{"id":"https://openalex.org/W3003881683","doi":"https://doi.org/10.1109/iros40897.2019.8967737","title":"A-EXP4: Online Social Policy Learning for Adaptive Robot-Pedestrian Interaction","display_name":"A-EXP4: Online Social Policy Learning for Adaptive Robot-Pedestrian Interaction","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3003881683","doi":"https://doi.org/10.1109/iros40897.2019.8967737","mag":"3003881683"},"language":"en","primary_location":{"id":"doi:10.1109/iros40897.2019.8967737","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros40897.2019.8967737","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5088881074","display_name":"Pengju Jin","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pengju Jin","raw_affiliation_strings":["Authors are affiliated with the Robotics Institute, Carnegie Mellon University,Pittsburgh,USA,PA 15213"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Authors are affiliated with the Robotics Institute, Carnegie Mellon University,Pittsburgh,USA,PA 15213","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025893246","display_name":"Eshed Ohn-Bar","orcid":"https://orcid.org/0000-0002-6750-7987"},"institutions":[{"id":"https://openalex.org/I4210135521","display_name":"Max Planck Institute for Intelligent Systems","ror":"https://ror.org/04fq9j139","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210135521"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Eshed Ohn-Bar","raw_affiliation_strings":["Max Planck Institute for Intelligent Systems"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Intelligent Systems","institution_ids":["https://openalex.org/I4210135521"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037322163","display_name":"Kris Kitani","orcid":"https://orcid.org/0000-0002-9389-4060"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kris Kitani","raw_affiliation_strings":["Authors are affiliated with the Robotics Institute, Carnegie Mellon University,Pittsburgh,USA,PA 15213"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Authors are affiliated with the Robotics Institute, Carnegie Mellon University,Pittsburgh,USA,PA 15213","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091550931","display_name":"Chieko Asakawa","orcid":"https://orcid.org/0000-0002-5447-1305"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chieko Asakawa","raw_affiliation_strings":["Authors are affiliated with the Robotics Institute, Carnegie Mellon University,Pittsburgh,USA,PA 15213"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Authors are affiliated with the Robotics Institute, Carnegie Mellon University,Pittsburgh,USA,PA 15213","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.18921826,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"5086","last_page":"5093"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9908000230789185,"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":0.9908000230789185,"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/T11980","display_name":"Human Mobility and Location-Based Analysis","score":0.9855999946594238,"subfield":{"id":"https://openalex.org/subfields/3313","display_name":"Transportation"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11942","display_name":"Transportation and Mobility Innovations","score":0.9768999814987183,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/computer-science","display_name":"Computer science","score":0.7387570738792419},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6539256572723389},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6138749122619629},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5723355412483215},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5580894351005554},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5082973837852478},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5028337836265564},{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.45850425958633423},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45834609866142273},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4559025466442108},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.4347577393054962},{"id":"https://openalex.org/keywords/pedestrian","display_name":"Pedestrian","score":0.4218323230743408},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4117392599582672},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3936934471130371},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.26617878675460815},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12996038794517517}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7387570738792419},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6539256572723389},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6138749122619629},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5723355412483215},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5580894351005554},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5082973837852478},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5028337836265564},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.45850425958633423},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45834609866142273},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4559025466442108},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.4347577393054962},{"id":"https://openalex.org/C2777113093","wikidata":"https://www.wikidata.org/wiki/Q221488","display_name":"Pedestrian","level":2,"score":0.4218323230743408},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4117392599582672},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3936934471130371},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.26617878675460815},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12996038794517517},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C22212356","wikidata":"https://www.wikidata.org/wiki/Q775325","display_name":"Transport