{"id":"https://openalex.org/W2782957303","doi":"https://doi.org/10.1109/coase.2017.8256095","title":"An algorithm and user study for teaching bilateral manipulation via iterated best response demonstrations","display_name":"An algorithm and user study for teaching bilateral manipulation via iterated best response demonstrations","publication_year":2017,"publication_date":"2017-08-01","ids":{"openalex":"https://openalex.org/W2782957303","doi":"https://doi.org/10.1109/coase.2017.8256095","mag":"2782957303"},"language":"en","primary_location":{"id":"doi:10.1109/coase.2017.8256095","is_oa":false,"landing_page_url":"https://doi.org/10.1109/coase.2017.8256095","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 13th IEEE Conference on Automation Science and Engineering (CASE)","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/A5014379165","display_name":"Carolyn Chen","orcid":"https://orcid.org/0000-0003-4933-6544"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Carolyn Chen","raw_affiliation_strings":["EECS, AUTOLAB UC Berkeley"],"affiliations":[{"raw_affiliation_string":"EECS, AUTOLAB UC Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018480426","display_name":"Sanjay Krishnan","orcid":"https://orcid.org/0000-0001-6968-4090"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjay Krishnan","raw_affiliation_strings":["EECS, AUTOLAB UC Berkeley"],"affiliations":[{"raw_affiliation_string":"EECS, AUTOLAB UC Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052716347","display_name":"Michael Laskey","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Laskey","raw_affiliation_strings":["EECS, AUTOLAB UC Berkeley"],"affiliations":[{"raw_affiliation_string":"EECS, AUTOLAB UC Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073588383","display_name":"Roy Fox","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roy Fox","raw_affiliation_strings":["EECS, AUTOLAB UC Berkeley"],"affiliations":[{"raw_affiliation_string":"EECS, AUTOLAB UC Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050342525","display_name":"Ken Goldberg","orcid":"https://orcid.org/0000-0002-2661-4524"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ken Goldberg","raw_affiliation_strings":["IEOR, CA, USA"],"affiliations":[{"raw_affiliation_string":"IEOR, CA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5014379165"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":0.6035,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.71405341,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"1","issue":null,"first_page":"151","last_page":"158"},"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":0.9876999855041504,"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/T10571","display_name":"Robotic Mechanisms and Dynamics","score":0.9596999883651733,"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/supervisor","display_name":"Supervisor","score":0.8622157573699951},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6992016434669495},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6790606379508972},{"id":"https://openalex.org/keywords/iterated-function","display_name":"Iterated function","score":0.6145742535591125},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5454760789871216},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4264169931411743},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.41223275661468506},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3837495446205139},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.382021427154541},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09705090522766113},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0901130735874176}],"concepts":[{"id":"https://openalex.org/C2779110517","wikidata":"https://www.wikidata.org/wiki/Q1240788","display_name":"Supervisor","level":2,"score":0.8622157573699951},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6992016434669495},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6790606379508972},{"id":"https://openalex.org/C140479938","wikidata":"https://www.wikidata.org/wiki/Q5254619","display_name":"Iterated function","level":2,"score":0.6145742535591125},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5454760789871216},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4264169931411743},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.41223275661468506},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3837495446205139},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.382021427154541},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09705090522766113},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0901130735874176},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/coase.2017.8256095","is_oa":false,"landing_page_url":"https://doi.org/10.1109/coase.2017.8256095","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 