{"id":"https://openalex.org/W4382936099","doi":"https://doi.org/10.23919/acc55779.2023.10156267","title":"Effectiveness of Warm-Start PPO for Guidance with Highly Constrained Nonlinear Fixed-Wing Dynamics","display_name":"Effectiveness of Warm-Start PPO for Guidance with Highly Constrained Nonlinear Fixed-Wing Dynamics","publication_year":2023,"publication_date":"2023-05-31","ids":{"openalex":"https://openalex.org/W4382936099","doi":"https://doi.org/10.23919/acc55779.2023.10156267"},"language":"en","primary_location":{"id":"doi:10.23919/acc55779.2023.10156267","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/acc55779.2023.10156267","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 American Control Conference (ACC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/servlets/purl/2004741","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066160569","display_name":"Christian T. Coletti","orcid":null},"institutions":[{"id":"https://openalex.org/I4210104735","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Christian T. Coletti","raw_affiliation_strings":["Sandia National Laboratories,Albuquerque,New Mexico","Sandia National Laboratories, Albuquerque, New Mexico"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories,Albuquerque,New Mexico","institution_ids":["https://openalex.org/I4210104735"]},{"raw_affiliation_string":"Sandia National Laboratories, Albuquerque, New Mexico","institution_ids":["https://openalex.org/I4210104735"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109041568","display_name":"Kyle A. Williams","orcid":"https://orcid.org/0000-0003-2642-8630"},"institutions":[{"id":"https://openalex.org/I4210104735","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyle A. Williams","raw_affiliation_strings":["Sandia National Laboratories,Albuquerque,New Mexico","Sandia National Laboratories, Albuquerque, New Mexico"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories,Albuquerque,New Mexico","institution_ids":["https://openalex.org/I4210104735"]},{"raw_affiliation_string":"Sandia National Laboratories, Albuquerque, New Mexico","institution_ids":["https://openalex.org/I4210104735"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083995425","display_name":"Hannah Lehman","orcid":null},"institutions":[{"id":"https://openalex.org/I4210104735","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hannah C. Lehman","raw_affiliation_strings":["Sandia National Laboratories,Albuquerque,New Mexico","Sandia National Laboratories, Albuquerque, New Mexico"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories,Albuquerque,New Mexico","institution_ids":["https://openalex.org/I4210104735"]},{"raw_affiliation_string":"Sandia National Laboratories, Albuquerque, New Mexico","institution_ids":["https://openalex.org/I4210104735"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042674480","display_name":"Zahi Kakish","orcid":"https://orcid.org/0000-0002-3506-5651"},"institutions":[{"id":"https://openalex.org/I4210104735","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zahi M. Kakish","raw_affiliation_strings":["Sandia National Laboratories,Albuquerque,New Mexico","Sandia National Laboratories, Albuquerque, New Mexico"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories,Albuquerque,New Mexico","institution_ids":["https://openalex.org/I4210104735"]},{"raw_affiliation_string":"Sandia National Laboratories, Albuquerque, New Mexico","institution_ids":["https://openalex.org/I4210104735"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051229101","display_name":"Daniel L Whitten","orcid":null},"institutions":[{"id":"https://openalex.org/I4210104735","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Whitten","raw_affiliation_strings":["Sandia National Laboratories,Albuquerque,New Mexico","Sandia National Laboratories, Albuquerque, New Mexico"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories,Albuquerque,New Mexico","institution_ids":["https://openalex.org/I4210104735"]},{"raw_affiliation_string":"Sandia National Laboratories, Albuquerque, New Mexico","institution_ids":["https://openalex.org/I4210104735"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015724708","display_name":"Julie Parish","orcid":null},"institutions":[{"id":"https://openalex.org/I4210104735","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julie J. Parish","raw_affiliation_strings":["Sandia National Laboratories,Albuquerque,New Mexico","Sandia National Laboratories, Albuquerque, New Mexico"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories,Albuquerque,New Mexico","institution_ids":["https://openalex.org/I4210104735"]},{"raw_affiliation_string":"Sandia National Laboratories, Albuquerque, New Mexico","institution_ids":["https://openalex.org/I4210104735"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5066160569"],"corresponding_institution_ids":["https://openalex.org/I4210104735"],"apc_list":null,"apc_paid":null,"fwci":0.3389,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.64298989,"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":"3288","last_page":"3295"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9969000220298767,"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":0.9969000220298767,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12158","display_name":"Guidance and Control Systems","score":0.9891999959945679,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7743478417396545},{"id":"https://openalex.org/keywords/agile-software-development","display_name":"Agile software development","score":0.7368674278259277},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6332616806030273},{"id":"https://openalex.org/keywords/staring","display_name":"Staring","score":0.5792986154556274},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.45256099104881287},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.43951523303985596},{"id":"https://openalex.org/keywords/fixed-wing","display_name":"Fixed wing","score":0.43906962871551514},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3582739233970642},{"id":"https://openalex.org/keywords/wing","display_name":"Wing","score":0.35294389724731445},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34336668252944946},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.3231295645236969},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.23073247075080872},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.20160087943077087},{"id":"https://openalex.org/keywords/aerospace-engineering","display_name":"Aerospace engineering","score":0.16815105080604553},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.06859338283538818}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7743478417396545},{"id":"https://openalex.org/C14185376","wikidata":"https://www.wikidata.org/wiki/Q30232","display_name":"Agile