{"id":"https://openalex.org/W1886379263","doi":"https://doi.org/10.1109/icra.2015.7140035","title":"Decentralized control of Partially Observable Markov Decision Processes using belief space macro-actions","display_name":"Decentralized control of Partially Observable Markov Decision Processes using belief space macro-actions","publication_year":2015,"publication_date":"2015-05-01","ids":{"openalex":"https://openalex.org/W1886379263","doi":"https://doi.org/10.1109/icra.2015.7140035","mag":"1886379263"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2015.7140035","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2015.7140035","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Robotics and Automation (ICRA)","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/A5052169592","display_name":"Shayegan Omidshafiei","orcid":"https://orcid.org/0000-0001-7758-1454"},"institutions":[{"id":"https://openalex.org/I4210143601","display_name":"Decision Systems (United States)","ror":"https://ror.org/0434dpa13","country_code":"US","type":"company","lineage":["https://openalex.org/I4210143601"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shayegan Omidshafiei","raw_affiliation_strings":["Laboratory for Information and Decision Systems (LIDS), MIT, Cambridge, MA","Laboratory for Information and Decision Systems (LIDS), MIT, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Laboratory for Information and Decision Systems (LIDS), MIT, Cambridge, MA","institution_ids":["https://openalex.org/I4210143601"]},{"raw_affiliation_string":"Laboratory for Information and Decision Systems (LIDS), MIT, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210143601"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042186658","display_name":"Ali\u2010akbar Agha\u2010mohammadi","orcid":"https://orcid.org/0000-0001-5509-1841"},"institutions":[{"id":"https://openalex.org/I4210143601","display_name":"Decision Systems (United States)","ror":"https://ror.org/0434dpa13","country_code":"US","type":"company","lineage":["https://openalex.org/I4210143601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ali-akbar Agha-mohammadi","raw_affiliation_strings":["Laboratory for Information and Decision Systems (LIDS), MIT, Cambridge, MA","Laboratory for Information and Decision Systems (LIDS), MIT, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Laboratory for Information and Decision Systems (LIDS), MIT, Cambridge, MA","institution_ids":["https://openalex.org/I4210143601"]},{"raw_affiliation_string":"Laboratory for Information and Decision Systems (LIDS), MIT, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210143601"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033129735","display_name":"Christopher Amato","orcid":"https://orcid.org/0000-0002-6786-7384"},"institutions":[{"id":"https://openalex.org/I161057412","display_name":"University of New Hampshire","ror":"https://ror.org/01rmh9n78","country_code":"US","type":"education","lineage":["https://openalex.org/I161057412"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher Amato","raw_affiliation_strings":["Dept. of Computer Science at the University of New Hampshire, Durham, NH","Dept. of Computer Science at the University of New Hampshire, Durham, USA"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science at the University of New Hampshire, Durham, NH","institution_ids":["https://openalex.org/I161057412"]},{"raw_affiliation_string":"Dept. of Computer Science at the University of New Hampshire, Durham, USA","institution_ids":["https://openalex.org/I161057412"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011665886","display_name":"Jonathan P. How","orcid":"https://orcid.org/0000-0001-8576-1930"},"institutions":[{"id":"https://openalex.org/I4210143601","display_name":"Decision Systems (United States)","ror":"https://ror.org/0434dpa13","country_code":"US","type":"company","lineage":["https://openalex.org/I4210143601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan P. How","raw_affiliation_strings":["Laboratory for Information and Decision Systems (LIDS), MIT, Cambridge, MA","Laboratory for Information and Decision Systems (LIDS), MIT, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Laboratory for Information and Decision Systems (LIDS), MIT, Cambridge, MA","institution_ids":["https://openalex.org/I4210143601"]},{"raw_affiliation_string":"Laboratory for Information and Decision Systems (LIDS), MIT, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210143601"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5052169592"],"corresponding_institution_ids":["https://openalex.org/I4210143601"],"apc_list":null,"apc_paid":null,"fwci":12.5119,"has_fulltext":false,"cited_by_count":62,"citation_normalized_percentile":{"value":0.98584591,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5962","last_page":"5969"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9976000189781189,"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":0.9976000189781189,"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/T10142","display_name":"Formal Methods in Verification","score":0.9954000115394592,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9948999881744385,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/observability","display_name":"Observability","score":0.797306478023529},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.7561328411102295},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7194812297821045},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6954135894775391},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5840343832969666},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5696275234222412},{"id":"https://openalex.org/keywords/macro","display_name":"Macro","score":0.5633291602134705},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.5448309779167175},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5291113257408142},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4844062924385071},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.44887518882751465},{"id":"https://openalex.org/keywords/decision-problem","display_name":"Decision