{"id":"https://openalex.org/W4379510793","doi":"https://doi.org/10.2514/1.i011146","title":"Multirobot Navigation Using Partially Observable Markov Decision Processes with Belief-Based Rewards","display_name":"Multirobot Navigation Using Partially Observable Markov Decision Processes with Belief-Based Rewards","publication_year":2023,"publication_date":"2023-06-07","ids":{"openalex":"https://openalex.org/W4379510793","doi":"https://doi.org/10.2514/1.i011146"},"language":"en","primary_location":{"id":"doi:10.2514/1.i011146","is_oa":false,"landing_page_url":"https://doi.org/10.2514/1.i011146","pdf_url":null,"source":{"id":"https://openalex.org/S4210240151","display_name":"Journal of Aerospace Information Systems","issn_l":"2327-3097","issn":["2327-3097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315709","host_organization_name":"American Institute of Aeronautics and Astronautics","host_organization_lineage":["https://openalex.org/P4310315709"],"host_organization_lineage_names":["American Institute of Aeronautics and Astronautics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Aerospace Information 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/A5056631676","display_name":"Alexandros E. Tzikas","orcid":"https://orcid.org/0000-0002-3003-4880"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexandros E. Tzikas","raw_affiliation_strings":["Stanford University, Stanford, California 94305"],"raw_orcid":"https://orcid.org/0000-0002-3003-4880","affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, California 94305","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088274433","display_name":"Derek Knowles","orcid":"https://orcid.org/0000-0001-7362-2327"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Derek Knowles","raw_affiliation_strings":["Stanford University, Stanford, California 94305"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, California 94305","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069625302","display_name":"Grace Gao","orcid":"https://orcid.org/0000-0002-1807-8637"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Grace X. Gao","raw_affiliation_strings":["Stanford University, Stanford, California 94305"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, California 94305","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068326377","display_name":"Mykel J. Kochenderfer","orcid":"https://orcid.org/0000-0002-7238-9663"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mykel J. Kochenderfer","raw_affiliation_strings":["Stanford University, Stanford, California 94305"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, California 94305","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":0.2222,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.48888252,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"20","issue":"8","first_page":"437","last_page":"446"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9984999895095825,"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":0.9984999895095825,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9921000003814697,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.9883000254631042,"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/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.9047937393188477},{"id":"https://openalex.org/keywords/extended-kalman-filter","display_name":"Extended Kalman filter","score":0.7376528978347778},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6065184473991394},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.5458744168281555},{"id":"https://openalex.org/keywords/monte-carlo-tree-search","display_name":"Monte Carlo tree search","score":0.5390950441360474},{"id":"https://openalex.org/keywords/particle-filter","display_name":"Particle filter","score":0.5240257382392883},{"id":"https://openalex.org/keywords/kalman-filter","display_name":"Kalman filter","score":0.5065261125564575},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.46945828199386597},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46219971776008606},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4563475549221039},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4338999390602112},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.43175172805786133},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.35977548360824585},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.35442543029785156},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.2420635223388672},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23872798681259155},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.23550152778625488},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.22400733828544617}],"concepts":[{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.9047937393188477},{"id":"https://openalex.org/C206833254","wikidata":"https://www.wikidata.org/wiki/Q5421817","display_name":"Extended