software development","level":2,"score":0.7368674278259277},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6332616806030273},{"id":"https://openalex.org/C2778949103","wikidata":"https://www.wikidata.org/wiki/Q600717","display_name":"Staring","level":2,"score":0.5792986154556274},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.45256099104881287},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.43951523303985596},{"id":"https://openalex.org/C3018522811","wikidata":"https://www.wikidata.org/wiki/Q2875704","display_name":"Fixed wing","level":3,"score":0.43906962871551514},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3582739233970642},{"id":"https://openalex.org/C97257150","wikidata":"https://www.wikidata.org/wiki/Q161358","display_name":"Wing","level":2,"score":0.35294389724731445},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34336668252944946},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.3231295645236969},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.23073247075080872},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.20160087943077087},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.16815105080604553},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06859338283538818},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","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},{"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/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.23919/acc55779.2023.10156267","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/acc55779.2023.10156267","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 American Control Conference (ACC)","raw_type":"proceedings-article"},{"id":"pmh:oai:osti.gov:2004741","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/2004741","pdf_url":"https://www.osti.gov/servlets/purl/2004741","source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},{"id":"pmh:oai:osti.gov:2431919","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/2431919","pdf_url":"https://www.osti.gov/servlets/purl/2431919","source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:osti.gov:2004741","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/2004741","pdf_url":"https://www.osti.gov/servlets/purl/2004741","source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2209453243","display_name":null,"funder_award_id":"DE-NA0003525","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G2214935549","display_name":null,"funder_award_id":"NA0003525","funder_id":"https://openalex.org/F4320338291","funder_display_name":"Sandia National Laboratories"},{"id":"https://openalex.org/G4903105778","display_name":null,"funder_award_id":"NA0003525","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G4947178736","display_name":null,"funder_award_id":"-NA0003525","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G5211897158","display_name":null,"funder_award_id":"DE-NA0003525","funder_id":"https://openalex.org/F4320332369","funder_display_name":"National Nuclear Security Administration"},{"id":"https://openalex.org/G5339743583","display_name":null,"funder_award_id":"NA0003525","funder_id":"https://openalex.org/F4320332369","funder_display_name":"National Nuclear Security Administration"},{"id":"https://openalex.org/G8279418378","display_name":null,"funder_award_id":"DE-NA0003525","funder_id":"https://openalex.org/F4320338291","funder_display_name":"Sandia National Laboratories"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320332369","display_name":"National Nuclear Security Administration","ror":"https://ror.org/03sk1we31"},{"id":"https://openalex.org/F4320338291","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4382936099.pdf","grobid_xml":"https://content.openalex.org/works/W4382936099.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W1534966272","https://openalex.org/W2076337359","https://openalex.org/W2109749791","https://openalex.org/W2114901627","https://openalex.org/W2166377112","https://openalex.org/W2345097924","https://openalex.org/W2419597278","https://openalex.org/W2597087754","https://openalex.org/W2736601468","https://openalex.org/W2763517189","https://openalex.org/W2804930149","https://openalex.org/W2907275873","https://openalex.org/W2909445258","https://openalex.org/W2916657295","https://openalex.org/W2962890638","https://openalex.org/W2968312042","https://openalex.org/W2997165841","https://openalex.org/W3048000637","https://openalex.org/W3094027362","https://openalex.org/W3101941357","https://openalex.org/W3110904951","https://openalex.org/W3113349091","https://openalex.org/W3119654194","https://openalex.org/W3120906841","https://openalex.org/W3156330606","https://openalex.org/W3173672478","https://openalex.org/W3185856055","https://openalex.org/W3190154035","https://openalex.org/W3216090517","https://openalex.org/W4205673521","https://openalex.org/W6681799783","https://openalex.org/W6717177883","https://openalex.org/W6741002519","https://openalex.org/W6752165109","https://openalex.org/W6770456446","https://openalex.org/W6781692108","https://openalex.org/W6787019836","https://openalex.org/W6796361866"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W1538637279"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,65],"(RL)":[2],"may":[3],"enable":[4],"fixedwing":[5],"unmanned":[6],"aerial":[7],"vehicle":[8],"(UAV)":[9],"guidance":[10,38],"to":[11,26,53,90],"achieve":[12,27,54],"more":[13],"agile":[14],"and":[15],"complex":[16],"objectives":[17],"than":[18],"typical":[19],"methods.":[20],"However,":[21],"RL":[22,92],"has":[23,39],"yet":[24],"struggled":[25],"even":[28],"minimal":[29],"success":[30,102,117],"on":[31,94],"this":[32,59,95],"problem;":[33],"fixed-wing":[34],"flight":[35],"with":[36,45,63,121],"RL-based":[37,57],"only":[40],"been":[41],"demonstrated":[42],"in":[43,104],"literature":[44],"reduced":[46],"state":[47],"and/or":[48],"action":[49],"spaces.":[50],"In":[51],"order":[52],"full":[55],"6-DOF":[56],"guidance,":[58,68],"study":[60],"begins":[61],"training":[62,77],"imitation":[64],"from":[66],"classical":[67],"a":[69,100],"method":[70],"known":[71],"as":[72],"warm-staring":[73],"(WS),":[74],"before":[75],"further":[76],"using":[78],"Proximal":[79],"Policy":[80],"Optimization":[81],"(PPO).":[82],"We":[83],"show":[84],"that":[85],"warm":[86],"starting":[87],"is":[88],"critical":[89],"successful":[91],"performance":[93],"problem.":[96],"PPO":[97,114],"alone":[98,108],"achieved":[99,109,115],"2%":[101],"rate":[103],"our":[105],"experiments.":[106],"Warm-starting":[107,112],"32%":[110],"success.":[111,127],"plus":[113],"57%":[116],"over":[118],"all":[119],"policies,":[120],"40%":[122],"of":[123],"policies":[124],"achieving":[125],"94%":[126]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-05-04T08:30:34.212998","created_date":"2025-10-10T00:00:00"}
