{"id":"https://openalex.org/W4360993698","doi":"https://doi.org/10.1109/access.2023.3262450","title":"Affordance-Based Human\u2013Robot Interaction With Reinforcement Learning","display_name":"Affordance-Based Human\u2013Robot Interaction With Reinforcement Learning","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4360993698","doi":"https://doi.org/10.1109/access.2023.3262450"},"language":"en","primary_location":{"id":"doi:10.1109/access.2023.3262450","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3262450","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10082924.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10082924.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046176579","display_name":"Francisco Munguia\u2010Galeano","orcid":"https://orcid.org/0000-0001-8397-3083"},"institutions":[{"id":"https://openalex.org/I79510175","display_name":"Cardiff University","ror":"https://ror.org/03kk7td41","country_code":"GB","type":"education","lineage":["https://openalex.org/I79510175"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Francisco Munguia-Galeano","raw_affiliation_strings":["School of Engineering, Cardiff University, Cardiff, U.K","School of Engineering, Cardiff University, Cardiff, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0001-8397-3083","affiliations":[{"raw_affiliation_string":"School of Engineering, Cardiff University, Cardiff, U.K","institution_ids":["https://openalex.org/I79510175"]},{"raw_affiliation_string":"School of Engineering, Cardiff University, Cardiff, United Kingdom","institution_ids":["https://openalex.org/I79510175"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022756848","display_name":"Satheeshkumar Veeramani","orcid":"https://orcid.org/0000-0003-2538-0022"},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Satheeshkumar Veeramani","raw_affiliation_strings":["Cooper Group, University of Liverpool, Liverpool, U.K","Cooper Group, The University of Liverpool, Liverpool, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cooper Group, University of Liverpool, Liverpool, U.K","institution_ids":["https://openalex.org/I146655781"]},{"raw_affiliation_string":"Cooper Group, The University of Liverpool, Liverpool, United Kingdom","institution_ids":["https://openalex.org/I146655781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101609628","display_name":"Juan David Hern\u00e1ndez","orcid":"https://orcid.org/0000-0002-9593-6789"},"institutions":[{"id":"https://openalex.org/I79510175","display_name":"Cardiff University","ror":"https://ror.org/03kk7td41","country_code":"GB","type":"education","lineage":["https://openalex.org/I79510175"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Juan David Hern\u00e1ndez","raw_affiliation_strings":["School of Computer Science and Informatics, Cardiff University, Cardiff, U.K","School of Computer Science and Informatics, Cardiff University, Cardiff, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-9593-6789","affiliations":[{"raw_affiliation_string":"School of Computer Science and Informatics, Cardiff University, Cardiff, U.K","institution_ids":["https://openalex.org/I79510175"]},{"raw_affiliation_string":"School of Computer Science and Informatics, Cardiff University, Cardiff, United Kingdom","institution_ids":["https://openalex.org/I79510175"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039712604","display_name":"Qingmeng Wen","orcid":"https://orcid.org/0000-0002-8972-4042"},"institutions":[{"id":"https://openalex.org/I79510175","display_name":"Cardiff University","ror":"https://ror.org/03kk7td41","country_code":"GB","type":"education","lineage":["https://openalex.org/I79510175"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Qingmeng Wen","raw_affiliation_strings":["School of Engineering, Cardiff University, Cardiff, U.K","School of Engineering, Cardiff University, Cardiff, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-8972-4042","affiliations":[{"raw_affiliation_string":"School of Engineering, Cardiff University, Cardiff, U.K","institution_ids":["https://openalex.org/I79510175"]},{"raw_affiliation_string":"School of Engineering, Cardiff University, Cardiff, United Kingdom","institution_ids":["https://openalex.org/I79510175"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068175770","display_name":"Ze Ji","orcid":"https://orcid.org/0000-0002-8968-9902"},"institutions":[{"id":"https://openalex.org/I79510175","display_name":"Cardiff University","ror":"https://ror.org/03kk7td41","country_code":"GB","type":"education","lineage":["https://openalex.org/I79510175"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ze