{"id":"https://openalex.org/W4404088773","doi":"https://doi.org/10.48550/arxiv.2410.15554","title":"A Plug-and-Play Fully On-the-Job Real-Time Reinforcement Learning\n Algorithm for a Direct-Drive Tandem-Wing Experiment Platforms Under Multiple\n Random Operating Conditions","display_name":"A Plug-and-Play Fully On-the-Job Real-Time Reinforcement Learning\n Algorithm for a Direct-Drive Tandem-Wing Experiment Platforms Under Multiple\n Random Operating Conditions","publication_year":2024,"publication_date":"2024-10-20","ids":{"openalex":"https://openalex.org/W4404088773","doi":"https://doi.org/10.48550/arxiv.2410.15554"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.15554","pdf_url":"http://arxiv.org/pdf/2410.15554","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"type":"preprint","type_crossref":"posted-content","indexed_in":["arxiv"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://arxiv.org/pdf/2410.15554","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100782594","display_name":"Minghao Zhang","orcid":"https://orcid.org/0000-0002-3366-0465"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minghao, Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019865106","display_name":"Bifeng Song","orcid":"https://orcid.org/0000-0002-1511-8381"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bifeng, Song","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103178459","display_name":"Yang Xiao-jun","orcid":"https://orcid.org/0000-0001-7157-7390"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaojun, Yang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100456505","display_name":"Liang Wang","orcid":"https://orcid.org/0000-0002-1566-9546"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang, Wang","raw_affiliation_strings":[],"affiliations":[]}],"institution_assertions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":0,"max":81},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9395,"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":0.9395,"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/T12125","display_name":"Aerospace and Aviation Technology","score":0.9339,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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":0.9313,"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/tandem","display_name":"Tandem","score":0.63686603},{"id":"https://openalex.org/keywords/spark-plug","display_name":"Spark plug","score":0.5094636},{"id":"https://openalex.org/keywords/plug-in","display_name":"Plug-in","score":0.49126095}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.66578203},{"id":"https://openalex.org/C2777814067","wikidata":"https://www.wikidata.org/wiki/Q1752317","display_name":"Tandem","level":2,"score":0.63686603},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5907245},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.54417294},{"id":"https://openalex.org/C97257150","wikidata":"https://www.wikidata.org/wiki/Q161358","display_name":"Wing","level":2,"score":0.5227556},{"id":"https://openalex.org/C164205550","wikidata":"https://www.wikidata.org/wiki/Q193340","display_name":"Spark plug","level":2,"score":0.5094636},{"id":"https://openalex.org/C4924752","wikidata":"https://www.wikidata.org/wiki/Q184148","display_name":"Plug-in","level":2,"score":0.49126095},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.36193278},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34867197},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.22176701},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.15921995},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.14710516},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.1311684},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.06800154}],"mesh":[],"locations_count":1,"locations":[{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.15554","pdf_url":"http://arxiv.org/pdf/2410.15554","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.15554","pdf_url":"http://arxiv.org/pdf/2410.15554","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W47352601","https://openalex.org/W4287378204","https://openalex.org/W4240705470","https://openalex.org/W2981957539","https://openalex.org/W2945311252","https://openalex.org/W2545422590","https://openalex.org/W2461489085","https://openalex.org/W2051353479","https://openalex.org/W1976929361","https://openalex.org/W1908382039"],"abstract_inverted_index":{"The":[0,92,161],"nonlinear":[1],"and":[2,73,101,125,180,194,223],"unstable":[3],"aerodynamic":[4],"interference":[5],"generated":[6],"by":[7,112],"the":[8,31,71,74,77,96,105,119,155,172,177,186,191,204,214],"tandem":[9],"wings":[10],"of":[11,76,164],"such":[12],"biomimetic":[13],"systems":[14],"poses":[15],"substantial":[16],"challenges":[17],"for":[18,66],"motion":[19],"control,":[20],"especially":[21,200],"under":[22,83,138],"multiple":[23],"random":[24,140],"operating":[25,86,141],"conditions.":[26],"To":[27,69],"address":[28],"these":[29],"challenges,":[30],"Concerto":[32,156],"Reinforcement":[33,157],"Learning":[34,158],"Extension":[35],"(CRL2E)":[36],"algorithm":[37,48,98,174,188],"has":[38],"been":[39],"developed.":[40],"This":[41],"plug-and-play,":[42],"fully":[43],"on-the-job,":[44],"real-time":[45,67,228],"reinforcement":[46],"learning":[47],"incorporates":[49],"a":[50,58,62],"novel":[51],"Physics-Inspired":[52],"Rule-Based":[53],"Policy":[54,123,130],"Composer":[55,178,192],"Strategy":[56],"with":[57,143,175],"Perturbation":[59,179,193,197],"Module":[60],"alongside":[61],"lightweight":[63,216],"network":[64,217],"optimized":[65,215],"control.":[68],"validate":[70],"performance":[72,137],"rationality":[75],"module":[78],"design,":[79],"experiments":[80],"were":[81],"conducted":[82],"six":[84],"challenging":[85],"conditions,":[87,142],"comparing":[88],"seven":[89],"different":[90],"algorithms.":[91,132],"results":[93],"demonstrate":[94],"that":[95,213],"CRL2E":[97,134,165],"achieves":[99],"safe":[100],"stable":[102],"training":[103],"within":[104],"first":[106],"500":[107],"steps,":[108],"improving":[109],"tracking":[110,146],"accuracy":[111,147],"14":[113],"to":[114,118,151,154,168,182,208],"66":[115],"times":[116],"compared":[117,153],"Soft":[120],"Actor-Critic,":[121],"Proximal":[122],"Optimization,":[124],"Twin":[126],"Delayed":[127],"Deep":[128],"Deterministic":[129],"Gradient":[131],"Additionally,":[133],"significantly":[135],"enhances":[136],"various":[139],"improvements":[144],"in":[145,201,220],"ranging":[148],"from":[149],"8.3%":[150],"60.4%":[152],"(CRL)":[159],"algorithm.":[160],"convergence":[162],"speed":[163],"is":[166],"36.11%":[167],"57.64%":[169],"faster":[170,184],"than":[171,185],"CRL":[173,187,206],"only":[176],"43.52%":[181],"65.85%":[183],"when":[189],"both":[190],"Time-Interleaved":[195],"Capability":[196],"are":[198],"introduced,":[199],"conditions":[202],"where":[203],"standard":[205],"struggles":[207],"converge.":[209],"Hardware":[210],"tests":[211],"indicate":[212],"structure":[218],"excels":[219],"weight":[221],"loading":[222],"average":[224],"inference":[225],"time,":[226],"meeting":[227],"control":[229],"requirements.":[230]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4404088773","counts_by_year":[],"updated_date":"2025-02-13T06:26:49.868940","created_date":"2024-11-06"}