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"School of Astronautics, Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034334762","display_name":"Haitham Bou Ammar","orcid":"https://orcid.org/0000-0002-6083-6171"},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]},{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Haitham Bou Ammar","raw_affiliation_strings":["Huawei Technologies,United Kingdom","Department of Computer Science, University College, London, United Kingdom","Huawei Technologies, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies,United Kingdom","institution_ids":["https://openalex.org/I4210160618"]},{"raw_affiliation_string":"Department of Computer Science, University College, London, United Kingdom","institution_ids":["https://openalex.org/I45129253"]},{"raw_affiliation_string":"Huawei Technologies, United Kingdom","institution_ids":["https://openalex.org/I4210160618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100332169","display_name":"Jun Wang","orcid":"https://orcid.org/0000-0003-3422-104X"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jun Wang","raw_affiliation_strings":["University College,Department of Computer Science,London,United Kingdom","Department of Computer Science, University College, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University College,Department of Computer Science,London,United Kingdom","institution_ids":["https://openalex.org/I45129253"]},{"raw_affiliation_string":"Department of Computer Science, University College, London, United Kingdom","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100721259","display_name":"Wei Pan","orcid":"https://orcid.org/0000-0003-1121-9879"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]},{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["GB","NL"],"is_corresponding":false,"raw_author_name":"Wei Pan","raw_affiliation_strings":["University of Manchester,Department of Computer Science,United Kingdom","Department of Cognitive Robotics, Delft University of Technology, Netherlands","Department of Computer Science, University of Manchester, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Manchester,Department of Computer Science,United Kingdom","institution_ids":["https://openalex.org/I28407311"]},{"raw_affiliation_string":"Department of Cognitive Robotics, Delft University of Technology, Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Department of Computer Science, University of Manchester, United Kingdom","institution_ids":["https://openalex.org/I28407311"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5114051149"],"corresponding_institution_ids":["https://openalex.org/I204983213","https://openalex.org/I98358874"],"apc_list":null,"apc_paid":null,"fwci":1.9011,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.88473872,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"9442","last_page":"9448"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9958999752998352,"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":0.9958999752998352,"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/T12810","display_name":"Real-time simulation and control systems","score":0.9710999727249146,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9699000120162964,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/reachability","display_name":"Reachability","score":0.9048267602920532},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7868549823760986},{"id":"https://openalex.org/keywords/lyapunov-function","display_name":"Lyapunov function","score":0.7250816822052002},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7174897789955139},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.664020299911499},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5871834754943848},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4728325307369232},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.46339303255081177},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.45434993505477905},{"id":"https://openalex.org/keywords/robot-control","display_name":"Robot control","score":0.4110831618309021},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.34118154644966125},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2643333375453949},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16013658046722412},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11233136057853699},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.07695409655570984}],"concepts":[{"id":"https://openalex.org/C136643341","wikidata":"https://www.wikidata.org/wiki/Q1361526","display_name":"Reachability","level":2,"score":0.9048267602920532},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7868549823760986},{"id":"https://openalex.org/C60640748","wikidata":"https://www.wikidata.org/wiki/Q2337858","display_name":"Lyapunov function","level":3,"score":0.7250816822052002},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7174897789955139},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.664020299911499},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5871834754943848},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4728325307369232},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.46339303255081177},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.45434993505477905},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.4110831618309021},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.34118154644966125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2643333375453949},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16013658046722412},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11233136057853699},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.07695409655570984},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icra48891.2023.10160991","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160991","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/5cb7e397-e5fc-41b3-8731-a1edd47526b9","is_oa":false,"landing_page_url":"https://research.manchester.ac.uk/en/publications/5cb7e397-e5fc-41b3-8731-a1edd47526b9","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Du, D, Han, S, Qi, N, Ammar, H