{"id":"https://openalex.org/W1528932438","doi":"https://doi.org/10.1145/2696454.2696455","title":"Efficient Model Learning from Joint-Action Demonstrations for Human-Robot Collaborative Tasks","display_name":"Efficient Model Learning from Joint-Action Demonstrations for Human-Robot Collaborative Tasks","publication_year":2015,"publication_date":"2015-03-02","ids":{"openalex":"https://openalex.org/W1528932438","doi":"https://doi.org/10.1145/2696454.2696455","mag":"1528932438"},"language":"en","primary_location":{"id":"doi:10.1145/2696454.2696455","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2696454.2696455","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Tenth Annual ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1405.6341","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Stefanos Nikolaidis","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Stefanos Nikolaidis","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ramya Ramakrishnan","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ramya Ramakrishnan","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Keren Gu","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Keren Gu","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":null,"display_name":"Julie Shah","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julie Shah","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":15.6317,"has_fulltext":false,"cited_by_count":92,"citation_normalized_percentile":{"value":0.9896796,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"189","last_page":"196"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9994000196456909,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9887999892234802,"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/robot","display_name":"Robot","score":0.6317999958992004},{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.5608999729156494},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.5449000000953674},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.44999998807907104},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.4336000084877014},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.42579999566078186},{"id":"https://openalex.org/keywords/preference-learning","display_name":"Preference learning","score":0.40869998931884766},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4047999978065491},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.3813000023365021}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7210000157356262},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6317999958992004},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6096000075340271},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.5608999729156494},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.5449000000953674},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.46970000863075256},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.44999998807907104},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.4336000084877014},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.42579999566078186},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4117000102996826},{"id":"https://openalex.org/C181204326","wikidata":"https://www.wikidata.org/wiki/Q7239820","display_name":"Preference learning","level":3,"score":0.40869998931884766},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4047999978065491},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3813000023365021},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3774999976158142},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.36500000953674316},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3643999993801117},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.3603000044822693},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.35690000653266907},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3467999994754791},{"id":"https://openalex.org/C105002631","wikidata":"https://www.wikidata.org/wiki/Q4833645","display_name":"Subject-matter expert","level":3,"score":0.3255000114440918},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.3027999997138977},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C73301696","wikidata":"https://www.wikidata.org/wiki/Q5469984","display_name":"Formalism (music)","level":3,"score":0.2630000114440918},{"id":"https://openalex.org/C2780626000","wikidata":"https://www.wikidata.org/wiki/Q5936775","display_name":"Human-in-the-loop","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.2578999996185303}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2696454.2696455","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2696454.2696455","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Tenth Annual ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1405.6341","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1405.6341","pdf_url":"https://arxiv.org/pdf/1405.6341","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"pmh:oai:arXiv.org:1405.6341","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1405.6341","pdf_url":"https://arxiv.org/pdf/1405.6341","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W155097506","https://openalex.org/W1986014385","https://openalex.org/W1999874108","https://openalex.org/W2010780110","https://openalex.org/W2055921164","https://openalex.org/W2071601825","https://openalex.org/W2081034428","https://openalex.org/W2085837954","https://openalex.org/W2117578934","https://openalex.org/W2151265172","https://openalex.org/W2154342426","https://openalex.org/W2168359464","https://openalex.org/W2170403483","https://openalex.org/W2294988802","https://openalex.org/W2295827790","https://openalex.org/W2296267298","https://openalex.org/W3210839039"],"related_works":[],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,15,19,23,27,70,82,97,111,127,145,200,205,224],"framework":[3,150,174,184],"for":[4,22,51,113],"automatically":[5],"learning":[6,43,61,213],"human":[7,38,79,94,128,193,214],"user":[8,99,215],"models":[9,216],"from":[10,217],"joint-action":[11,218],"demonstrations":[12,219],"that":[13,100,116,136,212],"enables":[14],"robot":[16,115,138,146,156,166,181],"to":[17,120,153,168,188,192,196],"compute":[18,110],"robust":[20],"policy":[21,112],"collaborative":[24,233],"task":[25],"with":[26,144],"human.":[28],"First,":[29],"the":[30,55,78,93,105,114,121,137,148,165,170,172,183],"demonstrated":[31],"action":[32],"sequences":[33],"are":[34],"clustered":[35],"into":[36,69],"different":[37],"types":[39],"using":[40,199],"an":[41,58],"unsupervised":[42],"algorithm.":[44,62],"A":[45],"reward":[46,202],"function":[47,203],"is":[48,66,81],"then":[49,67],"learned":[50,64],"each":[52],"type":[53,80,95],"through":[54],"employment":[56],"of":[57,96,123],"inverse":[59],"reinforcement":[60],"The":[63,180],"model":[65],"incorporated":[68],"mixed-observability":[71],"Markov":[72],"decision":[73],"process":[74],"(MOMDP)":[75],"formulation,":[76],"wherein":[77],"partially":[83],"observable":[84],"variable.":[85],"With":[86],"this":[87,124],"framework,":[88],"we":[89],"can":[90,109,227],"infer":[91],"online":[92],"new":[98],"was":[101,185],"not":[102],"included":[103],"in":[104,223,231],"training":[106],"set,":[107],"and":[108,220],"will":[117],"be":[118,189],"aligned":[119],"preference":[122],"user.":[125],"In":[126,158],"subject":[129],"experiment":[130],"(n=30),":[131],"participants":[132,161],"agreed":[133],"more":[134,190],"strongly":[135],"anticipated":[139],"their":[140],"actions":[141,167,194],"when":[142],"working":[143],"incorporating":[147,182],"proposed":[149,173],"(p<0.01),":[151],"compared":[152,195],"manually":[154],"annotating":[155,164],"actions.":[157],"trials":[159],"where":[160],"faced":[162],"difficulty":[163],"complete":[169],"task,":[171],"significantly":[175],"improved":[176],"team":[177],"efficiency":[178],"(p<0.01).":[179,208],"also":[186],"found":[187],"responsive":[191],"policies":[197],"computed":[198],"hand-coded":[201],"by":[204],"domain":[206],"expert":[207],"These":[209],"results":[210],"indicate":[211],"encoding":[221],"them":[222],"MOMDP":[225],"formalism":[226],"support":[228],"effective":[229],"teaming":[230],"human-robot":[232],"tasks.":[234]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":12},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":5}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2016-06-24T00:00:00"}