{"id":"https://openalex.org/W2963367680","doi":"https://doi.org/10.1609/aaai.v33i01.33012462","title":"Efficiently Combining Human Demonstrations and Interventions for Safe Training of Autonomous Systems in Real-Time","display_name":"Efficiently Combining Human Demonstrations and Interventions for Safe Training of Autonomous Systems in Real-Time","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2963367680","doi":"https://doi.org/10.1609/aaai.v33i01.33012462","mag":"2963367680"},"language":"en","primary_location":{"id":"pmh:oai:ojs.aaai.org:article/4091","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/4091","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"},"type":"article","indexed_in":[],"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/A5069949825","display_name":"Vinicius G. Goecks","orcid":"https://orcid.org/0000-0002-4481-671X"},"institutions":[{"id":"https://openalex.org/I2801613365","display_name":"Mitchell Institute","ror":"https://ror.org/03ds72003","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I2801613365"]},{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Goecks, Vinicius G.","raw_affiliation_strings":["Texas A&M University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texas A&M University","institution_ids":["https://openalex.org/I2801613365","https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042275001","display_name":"Gregory M. Gremillion","orcid":"https://orcid.org/0000-0002-0205-688X"},"institutions":[{"id":"https://openalex.org/I166416128","display_name":"DEVCOM Army Research Laboratory","ror":"https://ror.org/011hc8f90","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I166416128","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gremillion, Gregory M.","raw_affiliation_strings":["US Army Research Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"US Army Research Laboratory","institution_ids":["https://openalex.org/I166416128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051690828","display_name":"Vernon J. Lawhern","orcid":"https://orcid.org/0000-0002-3921-8723"},"institutions":[{"id":"https://openalex.org/I166416128","display_name":"DEVCOM Army Research Laboratory","ror":"https://ror.org/011hc8f90","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I166416128","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lawhern, Vernon J.","raw_affiliation_strings":["US Army Research Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"US Army Research Laboratory","institution_ids":["https://openalex.org/I166416128"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007706088","display_name":"John Valasek","orcid":"https://orcid.org/0000-0003-1999-0561"},"institutions":[{"id":"https://openalex.org/I2801613365","display_name":"Mitchell Institute","ror":"https://ror.org/03ds72003","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I2801613365"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Valasek, John","raw_affiliation_strings":["Texas A&M"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texas A&M","institution_ids":["https://openalex.org/I2801613365"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079459509","display_name":"Nicholas R. Waytowich","orcid":"https://orcid.org/0000-0002-3786-0675"},"institutions":[{"id":"https://openalex.org/I166416128","display_name":"DEVCOM Army Research Laboratory","ror":"https://ror.org/011hc8f90","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I166416128","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Waytowich, Nicholas R.","raw_affiliation_strings":["US Army  Research Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"US Army  Research Laboratory","institution_ids":["https://openalex.org/I166416128"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.6234,"has_fulltext":true,"cited_by_count":37,"citation_normalized_percentile":{"value":0.9335964,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9911999702453613,"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":0.9911999702453613,"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":0.9850000143051147,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9595000147819519,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7430614829063416},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7235620617866516},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.6525275707244873},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.6469935774803162},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.6102867722511292},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.5810997486114502},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4890783429145813},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.484551340341568},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.33114954829216003},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1345781683921814},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08689132332801819},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.06848210096359253}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7430614829063416},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7235620617866516},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.6525275707244873},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6469935774803162},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.6102867722511292},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.5810997486114502},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4890783429145813},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.484551340341568},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.33114954829216003},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1345781683921814},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08689132332801819},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.06848210096359253},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:ojs.aaai.org:article/4091","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/4091","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5259331294","display_name":null,"funder_award_id":"W911NF","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"},{"id":"https://openalex.org/G7637036795","display_name":null,"funder_award_id":"W911NF-18-2-0134","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"}],"funders":[{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W187005120","https://openalex.org/W1931877416","https://openalex.org/W1980969546","https://openalex.org/W1986014385","https://openalex.org/W2081034428","https://openalex.org/W2119388568","https://openalex.org/W2145339207","https://openalex.org/W2296673577","https://openalex.org/W2342840547","https://openalex.org/W2615547864","https://openalex.org/W2736601468","https://openalex.org/W2736629007","https://openalex.org/W2746553466","https://openalex.org/W2788518687","https://openalex.org/W2803761331","https://openalex.org/W2897664012","https://openalex.org/W2963489214","https://openalex.org/W3104515094","https://openalex.org/W4214717370","https://openalex.org/W4289667021","https://openalex.org/W4300110528"],"related_works":["https://openalex.org/W4313443006","https://openalex.org/W2945374968","https://openalex.org/W4385452045","https://openalex.org/W4293777179","https://openalex.org/W2164070813","https://openalex.org/W2363929919","https://openalex.org/W2135608140","https://openalex.org/W4224231624","https://openalex.org/W2369648859","https://openalex.org/W2319626700"],"abstract_inverted_index":{"This":[0,154],"paper":[1],"investigates":[2],"how":[3],"to":[4,11,54,66,76,80,137,150],"utilize":[5],"different":[6],"forms":[7],"of":[8,30,45,88,132,161,173],"human":[9,22,46,52,133,162],"interaction":[10,134,163],"safely":[12],"train":[13],"autonomous":[14,82,96,176],"systems":[15],"in":[16,94,117],"realtime":[17],"by":[18,72],"learning":[19,138],"from":[20,113,139],"both":[21,166],"demonstrations":[23,53,140],"and":[24,107,110,170],"interventions.":[25],"We":[26,90],"implement":[27],"two":[28],"components":[29],"the":[31,73,129,167],"Cycle-of":[32],"Learning":[33],"for":[34,41,68,128,175],"Autonomous":[35],"Systems,":[36],"which":[37],"is":[38],"our":[39],"framework":[40],"combining":[42,158],"multiple":[43,159],"modalities":[44],"interaction.":[47],"The":[48],"current":[49],"effort":[50],"employs":[51],"teach":[55,77],"a":[56,100,114,118],"desired":[57],"behavior":[58],"via":[59],"imitation":[60,74],"learning,":[61],"then":[62],"leverages":[63],"intervention":[64],"data":[65,149],"correct":[67],"undesired":[69],"behaviors":[70],"produced":[71],"learner":[75],"novel":[78],"tasks":[79],"an":[81,95],"agent":[83],"safely,":[84],"after":[85],"only":[86],"minutes":[87],"training.":[89],"demonstrate":[91],"this":[92],"method":[93,123],"perching":[97],"task":[98,125],"using":[99],"quadrotor":[101],"with":[102],"continuous":[103],"roll,":[104],"pitch,":[105],"yaw,":[106],"throttle":[108],"commands":[109],"imagery":[111],"captured":[112],"downward-facing":[115],"camera":[116],"high-fidelity":[119],"simulated":[120],"environment.":[121],"Our":[122],"improves":[124],"completion":[126],"performance":[127,172],"same":[130],"amount":[131],"when":[135],"compared":[136],"alone,":[141],"while":[142],"also":[143],"requiring":[144],"on":[145],"average":[146],"32%":[147],"less":[148],"achieve":[151],"that":[152,157],"performance.":[153],"provides":[155],"evidence":[156],"modes":[160],"can":[164],"increase":[165],"training":[168],"speed":[169],"overall":[171],"policies":[174],"systems.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":8}],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2025-10-10T00:00:00"}