{"id":"https://openalex.org/W3135582059","doi":null,"title":"Specifying User Preferences for Autonomous Robots through Interactive Learning","display_name":"Specifying User Preferences for Autonomous Robots through Interactive Learning","publication_year":2020,"publication_date":"2020-09-28","ids":{"openalex":"https://openalex.org/W3135582059","mag":"3135582059"},"language":"en","primary_location":{"id":"pmh:oai:uwspace.uwaterloo.ca:10012/16386","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10012/16386","pdf_url":"https://uwspace.uwaterloo.ca/bitstreams/c85ded34-2c10-427e-a398-140e2392bd73/download","source":{"id":"https://openalex.org/S4306401661","display_name":"UWSpace (University of Waterloo)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I151746483","host_organization_name":"University of Waterloo","host_organization_lineage":["https://openalex.org/I151746483"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Doctoral Thesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://uwspace.uwaterloo.ca/bitstreams/c85ded34-2c10-427e-a398-140e2392bd73/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083082763","display_name":"Nils Wilde","orcid":"https://orcid.org/0000-0003-3238-8153","observed_orcids":["https://orcid.org/0000-0003-3238-8153"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Nils Wilde","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-3238-8153","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5083082763"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.7089999914169312,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.7089999914169312,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.10520000010728836,"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":0.043299999088048935,"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/human-robot-interaction","display_name":"human-robot interaction","score":0.9010000228881836},{"id":"https://openalex.org/keywords/robot-task-specification","display_name":"robot task specification","score":0.8019999861717224},{"id":"https://openalex.org/keywords/user-preference-elicitation","display_name":"user preference elicitation","score":0.7229999899864197},{"id":"https://openalex.org/keywords/specification-revision","display_name":"specification revision","score":0.7829999923706055},{"id":"https://openalex.org/keywords/local-search","display_name":"local search","score":0.5199999809265137},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"multi-task learning","score":0.5400000214576721},{"id":"https://openalex.org/keywords/mobile-robot-path-planning","display_name":"mobile robot path planning","score":0.6290000081062317},{"id":"https://openalex.org/keywords/user-study","display_name":"user study","score":0.6439999938011169},{"id":"https://openalex.org/keywords/non-expert-users","display_name":"non-expert users","score":0.75},{"id":"https://openalex.org/keywords/robot-autonomy","display_name":"robot autonomy","score":0.38100001215934753}],"concepts":[{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.6902630925178528},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5453242659568787},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4929790496826172},{"id":"https://openalex.org/C2776716048","wikidata":"https://www.wikidata.org/wiki/Q6045290","display_name":"Interactive Learning","level":2,"score":0.42087432742118835},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3208065629005432},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3175269067287445}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:uwspace.uwaterloo.ca:10012/16386","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10012/16386","pdf_url":"https://uwspace.uwaterloo.ca/bitstreams/c85ded34-2c10-427e-a398-140e2392bd73/download","source":{"id":"https://openalex.org/S4306401661","display_name":"UWSpace (University