engineering","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"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":1,"locations":[{"id":"doi:10.1109/iros40897.2019.8967737","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros40897.2019.8967737","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W77456527","https://openalex.org/W123233698","https://openalex.org/W1579979603","https://openalex.org/W1651456183","https://openalex.org/W1912700219","https://openalex.org/W1969173200","https://openalex.org/W1977655452","https://openalex.org/W2012392077","https://openalex.org/W2020999234","https://openalex.org/W2029780883","https://openalex.org/W2077902449","https://openalex.org/W2088861238","https://openalex.org/W2101821104","https://openalex.org/W2103715332","https://openalex.org/W2105934661","https://openalex.org/W2119717200","https://openalex.org/W2120070743","https://openalex.org/W2127107099","https://openalex.org/W2127498532","https://openalex.org/W2137104525","https://openalex.org/W2140135625","https://openalex.org/W2160609653","https://openalex.org/W2162932021","https://openalex.org/W2167117957","https://openalex.org/W2173248099","https://openalex.org/W2256838191","https://openalex.org/W2341852456","https://openalex.org/W2343174257","https://openalex.org/W2424778531","https://openalex.org/W2463627759","https://openalex.org/W2508778727","https://openalex.org/W2512654307","https://openalex.org/W2536057734","https://openalex.org/W2537547826","https://openalex.org/W2565370028","https://openalex.org/W2736730521","https://openalex.org/W2765252989","https://openalex.org/W2817973999","https://openalex.org/W2888465049","https://openalex.org/W2889628315","https://openalex.org/W2895143214","https://openalex.org/W2911273949","https://openalex.org/W2919658942","https://openalex.org/W2951371685","https://openalex.org/W2953123842","https://openalex.org/W2963888093","https://openalex.org/W2964161785","https://openalex.org/W2964338736","https://openalex.org/W2998145016","https://openalex.org/W4236023519","https://openalex.org/W4249617246","https://openalex.org/W6603163463","https://openalex.org/W6621878715","https://openalex.org/W6634861202","https://openalex.org/W6653435097","https://openalex.org/W6675657435","https://openalex.org/W6680657880","https://openalex.org/W6682849425","https://openalex.org/W6684921986","https://openalex.org/W6691885583","https://openalex.org/W6740017579","https://openalex.org/W6752986182"],"related_works":["https://openalex.org/W4376155396","https://openalex.org/W2971351794","https://openalex.org/W1947085858","https://openalex.org/W2101991911","https://openalex.org/W2174986909","https://openalex.org/W2527791220","https://openalex.org/W2155070487","https://openalex.org/W4311589891","https://openalex.org/W1992295166","https://openalex.org/W2143508933"],"abstract_inverted_index":{"We":[0],"study":[1],"self-supervised":[2],"adaptation":[3,64,147,165],"of":[4,60,95,130,138,161,166,175,203],"a":[5,12,46,73,82,100,159,167,179,221],"robot's":[6,168],"policy":[7,13,78,217],"for":[8,14,51,156,218],"social":[9,39,143],"interaction,":[10],"i.e.,":[11],"active":[15],"communication":[16],"with":[17,135],"surrounding":[18],"pedestrians":[19,139,204],"through":[20,145],"audio":[21,193],"or":[22],"visual":[23],"signals.":[24],"Inspired":[25],"by":[26,196],"the":[27,53,77,93,104,114,128,146,150,173,189,197,201,215,236],"observation":[28],"that":[29,110],"humans":[30],"continually":[31],"adapt":[32,214],"their":[33],"behavior":[34,202],"when":[35],"interacting":[36],"under":[37],"varying":[38],"context,":[40],"we":[41,71,170,209],"propose":[42],"Adaptive":[43],"EXP4":[44,237],"(A-EXP4),":[45],"novel":[47],"online":[48],"learning":[49],"algorithm":[50,177,190],"adapting":[52],"robot-pedestrian":[54],"interaction":[55,134,216],"policy.":[56],"To":[57],"address":[58],"limitations":[59],"bandit":[61],"algorithms":[62],"in":[63,118,132,158,224,228,231],"to":[65,91,113,212,235],"unseen":[66],"and":[67,98,124,205],"highly":[68],"dynamic":[69],"scenarios,":[70],"employ":[72],"mixture":[74,101],"model":[75,102],"over":[76,103],"parameter":[79],"space.":[80],"Specifically,":[81],"Dirichlet":[83],"Process":[84],"Gaussian":[85],"Mixture":[86],"Model":[87],"(DPMM)":[88],"is":[89,153],"used":[90],"cluster":[92],"parameters":[94],"sampled":[96],"policies":[97,109],"maintain":[99],"clusters,":[105],"hence":[106],"effectively":[107,213],"discovering":[108],"are":[111],"suitable":[112],"current":[115],"environmental":[116],"context":[117],"an":[119],"unsupervised":[120],"manner.":[121],"Our":[122],"simulated":[123],"real-world":[125],"experiments":[126],"demonstrate":[127],"feasibility":[129],"A-EXP4":[131,151,211],"accommodating":[133],"different":[136],"types":[137],"while":[140],"jointly":[141],"minimizing":[142],"disruption":[144],"process.":[148],"While":[149],"formulation":[152],"kept":[154],"general":[155],"application":[157],"variety":[160],"domains":[162],"requiring":[163],"continual":[164],"policy,":[169],"specifically":[171],"evaluate":[172],"performance":[174],"our":[176],"using":[178],"suitcase-inspired":[180],"assistive":[181,187],"robotic":[182],"platform.":[183],"In":[184],"this":[185],"concrete":[186],"scenario,":[188],"observes":[191],"how":[192],"signals":[194],"produced":[195],"navigational":[198],"system":[199],"affect":[200],"adapts":[206],"accordingly.":[207],"Consequently,":[208],"find":[210],"gently":[219],"clearing":[220],"navigation":[222],"path":[223],"crowded":[225],"settings,":[226],"resulting":[227],"significant":[229],"reduction":[230],"empirical":[232],"regret":[233],"compared":[234],"baseline.":[238]},"counts_by_year":[{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}