Ji","raw_affiliation_strings":["School of Engineering, Cardiff University, Cardiff, U.K","School of Engineering, Cardiff University, Cardiff, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-8968-9902","affiliations":[{"raw_affiliation_string":"School of Engineering, Cardiff University, Cardiff, U.K","institution_ids":["https://openalex.org/I79510175"]},{"raw_affiliation_string":"School of Engineering, Cardiff University, Cardiff, United Kingdom","institution_ids":["https://openalex.org/I79510175"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":2.2208,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.89418105,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"11","issue":null,"first_page":"31282","last_page":"31292"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9995999932289124,"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/T10879","display_name":"Robotic Locomotion and Control","score":0.9757999777793884,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/affordance","display_name":"Affordance","score":0.931236207485199},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8766227960586548},{"id":"https://openalex.org/keywords/grasp","display_name":"GRASP","score":0.7971071004867554},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7666643857955933},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7624563574790955},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6550112962722778},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5708196759223938},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5523003339767456},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.5217762589454651},{"id":"https://openalex.org/keywords/train","display_name":"Train","score":0.5008821487426758},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4876214563846588},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36106836795806885},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.2704809904098511},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.06724762916564941}],"concepts":[{"id":"https://openalex.org/C194995250","wikidata":"https://www.wikidata.org/wiki/Q531136","display_name":"Affordance","level":2,"score":0.931236207485199},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8766227960586548},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.7971071004867554},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7666643857955933},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7624563574790955},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6550112962722778},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5708196759223938},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5523003339767456},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.5217762589454651},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.5008821487426758},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4876214563846588},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36106836795806885},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.2704809904098511},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.06724762916564941},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/access.2023.3262450","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3262450","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10082924.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},{"id":"pmh:oai:https://orca.cardiff.ac.uk:158882","is_oa":true,"landing_page_url":null,"pdf_url":"https://orca.cardiff.ac.uk/id/eprint/158882/1/Affordance-Based_HumanRobot_Interaction_With_Reinforcement_Learning.pdf","source":{"id":"https://openalex.org/S4306401195","display_name":"ORCA Online Research @Cardiff (Cardiff University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79510175","host_organization_name":"Cardiff University","host_organization_lineage":["https://openalex.org/I79510175"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"pmh:oai:doaj.org/article:5610b7d5fb5d46bebcfde1c5c05b639a","is_oa":true,"landing_page_url":"https://doaj.org/article/5610b7d5fb5d46bebcfde1c5c05b639a","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 11, Pp 31282-31292 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2023.3262450","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3262450","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10082924.