of Waterloo)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I151746483","host_organization_name":"University of Waterloo","host_organization_lineage":["https://openalex.org/I151746483"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Doctoral Thesis"},{"id":"mag:3135582059","doi":null,"is_oa":false,"landing_page_url":"https://uwspace.uwaterloo.ca/handle/10012/16386","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:uwspace.uwaterloo.ca:10012/16386","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10012/16386","pdf_url":"https://uwspace.uwaterloo.ca/bitstreams/c85ded34-2c10-427e-a398-140e2392bd73/download","source":{"id":"https://openalex.org/S4306401661","display_name":"UWSpace (University of Waterloo)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I151746483","host_organization_name":"University of Waterloo","host_organization_lineage":["https://openalex.org/I151746483"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Doctoral Thesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3135582059.pdf","grobid_xml":"https://content.openalex.org/works/W3135582059.grobid-xml"},"referenced_works_count":83,"referenced_works":["https://openalex.org/W206015396","https://openalex.org/W1496357020","https://openalex.org/W1503398984","https://openalex.org/W1557310162","https://openalex.org/W1583953806","https://openalex.org/W1864112212","https://openalex.org/W1970269621","https://openalex.org/W1970916399","https://openalex.org/W1977655452","https://openalex.org/W1983599491","https://openalex.org/W1986014385","https://openalex.org/W1992157405","https://openalex.org/W1999874108","https://openalex.org/W2006912660","https://openalex.org/W2020530538","https://openalex.org/W2023727736","https://openalex.org/W2023862787","https://openalex.org/W2028186501","https://openalex.org/W2032191478","https://openalex.org/W2035236405","https://openalex.org/W2045134164","https://openalex.org/W2048076085","https://openalex.org/W2051407192","https://openalex.org/W2059097437","https://openalex.org/W2098774185","https://openalex.org/W2100267317","https://openalex.org/W2103012681","https://openalex.org/W2103020682","https://openalex.org/W2104641222","https://openalex.org/W2105156548","https://openalex.org/W2108703536","https://openalex.org/W2113029345","https://openalex.org/W2115826669","https://openalex.org/W2116671302","https://openalex.org/W2121806728","https://openalex.org/W2121863487","https://openalex.org/W2122219027","https://openalex.org/W2134765105","https://openalex.org/W2142298978","https://openalex.org/W2142828048","https://openalex.org/W2151074445","https://openalex.org/W2152575493","https://openalex.org/W2155817812","https://openalex.org/W2156160632","https://openalex.org/W2156163138","https://openalex.org/W2158582431","https://openalex.org/W2159018822","https://openalex.org/W2167842266","https://openalex.org/W2170345640","https://openalex.org/W2171054284","https://openalex.org/W2209116470","https://openalex.org/W2279443383","https://openalex.org/W2500624988","https://openalex.org/W2611243847","https://openalex.org/W2626804490","https://openalex.org/W2735021678","https://openalex.org/W2737479107","https://openalex.org/W2750866482","https://openalex.org/W2789905221","https://openalex.org/W2791858758","https://openalex.org/W2793667181","https://openalex.org/W2806174881","https://openalex.org/W2889977736","https://openalex.org/W2889990052","https://openalex.org/W2890208026","https://openalex.org/W2898045695","https://openalex.org/W2902937442","https://openalex.org/W2913737986","https://openalex.org/W2921962626","https://openalex.org/W2923018352","https://openalex.org/W2949115740","https://openalex.org/W2951249809","https://openalex.org/W2962795549","https://openalex.org/W2963099438","https://openalex.org/W2999620783","https://openalex.org/W3022961952","https://openalex.org/W3029228949","