problem","score":0.42516419291496277},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36010199785232544},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.3539385497570038},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.228843092918396},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.20657044649124146},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18943306803703308},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14085671305656433}],"concepts":[{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.797306478023529},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.7561328411102295},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7194812297821045},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6954135894775391},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5840343832969666},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5696275234222412},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.5633291602134705},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.5448309779167175},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5291113257408142},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4844062924385071},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.44887518882751465},{"id":"https://openalex.org/C115988155","wikidata":"https://www.wikidata.org/wiki/Q3262192","display_name":"Decision problem","level":2,"score":0.42516419291496277},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36010199785232544},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.3539385497570038},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.228843092918396},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.20657044649124146},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18943306803703308},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14085671305656433},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra.2015.7140035","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2015.7140035","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5799999833106995,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W12258761","https://openalex.org/W29703438","https://openalex.org/W1535136082","https://openalex.org/W1563965851","https://openalex.org/W1977655452","https://openalex.org/W1988975763","https://openalex.org/W2023292158","https://openalex.org/W2082430444","https://openalex.org/W2087992130","https://openalex.org/W2088956500","https://openalex.org/W2109910161","https://openalex.org/W2141157184","https://openalex.org/W2156676156","https://openalex.org/W2162428884","https://openalex.org/W2164851390","https://openalex.org/W2168992242","https://openalex.org/W2290743114","https://openalex.org/W2294192315","https://openalex.org/W2325038505","https://openalex.org/W6600526285","https://openalex.org/W6601181163","https://openalex.org/W6633696232","https://openalex.org/W6683336107"],"related_works":["https://openalex.org/W11481024","https://openalex.org/W2999848267","https://openalex.org/W2096013579","https://openalex.org/W1589140671","https://openalex.org/W1760611253","https://openalex.org/W52153049","https://openalex.org/W2951545791","https://openalex.org/W1515117609","https://openalex.org/W2294884454","https://openalex.org/W4323315247"],"abstract_inverted_index":{"The":[0,77,128],"focus":[1],"of":[2],"this":[3,62,99],"paper":[4,63],"is":[5,36,49,87,102,132],"on":[6,134],"solving":[7,34,98],"multi-robot":[8,28,52,90,137,150],"planning":[9],"problems":[10,53,151],"in":[11,89,117],"continuous":[12,60],"spaces":[13],"with":[14],"partial":[15],"observability.":[16],"Decentralized":[17,70],"Partially":[18,71],"Observable":[19,72],"Markov":[20],"Decision":[21,74],"Processes":[22],"(Dec-POMDPs)":[23],"are":[24,121],"general":[25],"models":[26],"for":[27,39,44,51,97,156],"coordination":[29],"problems,":[30,61],"but":[31],"representing":[32],"and":[33,54,59,152],"Dec-POMDPs":[35],"often":[37],"intractable":[38],"large":[40,57],"problems.":[41,158],"To":[42],"allow":[43],"a":[45,135],"high-level":[46],"representation":[47],"that":[48,144],"natural":[50],"scalable":[55,105],"to":[56,68,124],"discrete":[58],"extends":[64],"the":[65,69,84],"Dec-POMDP":[66],"model":[67],"Semi-Markov":[73],"Process":[75],"(Dec-POSMDP).":[76],"Dec-POSMDP":[78,100],"formulation":[79],"allows":[80],"asynchronous":[81],"decision-making":[82],"by":[83],"robots,":[85],"which":[86,101],"crucial":[88],"domains.":[91],"We":[92],"also":[93],"present":[94],"an":[95],"algorithm":[96],"much":[103],"more":[104],"than":[106],"previous":[107],"methods":[108],"since":[109],"it":[110],"can":[111,147],"incorporate":[112],"closed-loop":[113],"belief":[114],"space":[115],"macro-actions":[116,120],"planning.":[118],"These":[119],"automatically":[122],"constructed":[123],"produce":[125],"robust":[126],"solutions.":[127],"proposed":[129],"method's":[130],"performance":[131],"evaluated":[133],"complex":[136],"package":[138],"delivery":[139],"problem":[140],"under":[141],"uncertainty,":[142],"showing":[143],"our":[145],"approach":[146],"naturally":[148],"represent":[149],"provide":[153],"high-quality":[154],"solutions":[155],"large-scale":[157]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":13},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}