{"id":"https://openalex.org/W7164414427","doi":"https://doi.org/10.1109/taes.2026.3702638","title":"Pursuit Strategy Design for Orbital Pursuit\u2013Evasion\u2013Defense Games via Costate Guided Reinforcement Learning","display_name":"Pursuit Strategy Design for Orbital Pursuit\u2013Evasion\u2013Defense Games via Costate Guided Reinforcement Learning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7164414427","doi":"https://doi.org/10.1109/taes.2026.3702638"},"language":null,"primary_location":{"id":"doi:10.1109/taes.2026.3702638","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taes.2026.3702638","pdf_url":null,"source":{"id":"https://openalex.org/S193624734","display_name":"IEEE Transactions on Aerospace and Electronic Systems","issn_l":"0018-9251","issn":["0018-9251","1557-9603","2371-9877"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Aerospace and Electronic Systems","raw_type":"journal-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/A5081518093","display_name":"Pengxuan Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengxuan Liu","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-1890-6746","affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138453812","display_name":"Bin Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Yang","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-6171-9436","affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010636608","display_name":"Xixiang Liu","orcid":"https://orcid.org/0000-0001-6847-1405"},"institutions":[{"id":"https://openalex.org/I4210088225","display_name":"China National Space Administration","ror":"https://ror.org/004vanv95","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210088225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoxiang Liu","raw_affiliation_strings":["National Key Laboratory of Space Intelligent Control, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Space Intelligent Control, Beijing, China","institution_ids":["https://openalex.org/I4210088225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5138437135","display_name":"Shuang Li","orcid":null},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuang Li","raw_affiliation_strings":["Nanjing University of Aeronautics and Astronautics, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-9142-5036","affiliations":[{"raw_affiliation_string":"Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87524128,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"62","issue":null,"first_page":"12182","last_page":"12195"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12158","display_name":"Guidance and Control Systems","score":0.8676999807357788,"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"}},"topics":[{"id":"https://openalex.org/T12158","display_name":"Guidance and Control Systems","score":0.8676999807357788,"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"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.040699999779462814,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.03739999979734421,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.5397999882698059},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4025000035762787},{"id":"https://openalex.org/keywords/design-strategy","display_name":"Design strategy","score":0.39239999651908875},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.32179999351501465},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.30730000138282776},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.3059000074863434}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6236000061035156},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5397999882698059},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4025000035762787},{"id":"https://openalex.org/C124216869","wikidata":"https://www.wikidata.org/wiki/Q7621833","display_name":"Design strategy","level":2,"score":0.39239999651908875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3231000006198883},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.32179999351501465},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.31690001487731934},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.30730000138282776},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.2791999876499176},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.2572999894618988},{"id":"https://openalex.org/C88959737","wikidata":"https://www.wikidata.org/wiki/Q1546627","display_name":"Strategy","level":3,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taes.2026.3702638","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taes.2026.3702638","pdf_url":null,"source":{"id":"https://openalex.org/S193624734","display_name":"IEEE Transactions on Aerospace and Electronic Systems","issn_l":"0018-9251","issn":["0018-9251","1557-9603","2371-9877"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Aerospace and Electronic Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,119],"orbital":[1],"pursuit-evasion-defense":[2],"(PED)":[3],"game":[4,29,46,54,190],"is":[5,30,40,70,82,117,153],"a":[6,33,43,52,63,87,113],"highly":[7],"challenging":[8],"engineering":[9],"problem,":[10],"as":[11,42,51],"the":[12,27,37,48,57,68,73,93,102,106,134,163,167,179],"pursuer":[13,69,94,168],"must":[14],"intercept":[15],"an":[16,142],"evader":[17],"while":[18],"simultaneously":[19],"avoiding":[20],"active":[21],"defense.":[22],"To":[23,104],"address":[24],"this":[25,61],"challenge,":[26],"PED":[28],"decomposed":[31],"into":[32],"bi-level":[34],"structure,":[35],"where":[36],"pursuit-evasion":[38],"interaction":[39,50],"modeled":[41],"Nash":[44],"equilibrium":[45],"and":[47,150,181],"defense-pursuit":[49],"Stackelberg":[53],"led":[55],"by":[56,110],"pursuer.":[58],"Based":[59],"on":[60],"formulation,":[62],"sufficient":[64],"feasibility":[65],"criterion":[66],"for":[67],"derived":[71,123],"under":[72,174],"free-time":[74],"optimal":[75,136],"control":[76,89],"framework.":[77],"Proximal":[78],"Policy":[79],"Optimization":[80],"(PPO)":[81],"then":[83],"employed":[84],"to":[85,126,155,169,178,186],"learn":[86],"feedback":[88],"policy":[90],"that":[91,130,162],"drives":[92],"from":[95],"arbitrary":[96],"initial":[97],"states":[98],"toward":[99],"configurations":[100],"satisfying":[101],"criterion.":[103],"overcome":[105],"slow":[107],"convergence":[108],"caused":[109],"sparse":[111],"rewards,":[112],"costate":[114,122],"alignment":[115],"mechanism":[116,120],"proposed.":[118],"exploits":[121],"structural":[124],"information":[125],"construct":[127],"dense":[128],"rewards":[129],"encourage":[131],"consistency":[132],"between":[133],"pursuer's":[135],"controls":[137],"in":[138],"both":[139],"subgames.":[140],"Moreover,":[141],"accelerated":[143],"reward":[144],"evaluation":[145],"scheme":[146],"combining":[147],"fixed-time":[148],"approximation":[149],"warm-start":[151],"strategies":[152],"developed":[154],"improve":[156],"training":[157],"efficiency.":[158],"Numerical":[159],"simulations":[160],"demonstrate":[161],"proposed":[164],"method":[165],"enables":[166],"successfully":[170],"complete":[171],"pursuit":[172],"tasks":[173],"maneuvering":[175],"capabilities":[176],"comparable":[177],"defender's,":[180],"exhibits":[182],"superior":[183],"performance":[184],"compared":[185],"conventional":[187],"fixed-weight":[188],"differential":[189],"methods.":[191]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-12T00:00:00"}