{"id":"https://openalex.org/W4389665844","doi":"https://doi.org/10.1109/iros55552.2023.10341904","title":"Reward Shaping for Building Trustworthy Robots in Sequential Human-Robot Interaction","display_name":"Reward Shaping for Building Trustworthy Robots in Sequential Human-Robot Interaction","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4389665844","doi":"https://doi.org/10.1109/iros55552.2023.10341904"},"language":"en","primary_location":{"id":"doi:10.1109/iros55552.2023.10341904","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10341904","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-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/A5003439325","display_name":"Yaohui Guo","orcid":"https://orcid.org/0000-0002-7064-9249"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yaohui Guo","raw_affiliation_strings":["University of Michigan,Department of Industrial and Operations Engineering,Ann Arbor,Michigan","Department of Industrial and Operations Engineering, University of Michigan, Ann Arbor, Michigan"],"affiliations":[{"raw_affiliation_string":"University of Michigan,Department of Industrial and Operations Engineering,Ann Arbor,Michigan","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"Department of Industrial and Operations Engineering, University of Michigan, Ann Arbor, Michigan","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067895217","display_name":"X. Jessie Yang","orcid":"https://orcid.org/0000-0001-6071-0387"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"X. Jessie Yang","raw_affiliation_strings":["University of Michigan,Department of Industrial and Operations Engineering,Ann Arbor,Michigan","Department of Industrial and Operations Engineering, University of Michigan, Ann Arbor, Michigan"],"affiliations":[{"raw_affiliation_string":"University of Michigan,Department of Industrial and Operations Engineering,Ann Arbor,Michigan","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"Department of Industrial and Operations Engineering, University of Michigan, Ann Arbor, Michigan","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023311569","display_name":"Cong Shi","orcid":"https://orcid.org/0000-0003-3564-3391"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan\u2013Ann Arbor","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cong Shi","raw_affiliation_strings":["University of Michigan,Department of Industrial and Operations Engineering,Ann Arbor,Michigan","Department of Industrial and Operations Engineering, University of Michigan, Ann Arbor, Michigan"],"affiliations":[{"raw_affiliation_string":"University of Michigan,Department of Industrial and Operations Engineering,Ann Arbor,Michigan","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"Department of Industrial and Operations Engineering, University of Michigan, Ann Arbor, Michigan","institution_ids":["https://openalex.org/I27837315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5003439325"],"corresponding_institution_ids":["https://openalex.org/I27837315"],"apc_list":null,"apc_paid":null,"fwci":2.0246,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.87091496,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7999","last_page":"8005"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10525","display_name":"Human-Automation Interaction and Safety","score":0.9994000196456909,"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/T10525","display_name":"Human-Automation Interaction and Safety","score":0.9994000196456909,"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/T13248","display_name":"Healthcare Technology and Patient Monitoring","score":0.9894999861717224,"subfield":{"id":"https://openalex.org/subfields/2746","display_name":"Surgery"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7512854933738708},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7180899977684021},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6752988696098328},{"id":"https://openalex.org/keywords/dilemma","display_name":"Dilemma","score":0.6742838621139526},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.669214129447937},{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.5339983701705933},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5291619300842285},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.44050687551498413},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4342000484466553},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3542498052120209},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2611965537071228},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12176862359046936}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7512854933738708},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7180899977684021},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6752988696098328},{"id":"https://openalex.org/C2778496695","wikidata":"https://www.wikidata.org/wiki/Q254128","display_name":"Dilemma","level":2,"score":0.6742838621139526},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.669214129447937},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.5339983701705933},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5291619300842285},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.44050687551498413},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4342000484466553},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3542498052120209},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2611965537071228},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12176862359046936},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros55552.2023.10341904","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10341904","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1777239053","https://openalex.org/W2007567868","https://openalex.org/W2070177757","https://openalex.org/W2110171129","https://openalex.org/W2127333783","https://openalex.org/W2339027962","https://openalex.org/W2572169790","https://openalex.org/W2594678573","https://openalex.org/W2969622979","https://openalex.org/W2989822567","https://openalex.org/W3004302416","https://openalex.org/W3012435612","https://openalex.org/W3083287224","https://openalex.org/W3089447464","https://openalex.org/W3098131776","https://openalex.org/W3101073843","https://openalex.org/W3137020344","https://openalex.org/W3197434213","https://openalex.org/W4285792044","https://openalex.org/W4307717765","https://openalex.org/W4385430482","https://openalex.org/W6638088447","https://openalex.org/W6713546108"],"related_works":["https://openalex.org/W2350209916","https://openalex.org/W2475524763","https://openalex.org/W2379651310","https://openalex.org/W2113019827","https://openalex.org/W1541249122","https://openalex.org/W2413828414","https://openalex.org/W2367222340","https://openalex.org/W187740018","https://openalex.org/W2162286586","https://openalex.org/W4255368532"],"abstract_inverted_index":{"Trust-aware":[0],"human-robot":[1,142],"interaction":[2],"(HRI)":[3],"has":[4,11],"received":[5],"increasing":[6],"research":[7],"attention,":[8],"as":[9,59],"trust":[10,42,72,114,166],"been":[12],"shown":[13],"to":[14,35,69,111,163],"be":[15,91,123],"a":[16,27,60,118,137,141,145,168],"crucial":[17],"factor":[18],"for":[19],"effective":[20],"HRI.":[21],"Research":[22],"in":[23,117,128,136],"trust-aware":[24],"HRI":[25,57],"discovered":[26],"dilemma":[28,53],"-":[29],"maximizing":[30,40],"task":[31,45,170],"rewards":[32],"often":[33],"leads":[34],"decreased":[36],"human":[37,41,71,165],"trust,":[38],"while":[39,73],"would":[43],"compromise":[44],"performance.":[46],"In":[47],"this":[48,52],"work,":[49],"we":[50,78],"address":[51],"by":[54,93],"formulating":[55],"the":[56,66,82,87,94,99,103,108,112,133,152,157],"process":[58],"two-player":[61],"Markov":[62,104],"game":[63],"and":[64,126],"utilizing":[65],"reward-shaping":[67],"technique":[68],"improve":[70],"limiting":[74],"performance":[75,88,171],"loss.":[76],"Specifically,":[77],"show":[79],"that":[80,121,151],"when":[81],"shaping":[83],"reward":[84],"is":[85],"potential-based,":[86],"loss":[89],"can":[90,122],"bounded":[92],"potential":[95],"functions":[96],"evaluated":[97],"at":[98,167],"final":[100],"states":[101],"of":[102],"game.":[105],"We":[106,131],"apply":[107],"proposed":[109,134,153],"framework":[110,135,154],"experience-based":[113],"model,":[115],"resulting":[116],"linear":[119],"program":[120],"efficiently":[124],"solved":[125],"deployed":[127],"real-world":[129],"applications.":[130],"evaluate":[132],"simulation":[138],"scenario":[139],"where":[140],"team":[143],"performs":[144],"search-and-rescue":[146],"mission.":[147],"The":[148],"results":[149],"demonstrate":[150],"successfully":[155],"modifies":[156],"robot's":[158],"optimal":[159],"policy,":[160],"enabling":[161],"it":[162],"increase":[164],"minimal":[169],"cost.":[172]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}