{"id":"https://openalex.org/W4411687973","doi":"https://doi.org/10.1109/lra.2025.3583508","title":"NeuTRL: Neural Trust-Guided Reinforcement Learning for Human-Robot Collaboration","display_name":"NeuTRL: Neural Trust-Guided Reinforcement Learning for Human-Robot Collaboration","publication_year":2025,"publication_date":"2025-06-26","ids":{"openalex":"https://openalex.org/W4411687973","doi":"https://doi.org/10.1109/lra.2025.3583508"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2025.3583508","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3583508","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","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/A5048932613","display_name":"Caiyue Xu","orcid":"https://orcid.org/0000-0002-2070-1475"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Caiyue Xu","raw_affiliation_strings":["Department of Control Science and Engineering, Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Control Science and Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000024164","display_name":"Hongrui Sang","orcid":"https://orcid.org/0000-0002-8026-1328"},"institutions":[{"id":"https://openalex.org/I96733725","display_name":"Shanghai Maritime University","ror":"https://ror.org/04z7qrj66","country_code":"CN","type":"education","lineage":["https://openalex.org/I96733725"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongrui Sang","raw_affiliation_strings":["School of Logistics Engineering, Shanghai Maritime University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Logistics Engineering, Shanghai Maritime University, Shanghai, China","institution_ids":["https://openalex.org/I96733725"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100639342","display_name":"Changming Zhang","orcid":"https://orcid.org/0009-0001-3285-0072"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changming Zhang","raw_affiliation_strings":["Department of Control Science and Engineering, Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Control Science and Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032983330","display_name":"Yanmin Zhou","orcid":"https://orcid.org/0000-0001-7824-1179"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Zhou","raw_affiliation_strings":["Department of Control Science and Engineering, Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Control Science and Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100424178","display_name":"Zhipeng Wang","orcid":"https://orcid.org/0000-0003-4632-9170"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhipeng Wang","raw_affiliation_strings":["Department of Control Science and Engineering, Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Control Science and Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100354039","display_name":"Xin Li","orcid":"https://orcid.org/0000-0003-2067-2763"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Li","raw_affiliation_strings":["Department of Control Science and Engineering, Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Control Science and Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049557511","display_name":"Bin He","orcid":"https://orcid.org/0000-0003-3193-6269"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin He","raw_affiliation_strings":["Department of Control Science and Engineering, Tongji University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Control Science and Engineering, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5048932613"],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":null,"apc_paid":null,"fwci":4.9978,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.95295758,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"10","issue":"8","first_page":"8155","last_page":"8162"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.8364999890327454,"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":0.8364999890327454,"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/T10525","display_name":"Human-Automation Interaction and Safety","score":0.8057000041007996,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7896000146865845,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.751502275466919},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5333659052848816},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5193289518356323},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5126327872276306},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.48809492588043213},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4580068290233612},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3951248526573181},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.14066079258918762}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.751502275466919},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5333659052848816},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5193289518356323},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5126327872276306},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48809492588043213},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4580068290233612},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3951248526573181},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.14066079258918762}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2025.3583508","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3583508","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","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":28,"referenced_works":["https://openalex.org/W1453801241","https://openalex.org/W2101409192","https://openalex.org/W2107726111","https://openalex.org/W2135907989","https://openalex.org/W2152304295","https://openalex.org/W2154018708","https://openalex.org/W2794595230","https://openalex.org/W2904276816","https://openalex.org/W2914120968","https://openalex.org/W2951360122","https://openalex.org/W2963489214","https://openalex.org/W2969622979","https://openalex.org/W3012435612","https://openalex.org/W3113465503","https://openalex.org/W3202542428","https://openalex.org/W4206622711","https://openalex.org/W4241874243","https://openalex.org/W4400770903","https://openalex.org/W4401240926","https://openalex.org/W4401415348","https://openalex.org/W6732417791","https://openalex.org/W6739585900","https://openalex.org/W6767914801","https://openalex.org/W6784131548","https://openalex.org/W6796168157","https://openalex.org/W6810738896","https://openalex.org/W6855173278","https://openalex.org/W6863618527"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"Reinforcement":[0,65],"Learning":[1,66],"from":[2,77],"Human":[3],"Feedback":[4],"(RLHF)":[5],"enables":[6,132],"robots":[7,133],"to":[8,40,96,99,119,134,167,177,197],"learn":[9,135],"cooperative":[10,188],"strategies":[11],"aligned":[12],"with":[13],"human":[14,54,74,170],"expectations":[15],"by":[16],"incorporating":[17],"feedback":[18,41,47,83,145,171],"into":[19],"the":[20,106,121,144],"learning":[21],"process.":[22],"However,":[23],"existing":[24],"RLHF":[25],"methods":[26],"rely":[27],"on":[28],"explicit":[29],"query-based":[30,178],"feedback,":[31,142],"which":[32],"is":[33],"limited":[34],"for":[35,84],"complex,":[36],"long-horizon":[37],"tasks":[38],"due":[39],"sparsity":[42,146],"and":[43,52,87,127,172,190],"delay.":[44],"Additionally,":[45,109],"active":[46],"collection":[48],"disrupts":[49],"task":[50,164],"execution":[51],"increases":[53],"cognitive":[55],"load.":[56],"To":[57],"address":[58],"these":[59],"challenges,":[60],"we":[61,110],"propose":[62,111],"Neural":[63],"Trust-guided":[64],"(NeuTRL),":[67],"a":[68,92,112,158,173],"novel":[69],"human-in-the-loop":[70],"framework":[71],"that":[72,155,184],"utilizes":[73],"trust,":[75],"derived":[76],"electroencephalography":[78],"(EEG)":[79],"signals,":[80],"as":[81],"implicit":[82],"reward":[85,117],"shaping":[86],"policy":[88],"optimization.":[89],"NeuTRL":[90,131,156,185],"incorporates":[91],"deep":[93],"neural":[94],"network":[95],"map":[97],"EEG":[98],"trust":[100,125,141],"states,":[101],"enabling":[102],"high-frequency":[103],"evaluations":[104],"of":[105,124],"robot's":[107],"behavior.":[108],"Long":[113],"Short-Term":[114],"Memory":[115],"(LSTM)-based":[116],"model":[118],"capture":[120],"temporal":[122],"dynamics":[123],"evolution":[126],"generate":[128],"dense":[129,139],"rewards.":[130],"collaborative":[136,163],"policies":[137],"using":[138],"EEG-based":[140],"addressing":[143],"challenge":[147],"while":[148],"maintaining":[149],"uninterrupted":[150],"interaction.":[151],"Experimental":[152],"results":[153,193],"demonstrate":[154],"achieves":[157],"74.5%":[159],"improvement":[160,175],"in":[161,203],"average":[162],"performance":[165],"compared":[166,176],"baselines":[168],"without":[169],"26.9%":[174],"RLHF.":[179],"Qualitative":[180],"analysis":[181],"further":[182],"reveals":[183],"significantly":[186],"enhances":[187],"adaptability":[189],"coordination.":[191],"These":[192],"highlight":[194],"NeuTRL's":[195],"potential":[196],"advance":[198],"trust-aware,":[199],"adaptive":[200],"human-robot":[201],"collaboration":[202],"dynamic":[204],"environments.":[205]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-25T14:56:36.534964","created_date":"2025-10-10T00:00:00"}