{"id":"https://openalex.org/W2739936129","doi":"https://doi.org/10.1109/iros.2017.8202242","title":"Simultaneous active parameter estimation and control using sampling-based Bayesian reinforcement learning","display_name":"Simultaneous active parameter estimation and control using sampling-based Bayesian reinforcement learning","publication_year":2017,"publication_date":"2017-09-01","ids":{"openalex":"https://openalex.org/W2739936129","doi":"https://doi.org/10.1109/iros.2017.8202242","mag":"2739936129"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2017.8202242","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2017.8202242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1707.09055","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042939370","display_name":"Patrick Slade","orcid":"https://orcid.org/0000-0001-9302-3911"},"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":"Patrick Slade","raw_affiliation_strings":["Department of Mechanical Engineering, Stanford University, CA, USA","#N#Department of Mechanical Engineering, Stanford University, Stanford, CA 94305,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, Stanford University, CA, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"#N#Department of Mechanical Engineering, Stanford University, Stanford, CA 94305,USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006569343","display_name":"Preston Culbertson","orcid":"https://orcid.org/0000-0002-1403-8697"},"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":"Preston Culbertson","raw_affiliation_strings":["Department of Mechanical Engineering, Stanford University, CA, USA","#N#Department of Mechanical Engineering, Stanford University, Stanford, CA 94305,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, Stanford University, CA, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"#N#Department of Mechanical Engineering, Stanford University, Stanford, CA 94305,USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054686855","display_name":"Zachary N. Sunberg","orcid":"https://orcid.org/0000-0001-9707-3035"},"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":"Zachary Sunberg","raw_affiliation_strings":["Department of Aeronautics and Astronautics, Stanford University","[Department of Aeronautics and Astronautics, Stanford University]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Aeronautics and Astronautics, Stanford University","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"[Department of Aeronautics and Astronautics, Stanford University]","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 Kochenderfer","raw_affiliation_strings":["Department of Aeronautics and Astronautics, Stanford University","[Department of Aeronautics and Astronautics, Stanford University]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Aeronautics and Astronautics, Stanford University","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"[Department of Aeronautics and Astronautics, Stanford University]","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":0.1984,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.50807533,"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":"804","last_page":"810"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9991999864578247,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9980999827384949,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9923999905586243,"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/computer-science","display_name":"Computer science","score":0.6670811772346497},{"id":"https://openalex.org/keywords/kalman-filter","display_name":"Kalman filter","score":0.5530920624732971},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5261749029159546},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4791806936264038},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.46228694915771484},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4588696360588074},{"id":"https://openalex.org/keywords/payload","display_name":"Payload (computing)","score":0.4553520977497101},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.44020649790763855},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4269633889198303},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.41957131028175354},{"id":"https://openalex.org/keywords/estimation-theory","display_name":"Estimation theory","score":0.41870665550231934},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.4112960696220398},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3132927715778351},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.2601777911186218},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.2501016855239868},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17474570870399475},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15658515691757202},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09252557158470154}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6670811772346497},{"id":"https://openalex.org/C157286648","wikidata":"https://www.wikidata.org/wiki/Q846780","display_name":"Kalman filter","level":2,"score":0.5530920624732971},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5261749029159546},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4791806936264038},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.46228694915771484},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4588696360588074},{"id":"https://openalex.org/C134066672","wikidata":"https://www.wikidata.org/wiki/Q1424639","display_name":"Payload (computing)","level":3,"score":0.4553520977497101},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.44020649790763855},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4269633889198303},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.41957131028175354},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.41870665550231934},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.4112960696220398},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3132927715778351},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2601777911186218},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.2501016855239868},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17474570870399475},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15658515691757202},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09252557158470154},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C158379750","wikidata":"https://www.wikidata.org/wiki/Q214111","display_name":"Network packet","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/iros.2017.8202242","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2017.8202242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1707.09055","is_oa":true,"landing_page_url":"https://arxiv.org/abs/1707.09055","pdf_url":"https://arxiv.org/pdf/1707.09055","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2739936129","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1707.09055","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1707.09055","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1707.09055","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1707.09055","is_oa":true,"landing_page_url":"https://arxiv.org/abs/1707.09055","pdf_url":"https://arxiv.org/pdf/1707.09055","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6899999976158142}],"awards":[{"id":"https://openalex.org/G2499887605","display_name":null,"funder_award_id":"DGE-1656518","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G320138474","display_name":null,"funder_award_id":"-1656518","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5267932457","display_name":"Graduate Research Fellowship Program (GRFP)","funder_award_id":"1656518","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320315934","display_name":"Toyota Research Institute","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2739936129.pdf","grobid_xml":"https://content.openalex.org/works/W2739936129.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W107054272","https://openalex.org/W1557122569","https://openalex.org/W1601081659","https://openalex.org/W1864112212","https://openalex.org/W1967769980","https://openalex.org/W2000359213","https://openalex.org/W2001728872","https://openalex.org/W2015913913","https://openalex.org/W2028169578","https://openalex.org/W2073787051","https://openalex.org/W2092950191","https://openalex.org/W2098432798","https://openalex.org/W2101786389","https://openalex.org/W2125016937","https://openalex.org/W2126316555","https://openalex.org/W2149586740","https://openalex.org/W2168359464","https://openalex.org/W2171269539","https://openalex.org/W2268119109","https://openalex.org/W2287992105","https://openalex.org/W2296319761","https://openalex.org/W2336416123","https://openalex.org/W2344384429","https://openalex.org/W2545546008","https://openalex.org/W2565370028","https://openalex.org/W2594201198","https://openalex.org/W2607868186","https://openalex.org/W2953027552","https://openalex.org/W3143169333","https://openalex.org/W3148740559","https://openalex.org/W6605349051","https://openalex.org/W6635108797","https://openalex.org/W6737007698"],"related_works":["https://openalex.org/W2963360571","https://openalex.org/W2886887402","https://openalex.org/W3104672407","https://openalex.org/W3091691968","https://openalex.org/W2484501038","https://openalex.org/W2799977193","https://openalex.org/W3104787446","https://openalex.org/W3155499355","https://openalex.org/W3129658336","https://openalex.org/W2738812390","https://openalex.org/W3186204815","https://openalex.org/W3099723796","https://openalex.org/W3213474687","https://openalex.org/W3133486243","https://openalex.org/W3129243175","https://openalex.org/W3025508484","https://openalex.org/W3006585854","https://openalex.org/W2974605810","https://openalex.org/W2548718026","https://openalex.org/W3120421313"],"abstract_inverted_index":{"Robots":[0],"performing":[1],"manipulation":[2],"tasks":[3],"must":[4,32],"operate":[5],"under":[6],"uncertainty":[7,95,107],"about":[8],"both":[9],"their":[10],"pose":[11],"and":[12,26,36,55,61,74,83,93,108,134],"the":[13,16,40,47,52,66,110],"dynamics":[14],"of":[15],"system.":[17],"In":[18],"order":[19],"to":[20,23,88,104,125],"remain":[21],"robust":[22],"modeling":[24],"error":[25],"shifts":[27],"in":[28,96,128],"payload":[29],"dynamics,":[30],"agents":[31,57],"simultaneously":[33],"perform":[34],"estimation":[35,42],"control":[37,53,102,119],"tasks.":[38],"However,":[39],"optimal":[41,48],"actions":[43,49,103],"are":[44],"often":[45],"not":[46],"for":[50],"accomplishing":[51],"tasks,":[54],"thus":[56],"trade":[58],"between":[59],"exploration":[60],"exploitation.":[62],"This":[63],"work":[64],"frames":[65],"problem":[67],"as":[68,122],"a":[69,97,123],"Bayes-adaptive":[70],"Markov":[71],"decision":[72],"process":[73,91,132],"solves":[75],"it":[76],"online":[77],"using":[78],"Monte":[79],"Carlo":[80],"tree":[81],"search":[82],"an":[84],"extended":[85],"Kalman":[86],"filter":[87],"handle":[89],"Gaussian":[90],"noise":[92,133],"parameter":[94,135],"continuous":[98],"space.":[99],"MCTS":[100],"selects":[101],"reduce":[105],"model":[106,117],"reach":[109],"goal":[111],"state":[112],"nearly":[113],"optimally.":[114],"Certainty":[115],"equivalent":[116],"predictive":[118],"is":[120],"used":[121],"benchmark":[124],"compare":[126],"performance":[127],"simulations":[129],"with":[130],"varying":[131],"uncertainty.":[136]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}