13th IEEE Conference on Automation Science and Engineering (CASE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4000000059604645,"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1584687743","https://openalex.org/W1931877416","https://openalex.org/W1986014385","https://openalex.org/W1995411041","https://openalex.org/W2013293242","https://openalex.org/W2018346149","https://openalex.org/W2024853171","https://openalex.org/W2050635357","https://openalex.org/W2078763164","https://openalex.org/W2084575083","https://openalex.org/W2092619707","https://openalex.org/W2103151730","https://openalex.org/W2125602005","https://openalex.org/W2147168033","https://openalex.org/W2158976313","https://openalex.org/W2167224731","https://openalex.org/W2220490338","https://openalex.org/W2291646284","https://openalex.org/W2292863051","https://openalex.org/W2293818481","https://openalex.org/W2492636994","https://openalex.org/W2527925052","https://openalex.org/W2551182329","https://openalex.org/W2558355904","https://openalex.org/W2562192611","https://openalex.org/W2581799494","https://openalex.org/W2738190501","https://openalex.org/W2783091972","https://openalex.org/W2962957031","https://openalex.org/W3146724588","https://openalex.org/W4229812034","https://openalex.org/W4235291218","https://openalex.org/W6640174482","https://openalex.org/W6684338915","https://openalex.org/W6696760139","https://openalex.org/W6730489210","https://openalex.org/W7073631092"],"related_works":["https://openalex.org/W4387731985","https://openalex.org/W2755149878","https://openalex.org/W2468425257","https://openalex.org/W2941808082","https://openalex.org/W4379086698","https://openalex.org/W2528721242","https://openalex.org/W4377009725","https://openalex.org/W2110944602","https://openalex.org/W3213722473","https://openalex.org/W3196817267"],"abstract_inverted_index":{"Human":[0],"demonstrations":[1,24,103,109,122,134],"can":[2,16],"be":[3,17],"valuable":[4],"for":[5,19,25,112,142,149],"teaching":[6],"robots":[7],"to":[8,22,62,158,174],"perform":[9],"manipulation":[10],"and":[11,71,106,197],"coordination":[12],"tasks.":[13],"However,":[14],"it":[15],"difficult":[18],"human":[20,147],"supervisors":[21],"provide":[23],"multilateral":[26],"(multi-arm)":[27],"tasks,":[28],"which":[29,47],"require":[30],"divided":[31],"attention.":[32],"In":[33],"this":[34,125],"paper,":[35],"we":[36],"propose":[37],"a":[38,60,79,90,94,159],"new":[39],"algorithm":[40,58],"called":[41],"Bilateral":[42],"Iterated":[43,54],"Best":[44,55],"Response":[45],"(BIBR),":[46],"builds":[48],"on":[49],"the":[50,73,116,146,150,154,165,169,177,181],"game-theoretic":[51],"concept":[52],"of":[53,75,83,168,185],"Response.":[56],"This":[57],"allows":[59],"supervisor":[61,69],"train":[63],"each":[64],"manipulator":[65,114],"iteratively,":[66],"thereby":[67],"reducing":[68],"burden":[70],"improving":[72],"quality":[74],"demonstrations.":[76,186],"We":[77,97],"present":[78],"web-based":[80],"user":[81],"study":[82],"51":[84],"participants":[85],"controlling":[86],"two":[87],"agents":[88],"in":[89,176,180,205],"GridWorld":[91],"environment":[92],"with":[93],"keyboard":[95],"interface.":[96],"confirm":[98],"prior":[99],"work":[100],"that":[101,192],"bilateral":[102,130,160],"are":[104],"noisier":[105],"longer":[107],"than":[108],"provided":[110],"separately":[111],"either":[113],"when":[115],"task":[117,179],"is":[118],"asymmetric.":[119],"As":[120],"unilateral":[121,133],"lack":[123],"coordination,":[124],"paper":[126],"proposes":[127],"learning":[128],"coordinated":[129],"policies":[131,189],"from":[132,172],"by":[135],"rolling":[136],"out":[137],"an":[138],"estimated":[139,155],"robot":[140],"policy":[141,171],"one":[143],"arm":[144],"while":[145],"demonstrates":[148],"other,":[151],"iteratively":[152],"updating":[153],"policy.":[156],"Compared":[157],"demonstration":[161],"baseline,":[162],"BIBR":[163],"improves":[164],"success":[166],"rate":[167],"learned":[170],"29.17%":[173],"55.55%":[175],"asymmetric":[178],"first":[182],"full":[183],"round":[184],"Furthermore,":[187],"these":[188],"learn":[190],"trajectories":[191],"have":[193,201],"8.63%":[194],"fewer":[195,203],"steps":[196],"smoother":[198],"trajectories,":[199],"i.e.,":[200],"44.15%":[202],"changes":[204],"direction.":[206]},"counts_by_year":[{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}