{"id":"https://openalex.org/W7133542516","doi":"https://doi.org/10.1109/tcyb.2026.3668072","title":"Knowledge Distillation and Reinforcement Learning in a Human--Machine Collaboration Delivery System With a Robotic Arm","display_name":"Knowledge Distillation and Reinforcement Learning in a Human--Machine Collaboration Delivery System With a Robotic Arm","publication_year":2026,"publication_date":"2026-03-04","ids":{"openalex":"https://openalex.org/W7133542516","doi":"https://doi.org/10.1109/tcyb.2026.3668072","pmid":"https://pubmed.ncbi.nlm.nih.gov/41779648"},"language":"en","primary_location":{"id":"doi:10.1109/tcyb.2026.3668072","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2026.3668072","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"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 Cybernetics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5061491967","display_name":"Ping\u2010Huan Kuo","orcid":"https://orcid.org/0000-0001-5125-4420"},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ping-Huan Kuo","raw_affiliation_strings":["National Cheng Kung University"],"raw_orcid":"https://orcid.org/0000-0001-5125-4420","affiliations":[{"raw_affiliation_string":"National Cheng Kung University","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128083473","display_name":"Po-Hsun Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Po-Hsun Feng","raw_affiliation_strings":["National Cheng Kung University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Cheng Kung University","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067672903","display_name":"Chen-Wen Chang","orcid":"https://orcid.org/0000-0002-5148-5103"},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chen-Wen Chang","raw_affiliation_strings":["National Cheng Kung University"],"raw_orcid":"https://orcid.org/0000-0002-5148-5103","affiliations":[{"raw_affiliation_string":"National Cheng Kung University","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100860279","display_name":"Yu-Sian Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Sian Lin","raw_affiliation_strings":["National Cheng Kung University"],"raw_orcid":"https://orcid.org/0009-0009-7673-7715","affiliations":[{"raw_affiliation_string":"National Cheng Kung University","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128092622","display_name":"Yu-Chih Chiu","orcid":null},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Chih Chiu","raw_affiliation_strings":["National Cheng Kung University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Cheng Kung University","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5128095567","display_name":"Bang-Yu Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Bang-Yu Chen","raw_affiliation_strings":["National Cheng Kung University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Cheng Kung University","institution_ids":["https://openalex.org/I91807558"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I91807558"],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":3.7692,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.91238034,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"56","issue":"8","first_page":"4456","last_page":"4469"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.45730000734329224,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.45730000734329224,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.06459999829530716,"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/T10820","display_name":"Fuzzy Logic and Control Systems","score":0.019500000402331352,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/robotic-arm","display_name":"Robotic arm","score":0.5636000037193298},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4584999978542328},{"id":"https://openalex.org/keywords/knowledge-based-systems","display_name":"Knowledge-based systems","score":0.33730000257492065},{"id":"https://openalex.org/keywords/delivery-system","display_name":"Delivery system","score":0.3278999924659729},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.3206999897956848},{"id":"https://openalex.org/keywords/control-system","display_name":"Control system","score":0.320499986410141},{"id":"https://openalex.org/keywords/expert-system","display_name":"Expert system","score":0.3082999885082245}],"concepts":[{"id":"https://openalex.org/C150415221","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic arm","level":2,"score":0.5636000037193298},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5273000001907349},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4584999978542328},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.38589999079704285},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.382999986410141},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.33730000257492065},{"id":"https://openalex.org/C2983812674","wikidata":"https://www.wikidata.org/wiki/Q134808","display_name":"Delivery system","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3206999897956848},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.320499986410141},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C2777220311","wikidata":"https://www.wikidata.org/wiki/Q6423340","display_name":"Knowledge