{"id":"https://openalex.org/W4225726291","doi":"https://doi.org/10.1109/cdc45484.2021.9683023","title":"Human-in-the-Loop Robot Planning with Non-Contextual Bandit Feedback","display_name":"Human-in-the-Loop Robot Planning with Non-Contextual Bandit Feedback","publication_year":2021,"publication_date":"2021-12-14","ids":{"openalex":"https://openalex.org/W4225726291","doi":"https://doi.org/10.1109/cdc45484.2021.9683023"},"language":"en","primary_location":{"id":"doi:10.1109/cdc45484.2021.9683023","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc45484.2021.9683023","pdf_url":null,"source":{"id":"https://openalex.org/S4363607724","display_name":"2021 60th IEEE Conference on Decision and Control (CDC)","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 60th IEEE Conference on Decision and Control (CDC)","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/A5101403001","display_name":"Yijie Zhou","orcid":"https://orcid.org/0009-0002-5892-6925"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yijie Zhou","raw_affiliation_strings":["Duke University, Durham, NC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University, Durham, NC, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100456179","display_name":"Yan Zhang","orcid":"https://orcid.org/0000-0001-9890-8380"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yan Zhang","raw_affiliation_strings":["Duke University, Durham, NC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University, Durham, NC, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009405571","display_name":"Xusheng Luo","orcid":"https://orcid.org/0000-0003-4342-7234"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xusheng Luo","raw_affiliation_strings":["Duke University, Durham, NC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University, Durham, NC, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080808780","display_name":"Michael M. Zavlanos","orcid":"https://orcid.org/0000-0003-1748-8228"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael M. Zavlanos","raw_affiliation_strings":["Duke University, Durham, NC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University, Durham, NC, USA","institution_ids":["https://openalex.org/I170897317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170897317"],"apc_list":null,"apc_paid":null,"fwci":0.2864,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.63944427,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2848","last_page":"2853"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9976999759674072,"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"}},"topics":[{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9976999759674072,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9959999918937683,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9952999949455261,"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/trajectory","display_name":"Trajectory","score":0.7446197271347046},{"id":"https://openalex.org/keywords/human-in-the-loop","display_name":"Human-in-the-loop","score":0.6982227563858032},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6449812650680542},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.644437313079834},{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.5584297776222229},{"id":"https://openalex.org/keywords/feedback-loop","display_name":"Feedback loop","score":0.5286094546318054},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.49988675117492676},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4709818363189697},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.43195435404777527},{"id":"https://openalex.org/keywords/bayesian-optimization","display_name":"Bayesian optimization","score":0.415861576795578},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3455047607421875},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3221670389175415},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.321859747171402},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1481662094593048}],"concepts":[{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.7446197271347046},{"id":"https://openalex.org/C2780626000","wikidata":"https://www.wikidata.org/wiki/Q5936775","display_name":"Human-in-the-loop","level":2,"score":0.6982227563858032},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6449812650680542},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.644437313079834},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.5584297776222229},{"id":"https://openalex.org/C186886427","wikidata":"https://www.wikidata.org/wiki/Q5441213","display_name":"Feedback loop","level":2,"score":0.5286094546318054},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.49988675117492676},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4709818363189697},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.43195435404777527},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.415861576795578},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3455047607421875},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3221670389175415},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.321859747171402},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1481662094593048},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc45484.2021.9683023","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc45484.2021.9683023","pdf_url":null,"source":{"id":"https://openalex.org/S4363607724","display_name":"2021 60th IEEE Conference on Decision and Control (CDC)","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 60th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.5199999809265137,"id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W160562721","https://openalex.org/W1155403144","https://openalex.org/W1529379539","https://openalex.org/W1937512970","https://openalex.org/W1986210666","https://openalex.org/W2016211524","https://openalex.org/W2086860466","https://openalex.org/W2102409316","https://openalex.org/W2123368367","https://openalex.org/W2139805416","https://openalex.org/W2156834236","https://openalex.org/W2186013251","https://openalex.org/W2408979476","https://openalex.org/W2961987377","https://openalex.org/W2963805801","https://openalex.org/W3027683692","https://openalex.org/W3087999580","https://openalex.org/W3089419733","https://openalex.org/W6675401909","https://openalex.org/W6680331187","https://openalex.org/W6683329757","https://openalex.org/W6763299424","https://openalex.org/W6765752869"],"related_works":["https://openalex.org/W4288099294","https://openalex.org/W4306697907","https://openalex.org/W3091793048","https://openalex.org/W3081671202","https://openalex.org/W2238043057","https://openalex.org/W4386728952","https://openalex.org/W4248476739","https://openalex.org/W2939389115","https://openalex.org/W4382680211","https://openalex.org/W2765350133"],"abstract_inverted_index":{"In":[0,25],"this":[1,45,54],"paper,":[2],"we":[3,42,56],"consider":[4,43],"robot":[5,68],"navigation":[6],"problems":[7],"in":[8,44,74,99],"environments":[9],"populated":[10],"by":[11],"humans.":[12],"The":[13],"goal":[14],"is":[15,29],"to":[16,33,64],"determine":[17],"safe":[18],"trajectories":[19,69],"that":[20,82],"also":[21],"maximize":[22],"human":[23,27,72],"satisfaction.":[24],"practice,":[26],"satisfaction":[28,80],"subjective":[30],"and":[31,107],"hard":[32],"describe":[34],"mathematically.":[35],"As":[36],"a":[37,58,86,100],"result,":[38],"the":[39,75,91],"planning":[40,97],"problem":[41],"paper":[46],"may":[47],"lack":[48],"important":[49],"contextual":[50],"information.":[51],"To":[52],"address":[53],"challenge,":[55],"propose":[57],"semi-supervised":[59],"Bayesian":[60],"Optimization":[61],"(BO)":[62],"method":[63,98],"design":[65],"globally":[66],"optimal":[67],"using":[70],"bandit":[71],"feedback,":[73],"form":[76],"of":[77,93],"complaints":[78],"or":[79],"ratings,":[81],"expresses":[83],"how":[84],"desirable":[85],"trajectory":[87,96],"is.":[88],"We":[89],"demonstrate":[90],"efficiency":[92],"our":[94],"proposed":[95],"simulated":[101],"scenario":[102],"where":[103],"humans":[104],"have":[105],"diversified":[106],"unknown":[108],"demands.":[109]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}