{"id":"https://openalex.org/W4205156393","doi":"https://doi.org/10.1109/icar53236.2021.9659472","title":"Explainable Reinforcement Learning for Human-Robot Collaboration","display_name":"Explainable Reinforcement Learning for Human-Robot Collaboration","publication_year":2021,"publication_date":"2021-12-06","ids":{"openalex":"https://openalex.org/W4205156393","doi":"https://doi.org/10.1109/icar53236.2021.9659472"},"language":"en","primary_location":{"id":"doi:10.1109/icar53236.2021.9659472","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icar53236.2021.9659472","pdf_url":null,"source":{"id":"https://openalex.org/S4363608199","display_name":"2021 20th International Conference on Advanced Robotics (ICAR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 20th International Conference on Advanced Robotics (ICAR)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5030898842","display_name":"Alessandro Iucci","orcid":null},"institutions":[{"id":"https://openalex.org/I1306339040","display_name":"Ericsson (Sweden)","ror":"https://ror.org/05a7rhx54","country_code":"SE","type":"company","lineage":["https://openalex.org/I1306339040"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Alessandro Iucci","raw_affiliation_strings":["Ericsson Research AI, Ericsson AB, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ericsson Research AI, Ericsson AB, Stockholm, Sweden","institution_ids":["https://openalex.org/I1306339040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016562532","display_name":"Alberto Hata","orcid":"https://orcid.org/0000-0002-6968-7387"},"institutions":[{"id":"https://openalex.org/I1306339040","display_name":"Ericsson (Sweden)","ror":"https://ror.org/05a7rhx54","country_code":"SE","type":"company","lineage":["https://openalex.org/I1306339040"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Alberto Hata","raw_affiliation_strings":["Ericsson Research AI, Ericsson Telecomunicações S/A, Indaiatuba, Brazil","&#x00F5","Ericsson Research AI, Ericsson Telecomunica&#x00E7","es S/A, Indaiatuba, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ericsson Research AI, Ericsson Telecomunicações S/A, Indaiatuba, Brazil","institution_ids":["https://openalex.org/I1306339040"]},{"raw_affiliation_string":"&#x00F5","institution_ids":[]},{"raw_affiliation_string":"Ericsson Research AI, Ericsson Telecomunica&#x00E7","institution_ids":["https://openalex.org/I1306339040"]},{"raw_affiliation_string":"es S/A, Indaiatuba, Brazil","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051329426","display_name":"Ahmad Terra","orcid":"https://orcid.org/0000-0002-6650-2789"},"institutions":[{"id":"https://openalex.org/I1306339040","display_name":"Ericsson (Sweden)","ror":"https://ror.org/05a7rhx54","country_code":"SE","type":"company","lineage":["https://openalex.org/I1306339040"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Ahmad Terra","raw_affiliation_strings":["Ericsson Research AI, Ericsson AB, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ericsson Research AI, Ericsson AB, Stockholm, Sweden","institution_ids":["https://openalex.org/I1306339040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067675907","display_name":"Rafia Inam","orcid":"https://orcid.org/0000-0001-7448-3381"},"institutions":[{"id":"https://openalex.org/I1306339040","display_name":"Ericsson (Sweden)","ror":"https://ror.org/05a7rhx54","country_code":"SE","type":"company","lineage":["https://openalex.org/I1306339040"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Rafia Inam","raw_affiliation_strings":["Ericsson Research AI, Ericsson AB, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ericsson Research AI, Ericsson AB, Stockholm, Sweden","institution_ids":["https://openalex.org/I1306339040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082559019","display_name":"Iolanda Leite","orcid":"https://orcid.org/0000-0002-2212-4325"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Iolanda Leite","raw_affiliation_strings":["Division of Robotics, Perception and Learning, Kungliga Tekniska Högskolan, Stockholm, Sweden","Division of Robotics, Perception and Learning, Kungliga Tekniska H&#x00F6","gskolan, Stockholm, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Robotics, Perception and Learning, Kungliga Tekniska Högskolan, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Division of Robotics, Perception and Learning, Kungliga Tekniska H&#x00F6","institution_ids":[]},{"raw_affiliation_string":"gskolan, Stockholm, Sweden","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0255,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.80362496,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"927","last_page":"934"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987000226974487,"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":0.9987000226974487,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9987000226974487,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9923999905586243,"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":0.8278796672821045},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.777813196182251},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6995940208435059},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.6796761751174927},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6580029726028442},{"id":"https://openalex.org/keywords/debugging","display_name":"Debugging","score":0.6232919692993164},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5573712587356567},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.49794483184814453},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4978315830230713},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4947649836540222},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4836098253726959},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.48228195309638977},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.46441739797592163},{"id":"https://openalex.org/keywords/behavior-based-robotics","display_name":"Behavior-based