{"id":"https://openalex.org/W2898067520","doi":"https://doi.org/10.1109/coase.2018.8560342","title":"Constraint Estimation and Derivative-Free Recovery for Robot Learning from Demonstrations","display_name":"Constraint Estimation and Derivative-Free Recovery for Robot Learning from Demonstrations","publication_year":2018,"publication_date":"2018-08-01","ids":{"openalex":"https://openalex.org/W2898067520","doi":"https://doi.org/10.1109/coase.2018.8560342","mag":"2898067520"},"language":"en","primary_location":{"id":"doi:10.1109/coase.2018.8560342","is_oa":false,"landing_page_url":"https://doi.org/10.1109/coase.2018.8560342","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE 14th International 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/A5100348028","display_name":"Jonathan Lee","orcid":"https://orcid.org/0000-0002-1828-1707"},"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":"Jonathan Lee","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, The AUTOLAB at UC Berkeley, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, The AUTOLAB at UC Berkeley, Berkeley, CA, USA","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":["Department of Electrical Engineering and Computer Science, The AUTOLAB at UC Berkeley, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, The AUTOLAB at UC Berkeley, Berkeley, CA, USA","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":["Department of Electrical Engineering and Computer Science, The AUTOLAB at UC Berkeley, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, The AUTOLAB at UC Berkeley, Berkeley, CA, USA","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":[{"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":"Ken Goldberg","raw_affiliation_strings":["Department of Industrial Engineering and Operations Research, The AUTOLAB at UC Berkeley, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering and Operations Research, The AUTOLAB at UC Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100348028"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":0.3679,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.61556251,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"7","issue":null,"first_page":"270","last_page":"277"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9970999956130981,"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":0.9810000061988831,"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/robot","display_name":"Robot","score":0.6881594657897949},{"id":"https://openalex.org/keywords/supervisor","display_name":"Supervisor","score":0.6650524735450745},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6588847041130066},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.6437081694602966},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5992416739463806},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5348851084709167},{"id":"https://openalex.org/keywords/phase","display_name":"Phase (matter)","score":0.43800777196884155},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.43632814288139343},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.4361906945705414},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.43555331230163574},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.42510056495666504},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39598628878593445},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.3609376847743988},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3409254252910614},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1989905834197998},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.18052560091018677},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1587802767753601}],"concepts":[{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6881594657897949},{"id":"https://openalex.org/C2779110517","wikidata":"https://www.wikidata.org/wiki/Q1240788","display_name":"Supervisor","level":2,"score":0.6650524735450745},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6588847041130066},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.6437081694602966},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5992416739463806},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5348851084709167},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.43800777196884155},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.43632814288139343},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.4361906945705414},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.43555331230163574},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.42510056495666504},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39598628878593445},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.3609376847743988},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3409254252910614},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1989905834197998},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.18052560091018677},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1587802767753601},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/coase.2018.8560342","is_oa":false,"landing_page_url":"https://doi.org/10.1109/coase.2018.8560342","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE 