{"id":"https://openalex.org/W3186772940","doi":"https://doi.org/10.1177/02783649231167210","title":"Bayesian controller fusion: Leveraging control priors in deep reinforcement learning for robotics","display_name":"Bayesian controller fusion: Leveraging control priors in deep reinforcement learning for robotics","publication_year":2023,"publication_date":"2023-03-01","ids":{"openalex":"https://openalex.org/W3186772940","doi":"https://doi.org/10.1177/02783649231167210","mag":"3186772940"},"language":"en","primary_location":{"id":"doi:10.1177/02783649231167210","is_oa":true,"landing_page_url":"https://doi.org/10.1177/02783649231167210","pdf_url":null,"source":{"id":"https://openalex.org/S73484101","display_name":"The International Journal of Robotics Research","issn_l":"0278-3649","issn":["0278-3649","1741-3176"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of Robotics Research","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1177/02783649231167210","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001506562","display_name":"Krishan Rana","orcid":"https://orcid.org/0000-0002-9028-9295"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Krishan Rana","raw_affiliation_strings":["Queensland University of Technology (QUT) Centre for Robotics, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"Queensland University of Technology (QUT) Centre for Robotics, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012909623","display_name":"Vibhavari Dasagi","orcid":null},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Vibhavari Dasagi","raw_affiliation_strings":["Queensland University of Technology (QUT) Centre for Robotics, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"Queensland University of Technology (QUT) Centre for Robotics, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054290504","display_name":"Jesse Haviland","orcid":"https://orcid.org/0000-0002-1227-7459"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jesse Haviland","raw_affiliation_strings":["Queensland University of Technology (QUT) Centre for Robotics, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"Queensland University of Technology (QUT) Centre for Robotics, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048415448","display_name":"Ben Talbot","orcid":"https://orcid.org/0000-0002-5670-1928"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ben Talbot","raw_affiliation_strings":["Queensland University of Technology (QUT) Centre for Robotics, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"Queensland University of Technology (QUT) Centre for Robotics, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078340555","display_name":"Michael Milford","orcid":"https://orcid.org/0000-0002-5162-1793"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Michael Milford","raw_affiliation_strings":["Queensland University of Technology (QUT) Centre for Robotics, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"Queensland University of Technology (QUT) Centre for Robotics, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034957065","display_name":"Niko S\u00fcnderhauf","orcid":"https://orcid.org/0000-0001-5286-3789"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Niko S\u00fcnderhauf","raw_affiliation_strings":["Queensland University of Technology (QUT) Centre for Robotics, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"Queensland University of Technology (QUT) Centre for Robotics, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5001506562"],"corresponding_institution_ids":["https://openalex.org/I160993911"],"apc_list":null,"apc_paid":null,"fwci":3.6415,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.93100301,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"42","issue":"3","first_page":"123","last_page":"146"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9976000189781189,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9976000189781189,"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":0.9945999979972839,"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":0.9728999733924866,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.7713401317596436},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7438705563545227},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.7388214468955994},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6210856437683105},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6165210604667664},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6043093204498291},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.6027194261550903},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