{"id":"https://openalex.org/W4412515741","doi":"https://doi.org/10.1007/s12369-025-01287-6","title":"Multimodal Reinforcement Learning for Robots Collaborating with Humans","display_name":"Multimodal Reinforcement Learning for Robots Collaborating with Humans","publication_year":2025,"publication_date":"2025-07-21","ids":{"openalex":"https://openalex.org/W4412515741","doi":"https://doi.org/10.1007/s12369-025-01287-6"},"language":"en","primary_location":{"id":"doi:10.1007/s12369-025-01287-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s12369-025-01287-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s12369-025-01287-6.pdf","source":{"id":"https://openalex.org/S168738021","display_name":"International Journal of Social Robotics","issn_l":"1875-4791","issn":["1875-4791","1875-4805"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Social Robotics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s12369-025-01287-6.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046069451","display_name":"Afagh Mehri Shervedani","orcid":null},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Afagh Mehri Shervedani","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Illinois Chicago, Chicago, IL, USA"],"raw_orcid":"https://orcid.org/0009-0007-9554-0681","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I39422238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100436431","display_name":"Siyu Li","orcid":"https://orcid.org/0000-0002-0976-9938"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siyu Li","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Illinois Chicago, Chicago, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I39422238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032630946","display_name":"Natawut Monaikul","orcid":"https://orcid.org/0000-0003-0439-8127"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Natawut Monaikul","raw_affiliation_strings":["Department of Computer Science, University of Illinois Chicago, Chicago, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Illinois Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I39422238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050538031","display_name":"Bahareh Abbasi","orcid":null},"institutions":[{"id":"https://openalex.org/I194388944","display_name":"California State University, Channel Islands","ror":"https://ror.org/04v097707","country_code":"US","type":"education","lineage":["https://openalex.org/I194388944"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bahareh Abbasi","raw_affiliation_strings":["Computer Science Department, California State University Channel Islands, Camarillo, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, California State University Channel Islands, Camarillo, CA, USA","institution_ids":["https://openalex.org/I194388944"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062331167","display_name":"Milo\u0161 \u017defran","orcid":"https://orcid.org/0000-0001-9558-3656"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Milo\u0161 \u017defran","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Illinois Chicago, Chicago, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Illinois Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I39422238"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055258367","display_name":"Barbara Di Eugenio","orcid":"https://orcid.org/0000-0003-1706-2577"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Barbara Di Eugenio","raw_affiliation_strings":["Department of Computer Science, University of Illinois Chicago, Chicago, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Illinois Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I39422238"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5046069451"],"corresponding_institution_ids":["https://openalex.org/I39422238"],"apc_list":{"value":2890,"currency":"EUR","value_usd":3690},"apc_paid":{"value":2890,"currency":"EUR","value_usd":3690},"fwci":1.8819,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85981078,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"17","issue":"12","first_page":"3003","last_page":"3025"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.9995999932289124,"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":0.9994000196456909,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.998199999332428,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.6856194138526917},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.6542752385139465},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6071014404296875},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5451478362083435},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.491811066865921},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.47594666481018066}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6856194138526917},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.6542752385139465},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6071014404296875},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5451478362083435},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.491811066865921},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47594666481018066}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s12369-025-01287-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s12369-025-01287-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s12369-025-01287-6.pdf","source":{"id":"https://openalex.org/S168738021","display_name":"International Journal of Social Robotics","issn_l":"1875-4791","issn":["1875-4791","1875-4805"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Social Robotics","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s12369-025-01287-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s12369-025-01287-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s12369-025-01287-6.pdf","source":{"id":"https://openalex.org/S168738021","display_name":"International