https://openalex.org/W3029645440","https://openalex.org/W3090470622","https://openalex.org/W3098878766","https://openalex.org/W3104160712","https://openalex.org/W3108252981","https://openalex.org/W3127820998"],"related_works":["https://openalex.org/W2963106920","https://openalex.org/W2913737986","https://openalex.org/W2979585617","https://openalex.org/W2793667181","https://openalex.org/W4393853298","https://openalex.org/W4392646421","https://openalex.org/W4410298297","https://openalex.org/W2899850214","https://openalex.org/W3022961952","https://openalex.org/W4416748594"],"abstract_inverted_index":{"This":[0,264,319],"thesis":[1],"studies":[2],"a":[3,41,127,130,249,308,324,333,360,389,445,454,488,508,553,640,688,716,744,756,765,795],"central":[4],"problem":[5],"in":[6,233,388,457,517,562,775],"human-robot":[7],"interaction":[8],"(HRI):":[9],"How":[10],"can":[11,112,132,612,662,720,746],"non-expert":[12],"users":[13,100,157,180,438,462],"specify":[14],"complex":[15],"behaviours":[16,52],"for":[17,23,126,242,266,273,307,345,401,407,420,524,550,618,630,669],"autonomous":[18,110],"robots?":[19],"A":[20,204],"common":[21],"technique":[22,576,629],"robot":[24,42,87,103,111,120,129,169,186,224,403,458,534,645,670,745,771],"task":[25,104,170,419],"specification":[26,243,447,554],"that":[27,67,245,255,304,310,368,435,514,592,708,777,794],"does":[28],"not":[29,493,529,799],"require":[30,494],"expert":[31],"knowledge":[32],"is":[33,43,65,246,285,305,311,321,336,343,352,371,386,394,424,767,780],"active":[34,174,413,573,593],"preference":[35,175,574,594,610],"learning.":[36,478],"The":[37,56,106,381,392,416],"desired":[38],"behaviour":[39,107,183,197,724],"of":[40,53,108,143,151,184,211,216,229,270,341,363,383,418,507,540,543,569,603,644,680,692,695,702,715,736,755,761],"learned":[44],"by":[45,115,709],"iteratively":[46,768],"presenting":[47],"the":[48,54,60,80,84,86,89,148,152,162,168,182,185,191,209,214,217,220,223,227,234,256,260,268,274,292,294,329,339,350,356,384,402,422,431,449,461,467,473,476,482,485,495,505,518,525,537,541,558,567,582,604,651,674,681,703,712,722,727,737,762,770,789,792],"user":[49,57,91,131,205,221,251,257,275,283,295,376,390,423,496,519,526,689,704,729,750,766,785,796],"with":[50,181,194,300,313,323,426],"alternative":[51,61,196,302,428,440],"robot.":[55,218],"then":[58],"chooses":[59],"they":[62,68],"prefer.":[63],"It":[64],"assumed":[66],"make":[69],"this":[70,369,778],"decision":[71],"based":[72,247,577,596,609,638,698],"on":[73,118,167,248,470,504,566,578,597,639,699,752,791],"an":[74,96,109,173,195,240,301,548,572,616,700],"internal,":[75],"hidden":[76,90],"cost":[77,92,153,206,235,262,501,520],"function.":[78,93,154,236,263,502],"From":[79,219,536],"user's":[81],"choice":[82,417],"among":[83],"alternatives,":[85],"learns":[88,225],"\\nWe":[94,237],"use":[95],"interactive":[97,477],"framework":[98,177,385],"allowing":[99],"to":[101,161,315,354,373,396,453,497,532,571,665,686,725,782,784],"create":[102],"specifications.":[105],"be":[113,159,202,613,663],"specified":[114],"defining":[116],"constraints":[117,146,165,200,212,276],"allowable":[119],"states":[121,646],"and":[122,213,279,411,442,556,560,621,624,647,678,759],"actions.":[123],"For":[124],"instance,":[125],"mobile":[128],"define":[133],"traffic":[134],"rules":[135],"such":[136,164,672],"as":[137,615,673],"roads,":[138],"slow":[139],"zones":[140],"or":[141],"areas":[142],"avoidance.":[144],"These":[145],"form":[147],"user-specified":[149],"terms":[150],"However,":[155],"inexperienced":[156],"might":[158,201],"oblivious":[160],"impact":[163,469],"have":[166],"performance.":[171,459],"Employing":[172],"learning":[176,414,450,552,575,595,611,659,710],"we":[178,290,433,480,491,512,546,719,741],"present":[179,291],"following":[187],"their":[188],"specification,":[189],"i.e.,":[190,231,522,581],"constraints,":[192,230,527],