acquisition","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.2705000042915344},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.26440000534057617},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.2558000087738037},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2558000087738037},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2526000142097473},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.2513999938964844}],"mesh":[{"descriptor_ui":"D000098408","descriptor_name":"Reinforcement Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000098408","descriptor_name":"Reinforcement Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000098842","descriptor_name":"Generative Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098842","descriptor_name":"Generative Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006225","descriptor_name":"Hand","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D006225","descriptor_name":"Hand","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008328","descriptor_name":"Man-Machine Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008328","descriptor_name":"Man-Machine Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012371","descriptor_name":"Robotics","qualifier_ui":"Q000295","qualifier_name":"instrumentation","is_major_topic":true},{"descriptor_ui":"D012371","descriptor_name":"Robotics","qualifier_ui":"Q000295","qualifier_name":"instrumentation","is_major_topic":true},{"descriptor_ui":"D012371","descriptor_name":"Robotics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D012371","descriptor_name":"Robotics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1109/tcyb.2026.3668072","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2026.3668072","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"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 Cybernetics","raw_type":"journal-article"},{"id":"pmid:41779648","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41779648","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on cybernetics","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2904246096","https://openalex.org/W2948175577","https://openalex.org/W2962793481","https://openalex.org/W3012522386","https://openalex.org/W3022324591","https://openalex.org/W3035756007","https://openalex.org/W3088310808","https://openalex.org/W3114952123","https://openalex.org/W3138129477","https://openalex.org/W3190316676","https://openalex.org/W3203417057","https://openalex.org/W3212646593","https://openalex.org/W4285293961","https://openalex.org/W4306910464","https://openalex.org/W4315489230","https://openalex.org/W4384158393","https://openalex.org/W4385938168","https://openalex.org/W4386523657","https://openalex.org/W4386758039","https://openalex.org/W4387965994","https://openalex.org/W4389665592","https://openalex.org/W4396875110","https://openalex.org/W4399487247","https://openalex.org/W4404952750","https://openalex.org/W4406028217","https://openalex.org/W4412588144","https://openalex.org/W4412693609","https://openalex.org/W4415048303","https://openalex.org/W4415222173","https://openalex.org/W4416010682","https://openalex.org/W4416707410","https://openalex.org/W7125580764"],"related_works":[],"abstract_inverted_index":{"Robotic":[0],"arms":[1,24,35,199],"are":[2],"widely":[3],"used":[4],"in":[5,30,39,113,172,200],"various":[6],"aspects":[7],"of":[8,14,22,152,169,181],"human-robot":[9,170],"collaboration.":[10],"The":[11,160],"primary":[12],"goal":[13],"this":[15,57,123,176],"study":[16,58,124,177],"is":[17],"to":[18,28,46,63,80,117,127],"explore":[19],"the":[20,103,120,138,145,155,165,179],"usability":[21],"robotic":[23,34,198],"for":[25,197],"delivering":[26],"objects":[27],"humans":[29],"dynamic":[31,47,202],"environments.":[32],"Traditional":[33],"often":[36],"face":[37],"limitations":[38],"path":[40,82],"planning,":[41],"such":[42],"as":[43],"difficulties":[44],"adapting":[45],"environments":[48],"and":[49,76,94,107,167,186,193],"complex":[50,173],"developmental":[51],"processes.":[52],"To":[53],"overcome":[54],"these":[55],"challenges,":[56],"employs":[59],"reinforcement":[60],"learning":[61],"(RL)":[62],"train":[64],"four":[65],"models-the":[66],"Approach":[67],"RL":[68,71,74,147],"Model,":[69,72,75],"Delivery":[70],"Decision":[73,146],"Merged":[77,156],"Model-as":[78],"alternatives":[79],"conventional":[81],"planning":[83],"control.":[84],"Typically,":[85],"there":[86],"exists":[87],"a":[88,191],"significant":[89],"discrepancy":[90],"between":[91,105],"simulated":[92],"data":[93],"real-world":[95],"features.":[96,115],"Although":[97],"image":[98,184,187],"segmentation":[99],"can":[100],"substantially":[101],"reduce":[102],"gap":[104],"virtual":[106,133],"real":[108,129],"environments,":[109],"notable":[110],"differences":[111],"remain":[112],"hand":[114,130,134],"Therefore,":[116],"further":[118],"bridge":[119],"simulation-to-reality":[121],"gap,":[122],"applies":[125],"CycleGAN":[126],"transform":[128],"features":[131],"into":[132],"features,":[135],"thereby":[136],"enhancing":[137],"model's":[139],"transferability.":[140],"Experimental":[141],"results":[142],"show":[143],"that":[144],"Model":[148,157],"achieved":[149,158],"an":[150],"accuracy":[151,168],"99.17%,":[153],"while":[154],"99.92%.":[159],"proposed":[161],"method":[162],"effectively":[163],"improves":[164],"stability":[166],"collaboration":[171],"scenarios.":[174],"Overall,":[175],"validates":[178],"feasibility":[180],"integrating":[182],"RL,":[183],"segmentation,":[185],"translation":[188],"techniques,":[189],"offering":[190],"scalable":[192],"efficient":[194],"task-solving":[195],"solution":[196],"highly":[201],"application":[203],"domains.":[204]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-03-05T00:00:00"}