{"id":"https://openalex.org/W4414110515","doi":"https://doi.org/10.1109/tase.2025.3608352","title":"Reinforcement Learning-Based Optimal Formation Control for Multiple WMRs With Visual Servoing","display_name":"Reinforcement Learning-Based Optimal Formation Control for Multiple WMRs With Visual Servoing","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4414110515","doi":"https://doi.org/10.1109/tase.2025.3608352"},"language":"en","primary_location":{"id":"doi:10.1109/tase.2025.3608352","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2025.3608352","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automation Science and Engineering","raw_type":"journal-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/A5012004938","display_name":"Biao Luo","orcid":"https://orcid.org/0000-0002-3353-2586"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Biao Luo","raw_affiliation_strings":["School of Automation, Central South University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-3353-2586","affiliations":[{"raw_affiliation_string":"School of Automation, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101761764","display_name":"Yuhao Zhou","orcid":"https://orcid.org/0000-0002-4004-1195"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhao Zhou","raw_affiliation_strings":["School of Automation, Central South University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-4004-1195","affiliations":[{"raw_affiliation_string":"School of Automation, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100383276","display_name":"Lin Liu","orcid":"https://orcid.org/0000-0002-0107-5819"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Liu","raw_affiliation_strings":["School of Automation, Central South University, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120391740","display_name":"Jialin Xiao","orcid":"https://orcid.org/0000-0003-1433-5437"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jialin Xiao","raw_affiliation_strings":["School of Automation, Central South University, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040076424","display_name":"Bing-Chuan Wang","orcid":"https://orcid.org/0000-0002-0234-2843"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing-Chuan Wang","raw_affiliation_strings":["School of Automation, Central South University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-0234-2843","affiliations":[{"raw_affiliation_string":"School of Automation, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101971818","display_name":"Chunhua Yang","orcid":"https://orcid.org/0000-0002-3770-9887"},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunhua Yang","raw_affiliation_strings":["School of Automation, Central South University, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-3770-9887","affiliations":[{"raw_affiliation_string":"School of Automation, Central South University, Changsha, China","institution_ids":["https://openalex.org/I139660479"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139660479"],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":1.1744,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.81553358,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"22","issue":null,"first_page":"21284","last_page":"21295"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11498","display_name":"Security in Wireless Sensor Networks","score":0.958899974822998,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11498","display_name":"Security in Wireless Sensor Networks","score":0.958899974822998,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.953000009059906,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.6984000205993652},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6340000033378601},{"id":"https://openalex.org/keywords/visual-servoing","display_name":"Visual servoing","score":0.5968999862670898},{"id":"https://openalex.org/keywords/kinematics","display_name":"Kinematics","score":0.5884000062942505},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.5855000019073486},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.5220999717712402},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5149000287055969},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.49239999055862427},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.48890000581741333},{"id":"https://openalex.org/keywords/tracking-error","display_name":"Tracking error","score":0.4862000048160553}],"concepts":[{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.6984000205993652},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6340000033378601},{"id":"https://openalex.org/C10912380","wikidata":"https://www.wikidata.org/wiki/Q527952","display_name":"Visual servoing","level":3,"score":0.5968999862670898},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5924999713897705},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.5884000062942505},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.5855000019073486},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5220999717712402},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5149000287055969},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.49239999055862427},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.48890000581741333},{"id":"https://openalex.org/C183356978","wikidata":"https://www.wikidata.org/wiki/Q1779213","display_name":"Tracking error","level":3,"score":0.4862000048160553},{"id":"https://openalex.org/C60640748","wikidata":"https://www.wikidata.org/wiki/Q2337858","display_name":"Lyapunov function","level":3,"score":0.4672999978065491},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.45730000734329224},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.41929998993873596},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4032000005245209},{"id":"https://openalex.org/C2776829284","wikidata":"https://www.wikidata.org/wiki/Q1341651","display_name":"Lyapunov stability","level":3,"score":0.39010000228881836},{"id":"https://openalex.org/C117619785","wikidata":"https://www.wikidata.org/wiki/Q6094414","display_name":"Iterative