B, Wang, J & Pan, W 2023, Reinforcement Learning for Safe Robot Control using Control Lyapunov Barrier Functions. in Proceedings - ICRA 2023 : IEEE International Conference on Robotics and Automation. Proceedings - IEEE International Conference on Robotics and Automation, vol. 2023-May, IEEE, pp. 9442-9448, 2023 IEEE International Conference on Robotics and Automation, ICRA 2023, London, United Kingdom, 29/05/23. https://doi.org/10.1109/ICRA48891.2023.10160991","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:tudelft.nl:uuid:9e01529f-e133-4794-bb32-eb525b08ede2","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:9e01529f-e133-4794-bb32-eb525b08ede2","pdf_url":"https://repository.tudelft.nl/file/File_437fd0a0-7953-41ff-b285-177a7f2bc644","source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference paper"}],"best_oa_location":{"id":"pmh:oai:tudelft.nl:uuid:9e01529f-e133-4794-bb32-eb525b08ede2","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:9e01529f-e133-4794-bb32-eb525b08ede2","pdf_url":"https://repository.tudelft.nl/file/File_437fd0a0-7953-41ff-b285-177a7f2bc644","source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference paper"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8589651859","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"}],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4383108928.pdf","grobid_xml":"https://content.openalex.org/works/W4383108928.grobid-xml"},"referenced_works_count":59,"referenced_works":["https://openalex.org/W1980569135","https://openalex.org/W2101075098","https://openalex.org/W2169206416","https://openalex.org/W2238345790","https://openalex.org/W2293539771","https://openalex.org/W2427917354","https://openalex.org/W2569839618","https://openalex.org/W2586067474","https://openalex.org/W2735010720","https://openalex.org/W2781726626","https://openalex.org/W2798791976","https://openalex.org/W2804791273","https://openalex.org/W2889711700","https://openalex.org/W2913300629","https://openalex.org/W2918383326","https://openalex.org/W2963293747","https://openalex.org/W2963796870","https://openalex.org/W2963864421","https://openalex.org/W2966735560","https://openalex.org/W3020718655","https://openalex.org/W3031634197","https://openalex.org/W3035702124","https://openalex.org/W3038180127","https://openalex.org/W3045059767","https://openalex.org/W3084158465","https://openalex.org/W3096954237","https://openalex.org/W3099352109","https://openalex.org/W3111531580","https://openalex.org/W3120272748","https://openalex.org/W3127031155","https://openalex.org/W3150718622","https://openalex.org/W3162439934","https://openalex.org/W3195968524","https://openalex.org/W3198980715","https://openalex.org/W3207637958","https://openalex.org/W4200438872","https://openalex.org/W4221161274","https://openalex.org/W4250739957","https://openalex.org/W4287629996","https://openalex.org/W4293545785","https://openalex.org/W4294555834","https://openalex.org/W4294562617","https://openalex.org/W6684921986","https://openalex.org/W6696708278","https://openalex.org/W6717915398","https://openalex.org/W6733118196","https://openalex.org/W6737893269","https://openalex.org/W6738483526","https://openalex.org/W6747473740","https://openalex.org/W6751535212","https://openalex.org/W6751725685","https://openalex.org/W6758924645","https://openalex.org/W6768397756","https://openalex.org/W6779657896","https://openalex.org/W6784630725","https://openalex.org/W6784643869","https://openalex.org/W6800526921","https://openalex.org/W6801468180","https://openalex.org/W6803800456"],"related_works":["https://openalex.org/W1886477626","https://openalex.org/W2762381663","https://openalex.org/W4317826762","https://openalex.org/W218732962","https://openalex.org/W1540467731","https://openalex.org/W1979383880","https://openalex.org/W2538037439","https://openalex.org/W2741909783","https://openalex.org/W4210919297","https://openalex.org/W1532677580"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"(RL)":[2],"exhibits":[3],"impressive":[4],"performance":[5],"when":[6],"managing":[7],"complicated":[8],"control":[9,37,96],"tasks":[10],"for":[11,72],"robots.":[12],"However,":[13],"its":[14],"wide":[15],"application":[16],"to":[17,42,70],"physical":[18],"robots":[19],"is":[20,89],"limited":[21],"by":[22],"the":[23,36,44,61,77,81],"absence":[24],"of":[25,80],"strong":[26],"safety":[27,45,82],"guarantees.":[28],"To":[29],"overcome":[30],"this":[31,33,108],"challenge,":[32],"paper":[34],"explores":[35],"Lyapunov":[38,62],"barrier":[39,63],"function":[40],"(CLBF)":[41],"analyze":[43],"and":[46,83,93,113],"reachability":[47,84,112],"solely":[48],"based":[49],"on":[50],"data":[51],"without":[52],"explicitly":[53],"employing":[54],"a":[55,66,73,99],"dynamic":[56],"model.":[57],"We":[58],"also":[59],"proposed":[60,87],"actor-critic":[64],"(LBAC),":[65],"model-free":[67,117],"RL":[68,118],"algorithm,":[69],"search":[71],"controller":[74],"that":[75],"satisfies":[76],"data-based":[78],"approximation":[79],"conditions.":[85],"The":[86,104],"approach":[88],"demonstrated":[90],"through":[91],"simulation":[92],"real-world":[94],"robot":[95],"experiments,":[97],"i.e.,":[98],"2D":[100],"quadrotor":[101],"navigation":[102],"task.":[103],"experimental":[105],"findings":[106],"reveal":[107],"approach's":[109],"effectiveness":[110],"in":[111],"safety,":[114],"surpassing":[115],"other":[116],"methods.":[119]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}