Kalman filter","level":3,"score":0.7376528978347778},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6065184473991394},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.5458744168281555},{"id":"https://openalex.org/C46149586","wikidata":"https://www.wikidata.org/wiki/Q11785332","display_name":"Monte Carlo tree search","level":3,"score":0.5390950441360474},{"id":"https://openalex.org/C52421305","wikidata":"https://www.wikidata.org/wiki/Q1151499","display_name":"Particle filter","level":3,"score":0.5240257382392883},{"id":"https://openalex.org/C157286648","wikidata":"https://www.wikidata.org/wiki/Q846780","display_name":"Kalman filter","level":2,"score":0.5065261125564575},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.46945828199386597},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46219971776008606},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4563475549221039},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4338999390602112},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.43175172805786133},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.35977548360824585},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.35442543029785156},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.2420635223388672},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23872798681259155},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.23550152778625488},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.22400733828544617},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.2514/1.i011146","is_oa":false,"landing_page_url":"https://doi.org/10.2514/1.i011146","pdf_url":null,"source":{"id":"https://openalex.org/S4210240151","display_name":"Journal of Aerospace Information Systems","issn_l":"2327-3097","issn":["2327-3097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315709","host_organization_name":"American Institute of Aeronautics and Astronautics","host_organization_lineage":["https://openalex.org/P4310315709"],"host_organization_lineage_names":["American Institute of Aeronautics and Astronautics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Aerospace Information Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1984338812","https://openalex.org/W2102621601","https://openalex.org/W2140929789","https://openalex.org/W2952258289","https://openalex.org/W2954742730","https://openalex.org/W3035436453","https://openalex.org/W3098184036","https://openalex.org/W3112005744","https://openalex.org/W4200537477","https://openalex.org/W4210519316"],"related_works":["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","https://openalex.org/W3169161914","https://openalex.org/W1585960250"],"abstract_inverted_index":{"For":[0],"the":[1,20,35,75,80,83,88,92,98,101,104,109,113,119,130,138,146,159,174,180],"safe":[2],"deployment":[3],"of":[4,23,100,108,201],"multirobot":[5,15,58,156],"systems,":[6],"accurate":[7],"position":[8,31,51,168,203],"estimation":[9],"is":[10,72],"necessary.":[11],"We":[12,33,142,176],"present":[13,143],"a":[14,38,54,61,155,184,196],"navigation":[16,148],"algorithm":[17,125,149],"that":[18,150,166,179],"accomplishes":[19],"dual":[21],"objective":[22],"reaching":[24],"designated":[25],"goal":[26],"positions":[27],"and":[28,94,140,195],"maintaining":[29],"low":[30],"uncertainty.":[32,204],"pose":[34],"problem":[36],"as":[37,74,77,79,91,136],"[Formula:":[39,84,114],"see":[40,47,85,115],"text]-partially":[41],"observable":[42,188],"Markov":[43],"decision":[44],"process":[45],"([Formula:":[46],"text]POMDP)":[48],"to":[49,126,162],"capture":[50],"uncertainty":[52,169],"through":[53],"belief-based":[55],"reward.":[56],"The":[57],"system":[59],"employs":[60],"centralized":[62],"extended":[63],"Kalman":[64],"filter":[65,123],"(EKF)":[66],"for":[67,97,145,154,170],"state":[68],"estimation,":[69],"whose":[70],"output":[71,90,133],"used":[73,135],"observation":[76,93,139,193],"well":[78],"belief":[81,95],"in":[82,103,173,199],"text]POMDP.":[86],"Using":[87],"EKF":[89,102,131],"allows":[96],"integration":[99],"action":[105],"planning":[106,191],"module":[107],"system.":[110,175],"To":[111],"solve":[112],"text]POMDP,":[116],"we":[117],"adapt":[118],"online":[120],"information":[121],"particle":[122],"tree":[124],"be":[127],"compatible":[128],"with":[129,192],"closed-form":[132],"being":[134],"both":[137],"belief.":[141],"results":[144],"proposed":[147,181],"show":[151],"emergent":[152],"behaviors":[153],"system,":[157],"where":[158],"robots":[160,172],"move":[161],"provide":[163],"inter-ranging":[164],"measurements":[165],"minimize":[167],"all":[171],"also":[177],"demonstrate":[178],"method":[182],"outperforms":[183],"state-of-the-art":[185],"solver":[186],"(partially":[187],"Monte":[189],"Carlo":[190],"widening)":[194],"direct-to-goal":[197],"planner":[198],"terms":[200],"minimizing":[202]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}