learning control","level":3,"score":0.37790000438690186},{"id":"https://openalex.org/C122383733","wikidata":"https://www.wikidata.org/wiki/Q865920","display_name":"Approximation error","level":2,"score":0.36480000615119934},{"id":"https://openalex.org/C74222875","wikidata":"https://www.wikidata.org/wiki/Q16000312","display_name":"Robot kinematics","level":4,"score":0.3560999929904938},{"id":"https://openalex.org/C167964875","wikidata":"https://www.wikidata.org/wiki/Q17011487","display_name":"Exponential stability","level":3,"score":0.337799996137619},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.32199999690055847},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.31869998574256897},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.3109000027179718},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.30880001187324524},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C107464732","wikidata":"https://www.wikidata.org/wiki/Q235781","display_name":"Adaptive control","level":3,"score":0.28209999203681946},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.27970001101493835},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.26499998569488525},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2556000053882599},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.2556000053882599},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.2549999952316284},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.25429999828338623}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tase.2025.3608352","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2025.3608352","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automation Science and Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1342224670","display_name":null,"funder_award_id":"U2341216","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3329652486","display_name":null,"funder_award_id":"2024RC1011","funder_id":"https://openalex.org/F4320330206","funder_display_name":"Science and Technology Program of Hunan Province"},{"id":"https://openalex.org/G5886857171","display_name":null,"funder_award_id":"62373375","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320330206","display_name":"Science and Technology Program of Hunan Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1907796993","https://openalex.org/W1980765536","https://openalex.org/W1983523797","https://openalex.org/W2033699235","https://openalex.org/W2047090868","https://openalex.org/W2095035710","https://openalex.org/W2097671019","https://openalex.org/W2106129306","https://openalex.org/W2335825547","https://openalex.org/W2345110532","https://openalex.org/W2466393651","https://openalex.org/W2484646121","https://openalex.org/W2520467133","https://openalex.org/W2550394442","https://openalex.org/W2555485441","https://openalex.org/W2912259603","https://openalex.org/W2943764792","https://openalex.org/W2951171829","https://openalex.org/W2974430893","https://openalex.org/W3005171747","https://openalex.org/W3015087125","https://openalex.org/W3089091488","https://openalex.org/W3201480909","https://openalex.org/W4213427794","https://openalex.org/W4224036449","https://openalex.org/W4226033453","https://openalex.org/W4285116591","https://openalex.org/W4313146255","https://openalex.org/W4320008682","https://openalex.org/W4362689374","https://openalex.org/W4366168973","https://openalex.org/W4377971518","https://openalex.org/W4380520057","https://openalex.org/W4382203359","https://openalex.org/W4383220183","https://openalex.org/W4388895126","https://openalex.org/W4394730929","https://openalex.org/W4401506918","https://openalex.org/W4402568700"],"related_works":["https://openalex.org/W2126852585","https://openalex.org/W2367086100","https://openalex.org/W2352270872","https://openalex.org/W1520171478","https://openalex.org/W2386520554","https://openalex.org/W3024380338","https://openalex.org/W4317830657","https://openalex.org/W2127866683","https://openalex.org/W2065095941","https://openalex.org/W110066474"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"a":[3,25,143],"reinforcement":[4],"learning":[5],"(RL)":[6],"control":[7,14,110],"method":[8,88,111],"is":[9,29,50,63,76,89,98,132],"developed":[10,160],"for":[11],"the":[12,33,39,43,55,60,66,72,80,85,93,127,135,140,147,156,159],"formation":[13,113],"of":[15,36,158],"multiple":[16],"wheeled":[17],"mobile":[18,37],"robots":[19,137],"(WMRs)":[20],"with":[21],"visual":[22],"servoing.":[23],"First,":[24],"multi-robot":[26],"system":[27],"model":[28],"constructed":[30],"based":[31,78],"on":[32,79],"kinematic":[34],"models":[35],"robots,":[38],"camera":[40],"model,":[41],"and":[42,71,115,146],"multiple-view":[44],"geometry":[45],"principles.":[46],"The":[47,107,152],"leader-follower":[48],"structure":[49],"then":[51],"applied":[52],"to":[53,91],"derive":[54],"distributed":[56],"error":[57,61,75,149],"system.":[58],"Next,":[59],"term":[62],"separated":[64],"from":[65],"optimal":[67],"performance":[68,116],"index":[69],"function,":[70],"Bellman":[73],"residual":[74],"obtained":[77],"Hamilton-Jacobi-Bellman":[81],"equation":[82],"(HJBE).":[83],"Subsequently,":[84],"gradient":[86],"descent":[87],"employed":[90],"design":[92],"weight":[94],"update":[95],"rate,":[96],"which":[97,119],"implemented":[99],"in":[100,142],"an":[101],"actor-critic":[102],"neural":[103],"network":[104],"(NN)":[105],"architecture.":[106],"proposed":[108],"RL":[109],"achieves":[112],"tracking":[114,148],"optimization":[117],"simultaneously,":[118],"previous":[120],"approaches":[121],"have":[122],"not":[123],"accomplished.":[124],"Furthermore,":[125],"under":[126],"Lyapunov":[128],"stability":[129],"theory,":[130],"it":[131],"proven":[133],"that":[134],"follower":[136],"can":[138],"track":[139],"leader":[141],"predefined":[144],"formation,":[145],"converges":[150],"ultimately.":[151],"simulation":[153],"outcomes":[154],"verify":[155],"effectiveness":[157],"approach.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}