{"id":"https://openalex.org/W4389667231","doi":"https://doi.org/10.1109/iros55552.2023.10341561","title":"Lyapunov Constrained Safe Reinforcement Learning for Multicopter Visual Servoing","display_name":"Lyapunov Constrained Safe Reinforcement Learning for Multicopter Visual Servoing","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4389667231","doi":"https://doi.org/10.1109/iros55552.2023.10341561"},"language":"en","primary_location":{"id":"doi:10.1109/iros55552.2023.10341561","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iros55552.2023.10341561","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5084429143","display_name":"Dafang Yu","orcid":"https://orcid.org/0009-0003-1166-8372"},"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":true,"raw_author_name":"Dafang Yu","raw_affiliation_strings":["AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,Shanghai,China,200240"],"affiliations":[{"raw_affiliation_string":"AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,Shanghai,China,200240","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084835357","display_name":"Mengxin Xu","orcid":"https://orcid.org/0000-0003-1308-5958"},"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":"Mengxin Xu","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Automation,Shanghai,China,200240"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Automation,Shanghai,China,200240","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100462338","display_name":"Zhe Liu","orcid":"https://orcid.org/0000-0001-6753-0303"},"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":"Zhe Liu","raw_affiliation_strings":["AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,Shanghai,China,200240"],"affiliations":[{"raw_affiliation_string":"AI Institute, Shanghai Jiao Tong University,MoE Key Lab of Artificial Intelligence,Shanghai,China,200240","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107772128","display_name":"Hesheng Wang","orcid":"https://orcid.org/0000-0002-9959-1634"},"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":"Hesheng Wang","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Automation,Shanghai,China,200240"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Automation,Shanghai,China,200240","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5084429143"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15781814,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"30","issue":null,"first_page":"6419","last_page":"6424"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9923999905586243,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9923999905586243,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9912999868392944,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T11601","display_name":"Neuroscience and Neural Engineering","score":0.9900000095367432,"subfield":{"id":"https://openalex.org/subfields/2804","display_name":"Cellular and Molecular Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7686507701873779},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7161312103271484},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.6235953569412231},{"id":"https://openalex.org/keywords/lyapunov-function","display_name":"Lyapunov function","score":0.6221295595169067},{"id":"https://openalex.org/keywords/visual-servoing","display_name":"Visual servoing","score":0.5546888113021851},{"id":"https://openalex.org/keywords/safer","display_name":"SAFER","score":0.5007421970367432},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.48172858357429504},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4805870056152344},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.44921472668647766},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.4485796093940735},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.3445780575275421},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3007127046585083},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.24491655826568604},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.09889009594917297}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7686507701873779},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7161312103271484},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.6235953569412231},{"id":"https://openalex.org/C60640748","wikidata":"https://www.wikidata.org/wiki/Q2337858","display_name":"Lyapunov function","level":3,"score":0.6221295595169067},{"id":"https://openalex.org/C10912380","wikidata":"https://www.wikidata.org/wiki/Q527952","display_name":"Visual servoing","level":3,"score":0.5546888113021851},{"id":"https://openalex.org/C2776654903","wikidata":"https://www.wikidata.org/wiki/Q2601463","display_name":"SAFER","level":2,"score":0.5007421970367432},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.48172858357429504},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4805870056152344},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.44921472668647766},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.4485796093940735},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3445780575275421},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3007127046585083},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.24491655826568604},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.09889009594917297},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/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/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros55552.2023.10341561","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iros55552.2023.10341561","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":21,"referenced_works":["https://openalex.org/W2084447079","https://openalex.org/W2136492961","https://openalex.org/W2168947801","https://openalex.org/W2564753640","https://openalex.org/W2788862220","https://openalex.org/W2940375853","https://openalex.org/W2962890638","https://openalex.org/W2963092423","https://openalex.org/W2963525569","https://openalex.org/W2963864421","https://openalex.org/W2967727187","https://openalex.org/W3081200565","https://openalex.org/W3101875589","https://openalex.org/W3197400104","https://openalex.org/W4286374783","https://openalex.org/W4294555834","https://openalex.org/W4294562617","https://openalex.org/W6684921986","https://openalex.org/W6738483526","https://openalex.org/W6748972340","https://openalex.org/W6751535212"],"related_works":["https://openalex.org/W2357124094","https://openalex.org/W2953205341","https://openalex.org/W2387399993","https://openalex.org/W2389739210","https://openalex.org/W2348924972","https://openalex.org/W235065745","https://openalex.org/W2029935773","https://openalex.org/W2365736347","https://openalex.org/W2787754950","https://openalex.org/W1572215850"],"abstract_inverted_index":{"Traditional":[0,22],"methods":[1,23],"based":[2,54],"on":[3,43,55,63,167,190],"Lyapunov":[4,33,116],"analysis":[5],"and":[6,26,58,65,73,132,147,157,164],"learning-based":[7],"approaches":[8,50],"such":[9],"as":[10],"reinforcement":[11],"learning":[12],"(RL)":[13],"are":[14,24,170],"two":[15],"powerful":[16],"tools":[17],"in":[18,112,148,162],"visual":[19,102],"servo":[20,103],"tasks.":[21],"interpretable":[25],"their":[27],"stability":[28,77,134],"can":[29],"be":[30],"guar-anteed":[31],"by":[32,108],"analysis.":[34],"However,":[35,67],"they":[36],"tend":[37],"to":[38,52,81,100,174],"have":[39,60],"a":[40,92,98,168],"high":[41],"dependency":[42],"an":[44,119],"accurate":[45],"system":[46,110,115],"dynamic":[47],"model.":[48],"RL":[49,94,138,188],"learn":[51],"act":[53],"past":[56],"experiences":[57],"thus":[59],"higher":[61],"adaptability":[62],"disturbances":[64],"errors.":[66],"the":[68,109,123,129,137,145,149,158],"training":[69,85,97,146],"process":[70],"is":[71,78,160],"long":[72],"its":[74],"safety":[75,111],"or":[76],"generally":[79],"hard":[80],"guarantee,":[82],"making":[83],"real-world":[84,165,191],"risky.":[86],"In":[87],"this":[88,181],"paper,":[89],"we":[90],"propose":[91],"residual":[93],"framework":[95],"for":[96,122],"multicopter":[99,169],"finish":[101],"tasks":[104],"under":[105],"disturbances,":[106],"guided":[107],"terms":[113],"of":[114,125,128],"function.":[117],"Such":[118],"approach":[120,156],"compensates":[121],"lack":[124],"disturbance-rejection":[126],"ability":[127],"traditional":[130],"method,":[131],"optimizes":[133],"explicitly":[135],"so":[136],"agent":[139],"makes":[140],"safer":[141],"actions":[142],"both":[143],"during":[144],"final":[150],"policy.":[151],"A":[152],"comparison":[153],"between":[154],"our":[155,176],"baselines":[159],"provided":[161],"simulation,":[163],"experiments":[166],"also":[171],"carried":[172],"out":[173],"show":[175],"effectiveness.":[177],"We":[178],"believe":[179],"that":[180],"work":[182],"moves":[183],"one":[184],"step":[185],"toward":[186],"achieving":[187],"applications":[189],"robotic":[192],"systems.":[193]},"counts_by_year":[],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}