{"id":"https://openalex.org/W2735263551","doi":"https://doi.org/10.23919/acc.2017.7963532","title":"Air-to-ground shepherd problem: An action-delay reinforcement learning approach","display_name":"Air-to-ground shepherd problem: An action-delay reinforcement learning approach","publication_year":2017,"publication_date":"2017-05-01","ids":{"openalex":"https://openalex.org/W2735263551","doi":"https://doi.org/10.23919/acc.2017.7963532","mag":"2735263551"},"language":"en","primary_location":{"id":"doi:10.23919/acc.2017.7963532","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc.2017.7963532","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 American Control Conference (ACC)","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/A5102713772","display_name":"Jiangcheng Zhu","orcid":"https://orcid.org/0000-0002-6610-721X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiangcheng Zhu","raw_affiliation_strings":["State Key Lab of Industrial Control, Zhejiang University, Hangzhou, P.R. China"],"affiliations":[{"raw_affiliation_string":"State Key Lab of Industrial Control, Zhejiang University, Hangzhou, P.R. China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050543156","display_name":"Chao Xu","orcid":"https://orcid.org/0000-0002-2759-6364"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Xu","raw_affiliation_strings":["Faculty of State Key Lab of Industrial Control, Zhejiang University, Hangzhou, P.R. China"],"affiliations":[{"raw_affiliation_string":"Faculty of State Key Lab of Industrial Control, Zhejiang University, Hangzhou, P.R. China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102713772"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.091,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.44834259,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"3771","last_page":"3776"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9998999834060669,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9979000091552734,"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/T12158","display_name":"Guidance and Control Systems","score":0.9968000054359436,"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":0.7597804069519043},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.7210092544555664},{"id":"https://openalex.org/keywords/drone","display_name":"Drone","score":0.6274938583374023},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6138769388198853},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5996904969215393},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5576488971710205},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5543182492256165},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.5307899117469788},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.5131776928901672},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.49775055050849915},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.42526793479919434},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.4128056764602661},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.3376495838165283},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.33088070154190063},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.3224322199821472},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2881665527820587}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7597804069519043},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.7210092544555664},{"id":"https://openalex.org/C59519942","wikidata":"https://www.wikidata.org/wiki/Q650665","display_name":"Drone","level":2,"score":0.6274938583374023},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6138769388198853},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5996904969215393},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5576488971710205},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5543182492256165},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.5307899117469788},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.5131776928901672},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.49775055050849915},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.42526793479919434},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4128056764602661},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.3376495838165283},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.33088070154190063},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3224322199821472},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2881665527820587},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc.2017.7963532","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc.2017.7963532","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7799999713897705,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W91905023","https://openalex.org/W1608706637","https://openalex.org/W1626155273","https://openalex.org/W1635034095","https://openalex.org/W1949804828","https://openalex.org/W2026659355","https://openalex.org/W2091565802","https://openalex.org/W2108734173","https://openalex.org/W2113501460","https://openalex.org/W2132400125","https://openalex.org/W2167697140","https://openalex.org/W2169209873","https://openalex.org/W2767768680","https://openalex.org/W2963921033","https://openalex.org/W4214717370","https://openalex.org/W6676172287","https://openalex.org/W6685331716"],"related_works":["https://openalex.org/W4229448053","https://openalex.org/W4247925126","https://openalex.org/W4327774218","https://openalex.org/W2059768187","https://openalex.org/W4312858960","https://openalex.org/W4386036939","https://openalex.org/W4379143281","https://openalex.org/W2605096541","https://openalex.org/W3200286695","https://openalex.org/W4212885606"],"abstract_inverted_index":{"In":[0,123],"this":[1,111,188],"paper,":[2],"we":[3],"consider":[4],"an":[5,24,41],"optimization":[6],"problem":[7],"motivated":[8],"by":[9],"the":[10,18,28,37,62,70,85,99,132,143,146,178],"International":[11],"Aerial":[12],"Robotics":[13],"Competition":[14],"(IARC)":[15],"Mission-7,":[16],"or":[17,58],"shepherd":[19,29],"action.":[20],"IARC":[21,179],"Mission-7":[22,180],"requires":[23],"autonomous":[25],"drone":[26,71],"(i.e.":[27],"dog)":[30],"to":[31,60,73,93,98,125,139,142],"drive":[32],"ground":[33,65],"vehicle":[34],"(sheep)":[35],"across":[36],"green-line":[38],"boundary":[39],"of":[40,44,64,69,91,103,154],"competition":[42],"arena":[43],"20m":[45,47],"\u00d7":[46],"within":[48],"10":[49],"mins.":[50],"There":[51],"are":[52,160,169,190],"two":[53],"actions,":[54],"either":[55],"top":[56],"touch":[57],"collision":[59],"change":[61],"motion":[63],"vehicle(GV).":[66],"The":[67,151,174],"policy":[68],"is":[72,105,114,137],"choose":[74],"target":[75,144],"and":[76,121,168],"action":[77,83,108,127,156],"type,":[78],"as":[79,107],"decision-making.":[80,122],"Within":[81],"a":[82,115,163],"process,":[84],"aerial":[86],"robot":[87],"takes":[88],"certain":[89],"period":[90,102],"time":[92,104],"fly":[94],"from":[95],"current":[96],"position":[97],"target.":[100],"This":[101],"named":[106],"delay":[109,128],"in":[110,145,162,177,187],"work,":[112],"which":[113],"key":[116],"feature":[117],"for":[118,171],"reward":[119],"generation":[120],"order":[124],"predict":[126],"before":[129],"actual":[130],"implementation,":[131],"path":[133],"integral":[134],"control":[135],"method":[136],"applied":[138],"generate":[140],"trajectories":[141],"environment":[147],"with":[148],"moving":[149],"obstacles.":[150],"pre-trained":[152],"values":[153],"every":[155],"on":[157],"each":[158],"state":[159],"stored":[161],"discrete":[164],"multi-dimensional":[165],"tabular":[166],"system,":[167],"extracted":[170],"decision-making":[172],"module.":[173],"simulation":[175],"results":[176],"scenario":[181],"validate":[182],"that":[183],"our":[184],"methods":[185],"proposed":[186],"paper":[189],"effective.":[191]},"counts_by_year":[{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}