14th International Conference on Automation Science and Engineering (CASE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5600000023841858,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1505854147","https://openalex.org/W1560724230","https://openalex.org/W1633960869","https://openalex.org/W1684361744","https://openalex.org/W1771410628","https://openalex.org/W1963790880","https://openalex.org/W1993294034","https://openalex.org/W2018346149","https://openalex.org/W2039301348","https://openalex.org/W2053572490","https://openalex.org/W2118858375","https://openalex.org/W2132870739","https://openalex.org/W2135043890","https://openalex.org/W2137233422","https://openalex.org/W2142641780","https://openalex.org/W2158607953","https://openalex.org/W2158782408","https://openalex.org/W2160960847","https://openalex.org/W2318613964","https://openalex.org/W2409942531","https://openalex.org/W2551182329","https://openalex.org/W2618170641","https://openalex.org/W2735049119","https://openalex.org/W2736750746","https://openalex.org/W2738190501","https://openalex.org/W2750875954","https://openalex.org/W2774527530","https://openalex.org/W2782882532","https://openalex.org/W2782957303","https://openalex.org/W2952996256","https://openalex.org/W2962764078","https://openalex.org/W2962803570","https://openalex.org/W2963221965","https://openalex.org/W2963525569","https://openalex.org/W2964097578","https://openalex.org/W3144619878","https://openalex.org/W4211008118","https://openalex.org/W4293545785","https://openalex.org/W6638018090","https://openalex.org/W6680724558","https://openalex.org/W6680838405","https://openalex.org/W6737893269","https://openalex.org/W6743636021","https://openalex.org/W6747311492"],"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/W4320164562","https://openalex.org/W1410705132","https://openalex.org/W2471401384"],"abstract_inverted_index":{"Learning":[0],"from":[1,83,164],"human":[2],"demonstrations":[3,84,109],"can":[4,51,220],"facilitate":[5],"automation":[6],"but":[7],"is":[8,31],"risky":[9],"because":[10],"the":[11,14,36,48,90,100,112,129,144,148,151,161,165,168,182,191,200,205,208],"execution":[12,46],"of":[13,47,107,150,167,193],"learned":[15,49,145],"policy":[16,50,141,146,158],"might":[17],"lead":[18],"to":[19,27,60,93,137,155,159,197],"collisions":[20,222,244],"and":[21,110,153,237],"other":[22],"failures.":[23],"Adding":[24],"explicit":[25],"constraints":[26,44,116,206],"avoid":[28],"unsafe":[29],"states":[30],"generally":[32],"not":[33,203],"possible":[34],"when":[35],"state":[37,185],"representations":[38],"are":[39,58],"complex.":[40],"Furthermore,":[41],"enforcing":[42],"these":[43],"during":[45],"be":[52],"challenging":[53],"in":[54,66,85,147,184,215],"environments":[55],"where":[56,89],"dynamics":[57],"difficult":[59],"model":[61],"such":[62],"as":[63,114],"push":[64],"mechanics":[65],"grasping.":[67],"In":[68,99,128],"this":[69,134],"paper,":[70],"we":[71,103,132],"propose":[72,121],"Derivative-Free":[73],"Recovery":[74],"(DFR),":[75],"a":[76,122,139,156,226,232,238],"two-phase":[77],"method":[78],"for":[79,125],"generating":[80],"robust":[81],"policies":[82],"robotic":[86],"manipulation":[87],"tasks":[88],"system":[91],"comes":[92],"rest":[94],"at":[95,186],"each":[96,187],"time":[97,188],"step.":[98],"first":[101],"phase,":[102,131],"use":[104,133],"support":[105,113,135,152,169],"estimation":[106],"supervisor":[108],"treat":[111],"implicit":[115],"on":[117],"states.":[118],"We":[119,175],"also":[120],"time-varying":[123],"modification":[124],"sequential":[126],"tasks.":[127],"second":[130],"estimate":[136],"derive":[138],"switching":[140],"that":[142,199,218],"employs":[143],"interior":[149],"switches":[154],"recovery":[157,209],"steer":[160],"robot":[162,201],"away":[163],"boundary":[166],"if":[170],"it":[171],"drifts":[172],"too":[173],"close.":[174],"present":[176],"additional":[177],"conditions,":[178],"which":[179],"linearly":[180],"bound":[181],"difference":[183],"step":[189],"by":[190,223,245],"magnitude":[192],"control,":[194],"allowing":[195],"us":[196],"prove":[198],"will":[202],"violate":[204],"using":[207,231],"policy.":[210],"A":[211],"simulated":[212],"pushing":[213],"task":[214,230],"MuJoCo":[216],"suggests":[217],"DFR":[219,242],"reduce":[221],"83%.":[224],"On":[225],"physical":[227],"line":[228],"tracking":[229],"da":[233],"Vinci":[234],"Surgical":[235],"Robot":[236],"moving":[239],"Stewart":[240],"platform,":[241],"reduced":[243],"84%.":[246]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}