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321739","display_name":"Consejo Nacional de Ciencia y Tecnolog\u00eda","ror":"https://ror.org/059ex5q34"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4360993698.pdf","grobid_xml":"https://content.openalex.org/works/W4360993698.grobid-xml"},"referenced_works_count":64,"referenced_works":["https://openalex.org/W131069610","https://openalex.org/W1681019253","https://openalex.org/W1777783943","https://openalex.org/W1997880753","https://openalex.org/W2006292430","https://openalex.org/W2022365837","https://openalex.org/W2119112357","https://openalex.org/W2284276045","https://openalex.org/W2402164873","https://openalex.org/W2559960928","https://openalex.org/W2565110810","https://openalex.org/W2736601468","https://openalex.org/W2824479732","https://openalex.org/W2888116234","https://openalex.org/W2890001928","https://openalex.org/W2905082659","https://openalex.org/W2909123235","https://openalex.org/W2909564046","https://openalex.org/W2917089854","https://openalex.org/W2921851574","https://openalex.org/W2922340928","https://openalex.org/W2927564896","https://openalex.org/W2929352350","https://openalex.org/W2930863966","https://openalex.org/W2934391250","https://openalex.org/W2941630913","https://openalex.org/W2962746398","https://openalex.org/W2962793652","https://openalex.org/W2969464237","https://openalex.org/W2976611405","https://openalex.org/W2981759303","https://openalex.org/W2993140224","https://openalex.org/W2993390435","https://openalex.org/W2994446013","https://openalex.org/W2995980424","https://openalex.org/W2997890149","https://openalex.org/W3003320643","https://openalex.org/W3003887935","https://openalex.org/W3014495834","https://openalex.org/W3034321388","https://openalex.org/W3046547158","https://openalex.org/W3059965140","https://openalex.org/W3089760622","https://openalex.org/W3092927864","https://openalex.org/W3099098707","https://openalex.org/W3115959388","https://openalex.org/W3128256958","https://openalex.org/W3156492906","https://openalex.org/W3158072063","https://openalex.org/W3186035148","https://openalex.org/W3197739339","https://openalex.org/W3212826513","https://openalex.org/W4213446758","https://openalex.org/W4214717370","https://openalex.org/W4226413077","https://openalex.org/W4231152856","https://openalex.org/W4298857966","https://openalex.org/W4312481136","https://openalex.org/W6605295560","https://openalex.org/W6637967152","https://openalex.org/W6684921986","https://openalex.org/W6692846177","https://openalex.org/W6741002519","https://openalex.org/W6771157300"],"related_works":["https://openalex.org/W1972718289","https://openalex.org/W1791514435","https://openalex.org/W2346831895","https://openalex.org/W2248634132","https://openalex.org/W2295809616","https://openalex.org/W3014080459","https://openalex.org/W4386875794","https://openalex.org/W2951631158","https://openalex.org/W4288313544","https://openalex.org/W2976611405"],"abstract_inverted_index":{"Planning":[0],"precise":[1],"manipulation":[2],"in":[3,79,119,148],"robotics":[4],"to":[5,25,43,100,108,143],"perform":[6],"grasp":[7],"and":[8,87,106,134],"release-related":[9],"operations,":[10],"while":[11],"interacting":[12],"with":[13],"humans":[14],"is":[15,61],"a":[16,64,80,157],"challenging":[17],"problem.":[18],"Reinforcement":[19],"learning":[20,98],"(RL)":[21],"has":[22],"the":[23,45,53,57,75,96,102,115,124,126,132,135,139,149,154],"potential":[24],"make":[26],"robots":[27],"attain":[28],"this":[29,32],"capability.":[30],"In":[31],"paper,":[33],"we":[34,112],"propose":[35],"an":[36,89],"affordance-based":[37],"human-robot":[38],"interaction":[39],"(HRI)":[40],"framework,":[41],"aiming":[42],"reduce":[44],"action":[46],"space":[47],"size":[48],"that":[49,74,151],"would":[50],"considerably":[51],"impede":[52],"exploration":[54],"efficiency":[55,99],"of":[56,83,91,138,156],"agent.":[58],"The":[59],"framework":[60,116],"based":[62],"on":[63],"new":[65,158],"algorithm":[66,77],"called":[67],"Contextual":[68],"Q-learning":[69],"(CQL).":[70],"We":[71],"first":[72],"show":[73],"proposed":[76],"trains":[78],"reduced":[81],"amount":[82],"time":[84],"(2.7":[85],"seconds)":[86],"reaches":[88],"84%":[90],"success":[92],"rate.":[93],"This":[94],"suits":[95],"robot\u2019s":[97],"observe":[101],"current":[103],"scenario":[104],"configuration":[105],"learn":[107],"solve":[109],"it.":[110],"Then,":[111],"empirically":[113],"validate":[114],"for":[117,145],"implementation":[118],"HRI":[120],"real-world":[121],"scenarios.":[122],"During":[123],"HRI,":[125],"robot":[127],"uses":[128],"semantic":[129],"information":[130],"from":[131],"state":[133],"optimal":[136],"policy":[137],"last":[140],"training":[141],"step":[142],"search":[144],"relevant":[146],"changes":[147],"environment":[150],"may":[152],"trigger":[153],"generation":[155],"policy.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}