{"id":"https://openalex.org/W4417251846","doi":"https://doi.org/10.1109/tsp.2025.3642042","title":"Track-MDP: Reinforcement Learning for Target Tracking With Controlled Sensing","display_name":"Track-MDP: Reinforcement Learning for Target Tracking With Controlled Sensing","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4417251846","doi":"https://doi.org/10.1109/tsp.2025.3642042"},"language":null,"primary_location":{"id":"doi:10.1109/tsp.2025.3642042","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tsp.2025.3642042","pdf_url":null,"source":{"id":"https://openalex.org/S168680287","display_name":"IEEE Transactions on Signal Processing","issn_l":"1053-587X","issn":["1053-587X","1941-0476"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Signal Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/tsp.2025.3642042","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091204230","display_name":"Adarsh M. Subramaniam","orcid":"https://orcid.org/0009-0007-5690-3662"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Adarsh M. Subramaniam","raw_affiliation_strings":["Electrical & Computer Engineering Department and the Coordinated Science Laboratory, University of Illinois at Urbana-Champaign, Urbana, IL, USA","ECE Department and the Coordinated Science Lab, University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"Electrical & Computer Engineering Department and the Coordinated Science Laboratory, University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"ECE Department and the Coordinated Science Lab, University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120776409","display_name":"Argyrios Gerogiannisi","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Argyrios Gerogiannis","raw_affiliation_strings":["Electrical & Computer Engineering Department and the Coordinated Science Laboratory, University of Illinois at Urbana-Champaign, Urbana, IL, USA","ECE Department and the Coordinated Science Lab, University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"Electrical & Computer Engineering Department and the Coordinated Science Laboratory, University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"ECE Department and the Coordinated Science Lab, University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009542299","display_name":"James Z. Hare","orcid":"https://orcid.org/0000-0002-3920-7442"},"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"]},{"id":"https://openalex.org/I2802705668","display_name":"United States Army Combat Capabilities Development Command","ror":"https://ror.org/02rdkx920","country_code":"US","type":"other","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Z. Hare","raw_affiliation_strings":["DEVCOM Army Research Laboratory, Adelphi, MD, USA"],"affiliations":[{"raw_affiliation_string":"DEVCOM Army Research Laboratory, Adelphi, MD, USA","institution_ids":["https://openalex.org/I166416128","https://openalex.org/I2802705668"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067089715","display_name":"Venugopal V. Veeravalli","orcid":"https://orcid.org/0000-0001-5490-0037"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Venugopal V. Veeravalli","raw_affiliation_strings":["Electrical & Computer Engineering Department and the Coordinated Science Laboratory, University of Illinois at Urbana-Champaign, Urbana, IL, USA","ECE Department and the Coordinated Science Lab, University of Illinois at Urbana-Champaign, Urbana, IL, USA"],"affiliations":[{"raw_affiliation_string":"Electrical & Computer Engineering Department and the Coordinated Science Laboratory, University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"ECE Department and the Coordinated Science Lab, University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5091204230"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20778171,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"73","issue":null,"first_page":"5348","last_page":"5361"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.2921000123023987,"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":0.2921000123023987,"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/T10711","display_name":"Target Tracking and Data Fusion in Sensor Networks","score":0.25619998574256897,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.18389999866485596,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.95169997215271},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.744700014591217},{"id":"https://openalex.org/keywords/observability","display_name":"Observability","score":0.7347999811172485},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7226999998092651},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5824000239372253},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.5666999816894531},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.5591999888420105},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5465999841690063},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.4799000024795532}],"concepts":[{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.95169997215271},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.744700014591217},{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.7347999811172485},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7226999998092651},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5981000065803528},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5824000239372253},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.5666999816894531},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.5591999888420105},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5465999841690063},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.4799000024795532},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4560999870300293},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.45579999685287476},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.4309999942779541},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.41290000081062317},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39100000262260437},{"id":"https://openalex.org/C173028925","wikidata":"https://www.wikidata.org/wiki/Q7831461","display_name":"Track-before-detect","level":4,"score":0.359499990940094},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.35040000081062317},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3368000090122223},{"id":"https://openalex.org/C32283439","wikidata":"https://www.wikidata.org/wiki/Q1407014","display_name":"Radar