"together":[193,299],"where":[198],"some":[199],"violated.":[203],"function":[207],"trades-off":[208],"importance":[210,228],"performance":[215,471,559],"feedback,":[222],"about":[226,398,484,711,749],"parameters":[232,545],"first":[238],"introduce":[239],"algorithm":[241,351,393,549],"revision":[244,555],"deterministic":[250],"model:":[252],"We":[253,564,590,656,683,706,773],"assume":[254],"always":[258,498],"follows":[259],"proposed":[261],"allows":[265,406],"dividing":[267],"set":[269,643,691],"possible":[271,544,588],"weights":[272,281,331,523],"into":[277],"infeasible":[278],"feasible":[280,312,330],"whenever":[282],"feedback":[284],"obtained.":[286],"In":[287,487],"each":[288],"iteration":[289],"path":[293,303,320,335],"preferred":[296],"previously":[297],"again,":[298],"optimal":[306,357,690],"weight":[309],"respect":[314],"all":[316,437,587],"previous":[317],"iterations.":[318,364,380],"found":[322],"local":[325],"search,":[326],"iterating":[327],"over":[328,586],"until":[332],"new":[334],"found.":[337],"As":[338],"number":[340,362],"paths":[342],"finite":[344,361],"any":[346],"discrete":[347,620,642],"motion":[348,509,632,654,693,713,738],"planner,":[349,718],"guaranteed":[353],"find":[355],"solution":[358],"within":[359,378],"Simulation":[365],"results":[366],"show":[367,434,513,591,684],"approach":[370,779],"suitable":[372,781],"effectively":[374],"revise":[375],"specifications":[377,465],"few":[379],"practicality":[382],"investigated":[387],"study.":[391],"extended":[395],"learn":[397,666,748],"multiple":[399],"tasks":[400],"simultaneously,":[404],"which":[405,421],"more":[408],"realistic":[409],"scenarios":[410],"another":[412],"component:":[415],"presented":[425],"two":[427],"solutions.":[429,589],"Through":[430],"study":[432,657,742],"nearly":[436],"accept":[439],"solutions":[441],"thus":[443],"obtain":[444],"revised":[446],"through":[448],"process,":[451],"leading":[452],"substantial":[455],"improvement":[456],"Also,":[460],"whose":[463],"initial":[464],"had":[466],"largest":[468],"benefit":[472],"most":[474],"from":[475,660],"\\nNext,":[479],"weaken":[481],"assumptions":[483],"user:":[486],"probabilistic":[489],"model":[490],"do":[492,528],"follow":[499,726],"our":[500],"Based":[503],"sensitivity":[506,570],"planning":[510,633],"problem,":[511],"different":[515,533],"values":[516],"function,":[521],"necessarily":[530],"lead":[531],"behaviour.":[535,772],"implied":[538],"discretization":[539],"space":[542],"derive":[547],"efficiently":[551],"demonstrate":[557,707,774],"robustness":[561],"simulations.":[563],"build":[565],"notion":[568],"maximum":[579,583],"regret,":[580],"error":[584],"ratio":[585],"regret":[598,608],"substantially":[599],"outperforms":[600],"other":[601],"state":[602,623,635],"art":[605],"approaches.":[606],"Further,":[607],"used":[614,664],"heuristic":[617],"both":[619,753],"continuous":[622],"action":[625],"spaces.":[626],"\\nAn":[627],"emerging":[628],"real-time":[631],"are":[634,798],"lattice":[636,717,757],"planners,":[637],"regular":[641],"pre-computed":[648],"motions":[649,754],"connecting":[650],"states,":[652],"called":[653],"primitives.":[655],"how":[658,685,743],"demonstrations":[661],"global":[667,728],"preferences":[668,730,751,786],"movement,":[671],"trade-off":[675],"between":[676],"time":[677,735],"jerkiness":[679],"motions.":[682],"compute":[687],"primitives":[694,714],"given":[696],"size,":[697],"estimate":[701],"preferences.":[705],"shape":[721],"robot's":[723],"while":[731],"ensuring":[732],"good":[733],"computation":[734],"planner.":[739],"Furthermore,":[740],"simultaneously":[747],"planner":[758],"parts":[760],"environment":[763,793],"when":[764,788],"correcting":[769],"simulations":[776],"adapt":[783],"even":[787],"features":[790],"considers":[797],"given.":[800]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2021-03-15T00:00:00"}