{"id":"https://openalex.org/W4386981938","doi":"https://doi.org/10.1145/3623384","title":"Unified Learning from Demonstrations, Corrections, and Preferences during Physical Human\u2013Robot Interaction","display_name":"Unified Learning from Demonstrations, Corrections, and Preferences during Physical Human\u2013Robot Interaction","publication_year":2023,"publication_date":"2023-09-23","ids":{"openalex":"https://openalex.org/W4386981938","doi":"https://doi.org/10.1145/3623384"},"language":"en","primary_location":{"id":"doi:10.1145/3623384","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3623384","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3623384","source":{"id":"https://openalex.org/S4210193251","display_name":"ACM Transactions on Human-Robot Interaction","issn_l":"2573-9522","issn":["2573-9522"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Human-Robot Interaction","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3623384","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014071264","display_name":"Shaunak A. Mehta","orcid":"https://orcid.org/0000-0002-3160-6879"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shaunak A. Mehta","raw_affiliation_strings":["Virginia Tech, Blacksburg, USA","Virginia Tech Department of Mechanical Engineering, USA"],"raw_orcid":"https://orcid.org/0000-0002-3160-6879","affiliations":[{"raw_affiliation_string":"Virginia Tech, Blacksburg, USA","institution_ids":["https://openalex.org/I859038795"]},{"raw_affiliation_string":"Virginia Tech Department of Mechanical Engineering, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063608480","display_name":"Dylan P. Losey","orcid":"https://orcid.org/0000-0002-8787-5293"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dylan P. Losey","raw_affiliation_strings":["Virginia Tech, Blacksburg, USA","Virginia Tech Department of Mechanical Engineering, USA"],"raw_orcid":"https://orcid.org/0000-0002-8787-5293","affiliations":[{"raw_affiliation_string":"Virginia Tech, Blacksburg, USA","institution_ids":["https://openalex.org/I859038795"]},{"raw_affiliation_string":"Virginia Tech Department of Mechanical Engineering, USA","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5014071264"],"corresponding_institution_ids":["https://openalex.org/I859038795"],"apc_list":null,"apc_paid":null,"fwci":3.2281,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.92309681,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"13","issue":"3","first_page":"1","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9998999834060669,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9965999722480774,"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/T11023","display_name":"Prosthetics and Rehabilitation Robotics","score":0.9729999899864197,"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/robot","display_name":"Robot","score":0.7494605779647827},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.721468448638916},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6593959331512451},{"id":"https://openalex.org/keywords/scratch","display_name":"Scratch","score":0.6260265707969666},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5986247658729553},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5367819666862488},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4944477081298828},{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.4889465570449829},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.48584315180778503},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.45048049092292786},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.41736704111099243},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.2659367322921753},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0869951844215393}],"concepts":[{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7494605779647827},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.721468448638916},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6593959331512451},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.6260265707969666},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5986247658729553},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5367819666862488},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4944477081298828},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.4889465570449829},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.48584315180778503},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.45048049092292786},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.41736704111099243},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.2659367322921753},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0869951844215393},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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":2,"locations":[{"id":"doi:10.1145/3623384","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3623384","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3623384","source":{"id":"https://openalex.org/S4210193251","display_name":"ACM Transactions on Human-Robot Interaction","issn_l":"2573-9522","issn":["2573-9522"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Human-Robot