5769393444061279},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.469451367855072},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.413973331451416},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.2353702187538147},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.193464457988739}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7713401317596436},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7438705563545227},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.7388214468955994},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6210856437683105},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6165210604667664},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6043093204498291},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.6027194261550903},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5769393444061279},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.469451367855072},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.413973331451416},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2353702187538147},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.193464457988739},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1177/02783649231167210","is_oa":true,"landing_page_url":"https://doi.org/10.1177/02783649231167210","pdf_url":null,"source":{"id":"https://openalex.org/S73484101","display_name":"The International Journal of Robotics Research","issn_l":"0278-3649","issn":["0278-3649","1741-3176"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of Robotics Research","raw_type":"journal-article"},{"id":"pmh:oai:eprints.qut.edu.au:239326","is_oa":false,"landing_page_url":"http://purl.org/au-research/grants/arc/DP220102398","pdf_url":null,"source":{"id":"https://openalex.org/S4306402607","display_name":"QUT ePrints (Queensland University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I160993911","host_organization_name":"Queensland University of Technology","host_organization_lineage":["https://openalex.org/I160993911"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Journal of Robotics Research","raw_type":"Contribution to Journal"}],"best_oa_location":{"id":"doi:10.1177/02783649231167210","is_oa":true,"landing_page_url":"https://doi.org/10.1177/02783649231167210","pdf_url":null,"source":{"id":"https://openalex.org/S73484101","display_name":"The International Journal of Robotics Research","issn_l":"0278-3649","issn":["0278-3649","1741-3176"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of Robotics Research","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.4000000059604645}],"awards":[{"id":"https://openalex.org/G4327185696","display_name":null,"funder_award_id":"CE140100016","funder_id":"https://openalex.org/F4320331724","funder_display_name":"Australian Centre for Robotic Vision"}],"funders":[{"id":"https://openalex.org/F4320331724","display_name":"Australian Centre for Robotic Vision","ror":"https://ror.org/02zv9xv82"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":80,"referenced_works":["https://openalex.org/W1515851193","https://openalex.org/W1560270123","https://openalex.org/W1574514837","https://openalex.org/W1588998206","https://openalex.org/W2028173473","https://openalex.org/W2031727428","https://openalex.org/W2037917209","https://openalex.org/W2049410986","https://openalex.org/W2050883740","https://openalex.org/W2080834410","https://openalex.org/W2100790457","https://openalex.org/W2104332709","https://openalex.org/W2107297861","https://openalex.org/W2111034649","https://openalex.org/W2113286054","https://openalex.org/W2116966230","https://openalex.org/W2119717200","https://openalex.org/W2129299900","https://openalex.org/W2131938106","https://openalex.org/W2145339207","https://openalex.org/W2155968351","https://openalex.org/W2156174987","https://openalex.org/W2167362547","https://openalex.org/W2296073425","https://openalex.org/W2567075875","https://openalex.org/W2592538810","https://openalex.org/W2612690371","https://openalex.org/W2733961795","https://openalex.org/W2735995851","https://openalex.org/W2738724892","https://openalex.org/W2741122588","https://openalex.org/W2746553466","https://openalex.org/W2774785892","https://openalex.org/W2785342287","https://openalex.org/W2788862220","https://openalex.org/W2795561664","https://openalex.org/W2803616302","https://openalex.org/W2884565639","https://openalex.org/W2888960417","https://openalex.org/W2899496413","https://openalex.org/W2904246096","https://openalex.org/W2904746163","https://openalex.org/W2905364877","https://openalex.org/W2907537824","https://openalex.org/W2909000816","https://openalex.org/W2921528247