{"id":"https://openalex.org/W4391021818","doi":"https://doi.org/10.1109/cdc49753.2023.10383782","title":"Reinforcement Learning for Image-Based Visual Servo Control","display_name":"Reinforcement Learning for Image-Based Visual Servo Control","publication_year":2023,"publication_date":"2023-12-13","ids":{"openalex":"https://openalex.org/W4391021818","doi":"https://doi.org/10.1109/cdc49753.2023.10383782"},"language":"en","primary_location":{"id":"doi:10.1109/cdc49753.2023.10383782","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc49753.2023.10383782","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 62nd IEEE Conference on Decision and Control (CDC)","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/A5076083833","display_name":"Ashwin P. Dani","orcid":"https://orcid.org/0000-0002-7091-5607"},"institutions":[{"id":"https://openalex.org/I140172145","display_name":"University of Connecticut","ror":"https://ror.org/02der9h97","country_code":"US","type":"education","lineage":["https://openalex.org/I140172145"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashwin P. Dani","raw_affiliation_strings":["Engineering at University of Connecticut,Department of Electrical and Computer,Storrs,CT,06269"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Engineering at University of Connecticut,Department of Electrical and Computer,Storrs,CT,06269","institution_ids":["https://openalex.org/I140172145"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034219830","display_name":"Shubhendu Bhasin","orcid":"https://orcid.org/0000-0002-8002-9684"},"institutions":[{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shubhendu Bhasin","raw_affiliation_strings":["Indian Institute of Technology,Delhi","Indian Institute of Technology, Delhi"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Delhi","institution_ids":["https://openalex.org/I68891433"]},{"raw_affiliation_string":"Indian Institute of Technology, Delhi","institution_ids":["https://openalex.org/I68891433"]}]}],"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":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4358","last_page":"4363"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9800000190734863,"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/T11685","display_name":"Zebrafish Biomedical Research Applications","score":0.9689000248908997,"subfield":{"id":"https://openalex.org/subfields/1307","display_name":"Cell Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/jacobian-matrix-and-determinant","display_name":"Jacobian matrix and determinant","score":0.8855926990509033},{"id":"https://openalex.org/keywords/visual-servoing","display_name":"Visual servoing","score":0.8545323610305786},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.7632241249084473},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7514234185218811},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.679725170135498},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5625708103179932},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.48490267992019653},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.44421911239624023},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3739836812019348},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2724018692970276},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.24176010489463806},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.08109453320503235}],"concepts":[{"id":"https://openalex.org/C200331156","wikidata":"https://www.wikidata.org/wiki/Q506041","display_name":"Jacobian matrix and determinant","level":2,"score":0.8855926990509033},{"id":"https://openalex.org/C10912380","wikidata":"https://www.wikidata.org/wiki/Q527952","display_name":"Visual servoing","level":3,"score":0.8545323610305786},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.7632241249084473},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7514234185218811},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.679725170135498},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5625708103179932},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.48490267992019653},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.44421911239624023},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3739836812019348},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2724018692970276},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.24176010489463806},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.08109453320503235},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc49753.2023.10383782","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc49753.2023.10383782","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 62nd IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W68730346","https://openalex.org/W92805021","https://openalex.org/W120139811","https://openalex.org/W1483858097","https://openalex.org/W1665200104","https://openalex.org/W1975100084","https://openalex.org/W1981518010","https://openalex.org/W1983523797","https://openalex.org/W2010152647","https://openalex.org/W2024303516","https://openalex.org/W2047090868","https://openalex.org/W2047993072","https://openalex.org/W2081514674","https://openalex.org/W2082991751","https://openalex.org/W2103496339","https://openalex.org/W2104843094","https://openalex.org/W2108286682","https://openalex.org/W2111691855","https://openalex.org/W2113501460","https://openalex.org/W2124560430","https://openalex.org/W2148439597","https://openalex.org/W2168947801","https://openalex.org/W2564717627","https://openalex.org/W2772589676","https://openalex.org/W3213472335","https://openalex.org/W4237981787","https://openalex.org/W6804409665"],"related_works":["https://openalex.org/W2126852585","https://openalex.org/W2367086100","https://openalex.org/W2352270872","https://openalex.org/W2171817899","https://openalex.org/W2376367950","https://openalex.org/W213797040","https://openalex.org/W2620386921","https://openalex.org/W571470105","https://openalex.org/W1851410152","https://openalex.org/W2091554547"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"a":[3,47,51,69,116],"continuous-time":[4,52],"reinforcement":[5],"learning":[6],"(RL)-based":[7],"controller":[8,66,112],"is":[9,20,28,32,40,95,113],"developed":[10],"for":[11,49,73],"image-based":[12],"visual":[13],"servoing":[14],"(IBVS).":[15],"The":[16,55,110],"IBVS":[17],"control":[18,108],"dynamics":[19],"of":[21],"the":[22,25,36,43,74,78,86,99,104,121,124],"form":[23],"where":[24],"drift":[26],"term":[27],"absent":[29],"and":[30,81,120],"there":[31],"an":[33,58],"uncertainty":[34],"in":[35,77],"Jacobian":[37,80],"matrix":[38],"that":[39],"multiplied":[41],"with":[42,68,85,106],"input.":[44],"This":[45],"poses":[46],"challenge":[48],"developing":[50],"RL":[53,65],"controller.":[54,88],"paper":[56],"presents":[57],"actor-critic":[59],"or":[60],"synchronous":[61],"policy":[62],"iteration":[63],"(PI)-based":[64],"along":[67],"parameter":[70,76],"update":[71],"law":[72],"unknown":[75],"image":[79,101],"proves":[82],"closed-loop":[83],"stability":[84],"proposed":[87,111,125],"An":[89],"infinite-horizon":[90],"value":[91],"function":[92],"minimization":[93],"objective":[94],"achieved":[96],"by":[97],"regulating":[98],"current":[100],"features":[102],"to":[103],"desired":[105],"near-optimal":[107],"efforts.":[109],"tested":[114],"using":[115],"simulation":[117],"use":[118],"case":[119],"results":[122],"validate":[123],"theory.":[126]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}