robotics","score":0.4436432719230652},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.4057609736919403},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07783910632133484}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8278796672821045},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.777813196182251},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6995940208435059},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.6796761751174927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6580029726028442},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.6232919692993164},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5573712587356567},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.49794483184814453},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4978315830230713},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4947649836540222},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4836098253726959},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.48228195309638977},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.46441739797592163},{"id":"https://openalex.org/C19766214","wikidata":"https://www.wikidata.org/wiki/Q4880688","display_name":"Behavior-based robotics","level":4,"score":0.4436432719230652},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.4057609736919403},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07783910632133484},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icar53236.2021.9659472","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icar53236.2021.9659472","pdf_url":null,"source":{"id":"https://openalex.org/S4363608199","display_name":"2021 20th International Conference on Advanced Robotics (ICAR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 20th International Conference on Advanced Robotics (ICAR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6499999761581421,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2018094844","https://openalex.org/W2121517924","https://openalex.org/W2138965998","https://openalex.org/W2594336441","https://openalex.org/W2899483913","https://openalex.org/W2944850799","https://openalex.org/W2973132992","https://openalex.org/W3033407184","https://openalex.org/W3040973413","https://openalex.org/W3046003400","https://openalex.org/W3082925502","https://openalex.org/W3100789280","https://openalex.org/W3116073702","https://openalex.org/W6762157219"],"related_works":["https://openalex.org/W2694175881","https://openalex.org/W2056744823","https://openalex.org/W4206589974","https://openalex.org/W2087751887","https://openalex.org/W2693300019","https://openalex.org/W2151908411","https://openalex.org/W2048497019","https://openalex.org/W2343019076","https://openalex.org/W4378213246","https://openalex.org/W2627853561"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"(RL)":[2],"is":[3,21,119],"getting":[4],"popular":[5],"in":[6,36,45,54,177,191,219,225],"the":[7,66,73,77,81,123,135,139,144,159,171,178,200,205,220],"robotics":[8,55],"field":[9],"due":[10],"to":[11,14,23,51,59,71,86,99,116,186,216],"its":[12,226],"nature":[13],"learn":[15],"from":[16],"dynamic":[17],"environments.":[18],"However,":[19],"it":[20],"unable":[22],"provide":[24],"explanations":[25],"of":[26,76,125,151,170,180,199],"why":[27],"an":[28,109,132,196],"output":[29],"was":[30],"generated.":[31],"Explainability":[32],"becomes":[33],"therefore":[34],"important":[35],"situations":[37],"where":[38],"humans":[39],"interact":[40],"with":[41],"robots,":[42],"such":[43],"as":[44,92,211],"human-robot":[46],"collaboration":[47],"(HRC)":[48],"scenarios.":[49],"Attempts":[50],"address":[52],"explainability":[53,82,110],"usually":[56],"are":[57,84,96],"restricted":[58,85],"explain":[60],"a":[61,167,212],"specific":[62],"decision":[63,156],"taken":[64,157],"by":[65,89,107,122,142,174,204],"RL":[67,113],"model,":[68],"but":[69],"not":[70,97],"understand":[72],"complete":[74],"behavior":[75,173],"robot.":[78],"In":[79],"addition,":[80],"methods":[83],"be":[87],"used":[88],"domain":[90],"experts":[91],"queries":[93,176],"and":[94,223],"responses":[95],"translated":[98],"natural":[100,181],"language.":[101],"This":[102],"work":[103],"overcomes":[104],"these":[105],"limitations":[106],"proposing":[108],"solution":[111,209],"for":[112,154],"models":[114],"applied":[115],"HRC.":[117],"It":[118,147],"mainly":[120],"formed":[121],"adaptation":[124],"two":[126],"methods:":[127],"(i)":[128],"Reward":[129],"decomposition":[130],"gives":[131],"insight":[133],"into":[134],"factors":[136],"that":[137],"impacted":[138],"robot's":[140,160,172,221],"choice":[141],"decomposing":[143],"reward":[145],"function.":[146],"further":[148],"provides":[149,166],"sets":[150],"relevant":[152],"reasons":[153],"each":[155],"during":[158],"operation;":[161],"(ii)":[162],"Autonomous":[163],"policy":[164,222],"explanation":[165,169],"global":[168],"answering":[175],"form":[179],"language,":[182],"thus":[183],"making":[184],"understandable":[185],"any":[187],"human":[188],"user.":[189],"Experiments":[190],"simulated":[192],"HRC":[193],"scenarios":[194],"revealed":[195],"increased":[197],"understanding":[198],"optimal":[201],"choices":[202],"made":[203],"robots.":[206],"Additionally,":[207],"our":[208],"demonstrated":[210],"powerful":[213],"debugging":[214],"tool":[215],"find":[217],"weaknesses":[218],"assist":[224],"improvement.":[227]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}