","https://openalex.org/W2946396478","https://openalex.org/W2949608212","https://openalex.org/W2952581030","https://openalex.org/W2953082648","https://openalex.org/W2953144887","https://openalex.org/W2954718200","https://openalex.org/W2963238274","https://openalex.org/W2963376229","https://openalex.org/W2963923407","https://openalex.org/W2963973314","https://openalex.org/W2967727187","https://openalex.org/W2971262355","https://openalex.org/W2975593089","https://openalex.org/W2990138404","https://openalex.org/W2990747716","https://openalex.org/W2998396902","https://openalex.org/W3011120880","https://openalex.org/W3091552533","https://openalex.org/W3091648108","https://openalex.org/W3092899697","https://openalex.org/W3093210414","https://openalex.org/W3126321819","https://openalex.org/W3130717831","https://openalex.org/W3131309910","https://openalex.org/W3145123113","https://openalex.org/W3205487646","https://openalex.org/W3210184670","https://openalex.org/W4214717370","https://openalex.org/W4243385754","https://openalex.org/W4300799055","https://openalex.org/W6601774771","https://openalex.org/W6634970695","https://openalex.org/W6638018090","https://openalex.org/W6740879895"],"related_works":["https://openalex.org/W3074294383","https://openalex.org/W4233452137","https://openalex.org/W4206669594","https://openalex.org/W2961085424","https://openalex.org/W2959276766","https://openalex.org/W4319083788","https://openalex.org/W2143042284","https://openalex.org/W2158232074","https://openalex.org/W1554232575","https://openalex.org/W2182903468"],"abstract_inverted_index":{"We":[0,65,190],"present":[1],"Bayesian":[2],"Controller":[3],"Fusion":[4],"(BCF):":[5],"a":[6,76,82,106,214],"hybrid":[7],"control":[8,34,58,152,167,177],"strategy":[9],"that":[10,86,98],"combines":[11],"the":[12,27,101,114,133,136,148,151,155,163,166,176,181,188,196,209,219],"strengths":[13,221],"of":[14,139,150,165,222],"traditional":[15,226],"hand-crafted":[16],"controllers":[17,96],"and":[18,46,78,81,124,173,200,225,237],"model-free":[19],"deep":[20,223],"reinforcement":[21],"learning":[22],"(RL).":[23],"BCF":[24,56,67,141,169,212],"thrives":[25],"in":[26,75,105,119,135,184,208],"robotics":[28,71],"domain,":[29],"where":[30,175],"reliable":[31],"but":[32,40,109],"suboptimal":[33],"priors":[35],"exist":[36,97],"for":[37],"many":[38],"tasks,":[39],"RL":[41,224],"from":[42,53],"scratch":[43],"remains":[44],"unsafe":[45],"data-inefficient.":[47],"By":[48],"fusing":[49],"uncertainty-aware":[50],"distributional":[51],"outputs":[52],"each":[54],"system,":[55],"arbitrates":[57],"between":[59],"them,":[60],"exploiting":[61],"their":[62],"respective":[63],"strengths.":[64],"study":[66],"on":[68],"two":[69],"real-world":[70],"tasks":[72],"involving":[73],"navigation":[74],"vast":[77],"long-horizon":[79],"environment,":[80],"complex":[83],"reaching":[84],"task":[85,102,125],"involves":[87],"manipulability":[88],"maximisation.":[89],"For":[90],"both":[91],"these":[92],"domains,":[93],"simple":[94],"handcrafted":[95],"can":[99,232],"solve":[100],"at":[103,245],"hand":[104],"risk-averse":[107],"manner":[108],"do":[110],"not":[111],"necessarily":[112],"exhibit":[113],"optimal":[115],"solution":[116],"given":[117,162],"limitations":[118],"analytical":[120],"modelling,":[121],"controller":[122],"miscalibration":[123],"variation.":[126],"As":[127],"exploration":[128,172],"is":[129,213],"naturally":[130,179],"guided":[131],"by":[132],"prior":[134,178],"early":[137],"stages":[138],"training,":[140],"accelerates":[142],"learning,":[143],"while":[144],"substantially":[145],"improving":[146],"beyond":[147],"performance":[149],"prior,":[153,168],"as":[154],"policy":[156],"gains":[157],"more":[158],"experience.":[159],"More":[160],"importantly,":[161],"risk-aversity":[164],"ensures":[170],"safe":[171],"deployment,":[174],"dominates":[180],"action":[182],"distribution":[183],"states":[185,207],"unknown":[186],"to":[187,195,203],"policy.":[189],"additionally":[191],"show":[192],"BCF\u2019s":[193],"applicability":[194],"zero-shot":[197],"sim-to-real":[198],"setting":[199],"its":[201],"ability":[202],"deal":[204],"with":[205],"out-of-distribution":[206],"real":[210],"world.":[211],"promising":[215],"approach":[216],"towards":[217],"combining":[218],"complementary":[220],"robotic":[227],"control,":[228],"surpassing":[229],"what":[230],"either":[231],"achieve":[233],"independently.":[234],"The":[235],"code":[236],"supplementary":[238],"video":[239],"material":[240],"are":[241],"made":[242],"publicly":[243],"available":[244],"https://krishanrana.github.io/bcf":[246],".":[247]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}