Journal of Social Robotics","issn_l":"1875-4791","issn":["1875-4791","1875-4805"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Social Robotics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3229348200","display_name":null,"funder_award_id":"ECCS-2217023","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G330142691","display_name":null,"funder_award_id":"2217023","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3514232042","display_name":"RI: Medium: An Interaction Manager for Language and Force Exhanges in Human-Robot Physical Collaboration","funder_award_id":"1705058","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3963574240","display_name":"CIF: Small: MoDL: Interpreting Deep-Learned Error-Correcting Codes","funder_award_id":"2240532","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5346014613","display_name":"Collaborative Research: Single-Input Control of Large Microrobot Swarms using Serial Addressing for Microassembly and Biomedical Applications","funder_award_id":"1762924","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337391","display_name":"Division of Civil, Mechanical and Manufacturing Innovation","ror":"https://ror.org/028yd4c30"},{"id":"https://openalex.org/F4320337392","display_name":"Division of Electrical, Communications and Cyber Systems","ror":"https://ror.org/01krpsy48"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412515741.pdf","grobid_xml":"https://content.openalex.org/works/W4412515741.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W159980283","https://openalex.org/W1969897050","https://openalex.org/W1972978214","https://openalex.org/W2032100464","https://openalex.org/W2044663075","https://openalex.org/W2060245136","https://openalex.org/W2081105960","https://openalex.org/W2104308387","https://openalex.org/W2110316024","https://openalex.org/W2145339207","https://openalex.org/W2147357263","https://openalex.org/W2159306398","https://openalex.org/W2168745915","https://openalex.org/W2740011803","https://openalex.org/W2788862220","https://openalex.org/W2905180035","https://openalex.org/W2962776342","https://openalex.org/W2962787969","https://openalex.org/W2963567240","https://openalex.org/W3003608599","https://openalex.org/W3036876381","https://openalex.org/W3093628840","https://openalex.org/W3095030303","https://openalex.org/W3161207330","https://openalex.org/W4206513913","https://openalex.org/W4236654622","https://openalex.org/W4252684946","https://openalex.org/W4290742115","https://openalex.org/W4309698321","https://openalex.org/W4388624140","https://openalex.org/W4389519260","https://openalex.org/W4391094120","https://openalex.org/W4401042567","https://openalex.org/W4401413881","https://openalex.org/W4401415431","https://openalex.org/W4402727730"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W4233452137","https://openalex.org/W4254857216","https://openalex.org/W4231626925","https://openalex.org/W2962829499","https://openalex.org/W2767518918","https://openalex.org/W2131444840","https://openalex.org/W2414929284","https://openalex.org/W4391539200","https://openalex.org/W192849109"],"abstract_inverted_index":{"Abstract":[0],"Robot":[1],"assistants":[2],"for":[3,47,69,212],"older":[4],"adults":[5],"and":[6,33,37,44,131,156,173,199,209],"people":[7],"with":[8,15,149,159],"disabilities":[9],"need":[10],"to":[11,31,50,58,97,134,141,177],"perform":[12],"collaborative":[13],"tasks":[14],"users":[16],"effectively.":[17],"The":[18],"core":[19],"component":[20],"of":[21,41,55,61,81,103],"these":[22],"systems":[23,72],"is":[24,30,73,86,147],"an":[25],"interaction":[26,214],"manager":[27],"whose":[28],"job":[29],"observe":[32],"assess":[34],"the":[35,39,42,48,52,59,62,67,79,100,104,136,180,187],"task":[36,201],"infer":[38],"state":[40],"human":[43,154,184],"their":[45],"intent":[46],"robot":[49,115],"choose":[51],"best":[53,137],"course":[54],"action.":[56,138],"Due":[57],"sparseness":[60],"data":[63,155],"in":[64,119,189,216],"this":[65,84],"domain,":[66],"policy":[68,102],"such":[70],"multimodal":[71,101,127,217],"often":[74],"crafted":[75],"by":[76],"hand;":[77],"as":[78],"complexity":[80],"interactions":[82],"grows,":[83],"process":[85],"not":[87],"scalable.":[88],"This":[89,203],"paper":[90],"proposes":[91],"a":[92,110,114,117,123,150,164,190,207],"reinforcement":[93],"learning":[94],"(RL)":[95],"approach":[96,205],"automatically":[98],"generate":[99],"robot.":[105],"Our":[106],"system":[107,188],"focuses":[108],"on":[109],"realistic":[111],"scenario":[112],"where":[113],"assists":[116],"user":[118],"locating":[120],"objects":[121],"within":[122],"home":[124],"environment,":[125],"managing":[126],"signals,":[128],"including":[129],"language":[130],"physical":[132],"actions,":[133],"select":[135],"In":[139],"contrast":[140],"traditional":[142],"dialog":[143],"systems,":[144],"our":[145],"agent":[146],"trained":[148],"simulator":[151],"that":[152,169],"uses":[153],"can":[157],"deal":[158],"multiple":[160],"modalities.":[161],"We":[162],"use":[163],"simple":[165],"high-level":[166],"reward":[167],"function":[168],"needs":[170],"no":[171],"fine-tuning":[172],"enforce":[174],"some":[175],"preconditions":[176],"speed":[178],"up":[179],"training":[181],"process.":[182],"A":[183],"study":[185],"evaluating":[186],"real-world":[191],"setting":[192],"demonstrates":[193],"promising":[194],"results,":[195],"indicating":[196],"high":[197],"usability":[198],"effective":[200],"completion.":[202],"RL-based":[204],"offers":[206],"scalable":[208],"interpretable":[210],"alternative":[211],"designing":[213],"managers":[215],"human-robot":[218],"collaborations.":[219]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}