Interaction","raw_type":"journal-article"},{"id":"pmh:oai:vtechworks.lib.vt.edu:10919/116404","is_oa":true,"landing_page_url":"http://hdl.handle.net/10919/116404","pdf_url":"https://vtechworks.lib.vt.edu/bitstreams/cc013ff5-c128-46ef-9885-5e714c0c3795/download","source":{"id":"https://openalex.org/S4306400248","display_name":"VTechWorks (Virginia Tech)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I859038795","host_organization_name":"Virginia Tech","host_organization_lineage":["https://openalex.org/I859038795"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1145/3623384","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3623384","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3623384","source":{"id":"https://openalex.org/S4210193251","display_name":"ACM Transactions on Human-Robot Interaction","issn_l":"2573-9522","issn":["2573-9522"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Human-Robot Interaction","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3156217155","display_name":null,"funder_award_id":"2129201","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386981938.pdf","grobid_xml":"https://content.openalex.org/works/W4386981938.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W187005120","https://openalex.org/W1837766154","https://openalex.org/W1970101292","https://openalex.org/W1986014385","https://openalex.org/W1999874108","https://openalex.org/W2044442377","https://openalex.org/W2050835671","https://openalex.org/W2050985708","https://openalex.org/W2142224528","https://openalex.org/W2169513627","https://openalex.org/W2280090643","https://openalex.org/W2540877599","https://openalex.org/W2766053765","https://openalex.org/W2766253253","https://openalex.org/W2785922753","https://openalex.org/W2799280697","https://openalex.org/W2801531857","https://openalex.org/W2907920236","https://openalex.org/W2914304175","https://openalex.org/W3003858867","https://openalex.org/W3014235025","https://openalex.org/W3092948749","https://openalex.org/W3101780148","https://openalex.org/W3105789002","https://openalex.org/W3106171760","https://openalex.org/W3133184250","https://openalex.org/W3134935089","https://openalex.org/W3148444946","https://openalex.org/W3197594072","https://openalex.org/W3207713159","https://openalex.org/W3208223622","https://openalex.org/W4206386758","https://openalex.org/W4212898980","https://openalex.org/W4225737910","https://openalex.org/W4236573885","https://openalex.org/W4312772252"],"related_works":["https://openalex.org/W2768698792","https://openalex.org/W2930863966","https://openalex.org/W2126211886","https://openalex.org/W3153786280","https://openalex.org/W3127551068","https://openalex.org/W2643884694","https://openalex.org/W2165180011","https://openalex.org/W4220829754","https://openalex.org/W3165944253","https://openalex.org/W2351343564"],"abstract_inverted_index":{"Humans":[0],"can":[1],"leverage":[2],"physical":[3,10,198],"interaction":[4,11,41,200],"to":[5,94,111,117,134,150,158,170],"teach":[6,95],"robot":[7,24,51,157,178,207],"arms.":[8],"This":[9],"takes":[12],"multiple":[13],"forms":[14],"depending":[15],"on":[16,32],"the":[17,19,23,50,56,59,62,89,91,96,108,118,136,151,156,206],"task,":[18],"user,":[20],"and":[21,61,81,140,144,182],"what":[22],"has":[25,52],"learned":[26,173],"so":[27,46],"far.":[28],"State-of-the-art":[29],"approaches":[30],"focus":[31],"learning":[33,77],"from":[34,78,104,197],"a":[35,101,124,176,183],"single":[36],"modality,":[37],"or":[38,163,212],"combine":[39],"some":[40],"types.":[42],"Some":[43],"methods":[44],"do":[45],"by":[47,106],"assuming":[48],"that":[49,75,127,188],"prior":[53],"information":[54],"about":[55,88],"features":[57],"of":[58,131,146,216],"task":[60],"reward":[63,102,132,174],"structure.":[64],"By":[65],"contrast,":[66],"in":[67],"this":[68,160],"article,":[69],"we":[70,99,186],"introduce":[71],"an":[72,129],"algorithmic":[73],"formalism":[74],"unites":[76],"demonstrations,":[79,138],"corrections,":[80,139],"preferences.":[82,141],"Our":[83],"approach":[84,191],"makes":[85],"no":[86],"assumptions":[87],"tasks":[90,196],"human":[92,152,199],"wants":[93],"robot;":[97],"instead,":[98],"learn":[100],"model":[103],"scratch":[105],"comparing":[107],"human\u2019s":[109,119,137],"input":[110],"nearby":[112],"alternatives,":[113],"i.e.,":[114],"trajectories":[115],"close":[116],"feedback.":[120],"We":[121,154,165],"first":[122],"derive":[123],"loss":[125],"function":[126],"trains":[128],"ensemble":[130],"models":[133],"match":[135],"The":[142],"type":[143],"order":[145],"feedback":[147,161],"is":[148,208],"up":[149],"teacher:":[153],"enable":[155],"collect":[159],"passively":[162],"actively.":[164],"then":[166],"apply":[167],"constrained":[168],"optimization":[169],"convert":[171],"our":[172,189,217],"into":[175],"desired":[177],"trajectory.":[179],"Through":[180],"simulations":[181],"user":[184,218],"study,":[185],"demonstrate":[187],"proposed":[190],"more":[192],"accurately":[193],"learns":[194],"manipulation":[195],"than":[201],"existing":[202],"baselines,":[203],"particularly":[204],"when":[205],"faced":[209],"with":[210],"new":[211],"unexpected":[213],"objectives.":[214],"Videos":[215],"study":[219],"are":[220],"available":[221],"at":[222],"https://youtu.be/FSUJsTYvEKU":[223],".":[224]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}