tracker","level":3,"score":0.3321000039577484},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.328900009393692},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.32670000195503235},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32249999046325684},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3160000145435333},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.2775999903678894},{"id":"https://openalex.org/C157286648","wikidata":"https://www.wikidata.org/wiki/Q846780","display_name":"Kalman filter","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C39425265","wikidata":"https://www.wikidata.org/wiki/Q7098944","display_name":"Optimal estimation","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2653000056743622},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C115988155","wikidata":"https://www.wikidata.org/wiki/Q3262192","display_name":"Decision problem","level":2,"score":0.2572000026702881}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tsp.2025.3642042","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tsp.2025.3642042","pdf_url":null,"source":{"id":"https://openalex.org/S168680287","display_name":"IEEE Transactions on Signal Processing","issn_l":"1053-587X","issn":["1053-587X","1941-0476"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Signal Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/tsp.2025.3642042","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tsp.2025.3642042","pdf_url":null,"source":{"id":"https://openalex.org/S168680287","display_name":"IEEE Transactions on Signal Processing","issn_l":"1053-587X","issn":["1053-587X","1941-0476"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Signal Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4759515801","display_name":null,"funder_award_id":"W911NF-17-2-0196","funder_id":"https://openalex.org/F4320338456","funder_display_name":"DEVCOM Army Research Laboratory"}],"funders":[{"id":"https://openalex.org/F4320338456","display_name":"DEVCOM Army Research Laboratory","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1531532259","https://openalex.org/W1539216098","https://openalex.org/W1988302514","https://openalex.org/W2024661490","https://openalex.org/W2032100464","https://openalex.org/W2044136843","https://openalex.org/W2044375425","https://openalex.org/W2048605796","https://openalex.org/W2059485247","https://openalex.org/W2065070128","https://openalex.org/W2123487311","https://openalex.org/W2133486451","https://openalex.org/W2144913588","https://openalex.org/W2156256141","https://openalex.org/W2903962827","https://openalex.org/W2963411167","https://openalex.org/W2964209313","https://openalex.org/W2981365946","https://openalex.org/W3196743627","https://openalex.org/W4388240385","https://openalex.org/W4408352662"],"related_works":[],"abstract_inverted_index":{"State":[0],"of":[1,85,88,187,197],"the":[2,38,43,46,50,58,64,71,75,86,89,113,127,130,144,148,173,182,188,193,198,219],"art":[3],"methods":[4],"for":[5,42,49,112,147],"target":[6,65,90,162,220],"tracking":[7,114,185],"with":[8,116,164,172,221],"sensor":[9,96],"management":[10],"(or":[11],"controlled":[12,117],"sensing)":[13],"are":[14,17,67,78],"model-based":[15],"and":[16,74,80,177,224],"obtained":[18],"through":[19,154],"solutions":[20],"to":[21,37,52,57,126,135,158,213],"Partially":[22],"Observable":[23],"Markov":[24,102],"Decision":[25,103],"Process":[26,104],"(POMDP)":[27],"formulations.":[28],"In":[29,124,202],"this":[30],"paper":[31],"a":[32,100,214],"Reinforcement":[33],"Learning":[34],"(RL)":[35],"approach":[36],"problem":[39,115],"is":[40,55,61,82,110,120,133,141,152,156,169,179,192,205],"explored":[41],"setting":[44],"where":[45],"motion":[47],"model":[48],"object/target":[51],"be":[53],"tracked":[54],"unknown":[56],"observer.":[59],"It":[60,140],"assumed":[62],"that":[63,143,181,196,207,216],"dynamics":[66],"stationary":[68],"in":[69],"time,":[70],"state":[72],"space":[73,77],"observation":[76],"discrete,":[79],"there":[81],"complete":[83],"observability":[84],"location":[87],"under":[91],"certain":[92],"(a":[93],"priori":[94],"unknown)":[95],"control":[97],"actions.":[98],"Then,":[99],"novel":[101],"(MDP)":[105],"rather":[106],"than":[107],"POMDP":[108,128,175,200],"formulation":[109,132],"proposed":[111],"sensing,":[118],"which":[119,151],"termed":[121],"as":[122,195],"Track-MDP.":[123],"contrast":[125],"formulation,":[129,150],"Track-MDP":[131,149,167,190,208],"amenable":[134],"an":[136],"RL":[137,210],"based":[138,209],"solution.":[139],"shown":[142,180],"optimal":[145,174,189,199],"policy":[146,191,215],"approximated":[153],"RL,":[155],"guaranteed":[157],"track":[159,218],"all":[160],"significant":[161],"paths":[163],"certainty.":[165],"The":[166],"method":[168],"then":[170],"compared":[171],"policy,":[176],"it":[178,204],"infinite":[183],"horizon":[184],"reward":[186],"same":[194],"policy.":[201],"simulations":[203],"demonstrated":[206],"can":[211,217],"lead":[212],"high":[222],"accuracy":[223],"superior":[225],"energy":[226],"efficiency.":[227]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-12-11T00:00:00"}