{"id":"https://openalex.org/W7137900609","doi":"https://doi.org/10.1609/aaai.v40i21.38809","title":"Belief-Driven Value Alignment for Human-Robot Collaboration","display_name":"Belief-Driven Value Alignment for Human-Robot Collaboration","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137900609","doi":"https://doi.org/10.1609/aaai.v40i21.38809"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i21.38809","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i21.38809","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38809/42771","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38809/42771","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047736510","display_name":"Saisai Li","orcid":"https://orcid.org/0000-0003-1346-5870"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Saisai Li","raw_affiliation_strings":["Wuhan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129723115","display_name":"Bing Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Shi","raw_affiliation_strings":["Wuhan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129711810","display_name":"Yiming Xia","orcid":null},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiming Xia","raw_affiliation_strings":["Wuhan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078888666","display_name":"Xiao Su","orcid":"https://orcid.org/0009-0008-5408-8147"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Su","raw_affiliation_strings":["Wuhan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology","institution_ids":["https://openalex.org/I196699116"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I196699116"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11750826,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"21","first_page":"17544","last_page":"17552"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.5580000281333923,"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":0.5580000281333923,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.054499998688697815,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.03840000182390213,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/value","display_name":"Value (mathematics)","score":0.6279000043869019},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6273000240325928},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5819000005722046},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4900999963283539},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.3903999924659729},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.320499986410141},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.310699999332428}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7178000211715698},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.6279000043869019},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6273000240325928},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6122999787330627},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5819000005722046},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4900999963283539},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.446399986743927},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.3903999924659729},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.320499986410141},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.310699999332428},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.295199990272522},{"id":"https://openalex.org/C74072328","wikidata":"https://www.wikidata.org/wiki/Q1142726","display_name":"Intelligent agent","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C85617194","wikidata":"https://www.wikidata.org/wiki/Q2072794","display_name":"Particle swarm optimization","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2515000104904175}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i21.38809","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i21.38809","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38809/42771","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/38809","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/38809","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i21.38809","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i21.38809","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38809/42771","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7137900609.pdf","grobid_xml":"https://content.openalex.org/works/W7137900609.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"As":[0],"intelligent":[1,14],"systems":[2],"advance":[3],"rapidly,":[4],"human-robot":[5,64],"collaboration":[6],"is":[7,23,29,55,73],"becoming":[8],"increasingly":[9],"important.":[10],"Ensuring":[11],"that":[12,71,176],"the":[13,31,36,101,108,115,129,136,160,181],"agent's":[15],"behaviors":[16,126],"match":[17],"human":[18,72,120,144,187],"intentions":[19],"and":[20,49,76,145,147,188],"value":[21,32,41,60,150,193],"preferences":[22],"crucial":[24],"for":[25],"effective":[26],"collaboration,":[27],"which":[28],"termed":[30],"alignment":[33,42,61,142,151,182],"problem.":[34],"Within":[35],"Reinforcement":[37,52],"Learning":[38,53],"(RL)":[39],"paradigm,":[40],"typically":[43],"relies":[44],"on":[45,82,132],"pre-designed":[46],"reward":[47],"functions,":[48],"Cooperative":[50],"Inverse":[51],"(CIRL)":[54],"often":[56,69],"used":[57],"to":[58,121,127,158,191],"model":[59],"as":[62],"a":[63,91],"game.":[65],"However,":[66],"existing":[67],"works":[68],"assume":[70],"perfectly":[74],"rational,":[75],"can":[77,179],"fully":[78],"obtain":[79],"robot\u2019s":[80],"belief":[81,103,141,184],"human\u2019s":[83],"preference.":[84],"To":[85],"address":[86],"this":[87,105],"limitation,":[88],"we":[89,155],"propose":[90],"Particle":[92],"Filter-based":[93],"Hierarchical":[94],"Dynamic":[95],"Programming":[96],"algorithm":[97,106],"(PFHDP).":[98],"By":[99],"modeling":[100],"robot's":[102,116,137],"state,":[104],"ensures":[107],"correct":[109],"updates":[110],"of":[111,114,135,183],"human's":[112],"estimate":[113],"belief.":[117],"This":[118],"allows":[119],"adopt":[122],"more":[123,152],"targeted":[124],"pedagogical":[125],"guide":[128],"robot":[130,146],"based":[131],"her":[133],"understanding":[134],"current":[138],"belief,":[139],"achieving":[140],"between":[143,186],"thereby":[148],"promoting":[149],"effectively.":[153],"Furthermore,":[154],"run":[156],"experiments":[157],"evaluate":[159],"proposed":[161],"method":[162,178],"in":[163],"two":[164],"cooperative":[165],"scenarios":[166],"against":[167],"some":[168],"typical":[169],"benchmark":[170],"approaches.":[171],"The":[172],"experimental":[173],"results":[174],"show":[175],"our":[177],"strengthen":[180],"states":[185],"robot,":[189],"leading":[190],"enhanced":[192],"alignment.":[194]},"counts_by_year":[],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2026-03-18T00:00:00"}
