{"id":"https://openalex.org/W4401414310","doi":"https://doi.org/10.1109/icra57147.2024.10610381","title":"Actor-Critic Model Predictive Control","display_name":"Actor-Critic Model Predictive Control","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401414310","doi":"https://doi.org/10.1109/icra57147.2024.10610381"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10610381","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610381","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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/A5013089045","display_name":"\u00c1ngel Romero","orcid":"https://orcid.org/0000-0002-7977-7802"},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Angel Romero","raw_affiliation_strings":["University of Zurich,Robotics and Perception Group, Department of Informatics"],"affiliations":[{"raw_affiliation_string":"University of Zurich,Robotics and Perception Group, Department of Informatics","institution_ids":["https://openalex.org/I202697423"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085971429","display_name":"Yunlong Song","orcid":"https://orcid.org/0000-0002-6352-3744"},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Yunlong Song","raw_affiliation_strings":["University of Zurich,Robotics and Perception Group, Department of Informatics"],"affiliations":[{"raw_affiliation_string":"University of Zurich,Robotics and Perception Group, Department of Informatics","institution_ids":["https://openalex.org/I202697423"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057116316","display_name":"Davide Scaramuzza","orcid":"https://orcid.org/0000-0002-3831-6778"},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Davide Scaramuzza","raw_affiliation_strings":["University of Zurich,Robotics and Perception Group, Department of Informatics"],"affiliations":[{"raw_affiliation_string":"University of Zurich,Robotics and Perception Group, Department of Informatics","institution_ids":["https://openalex.org/I202697423"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5013089045"],"corresponding_institution_ids":["https://openalex.org/I202697423"],"apc_list":null,"apc_paid":null,"fwci":18.0095,"has_fulltext":false,"cited_by_count":54,"citation_normalized_percentile":{"value":0.99629725,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"14777","last_page":"14784"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.35409998893737793,"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":0.35409998893737793,"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/model-predictive-control","display_name":"Model predictive control","score":0.6819869875907898},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6178243160247803},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.42393308877944946},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27356037497520447}],"concepts":[{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.6819869875907898},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6178243160247803},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.42393308877944946},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27356037497520447}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10610381","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610381","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334678","display_name":"European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W2021096542","https://openalex.org/W2119885245","https://openalex.org/W2148764920","https://openalex.org/W2155027007","https://openalex.org/W2491934829","https://openalex.org/W2889731659","https://openalex.org/W2961703895","https://openalex.org/W2963238245","https://openalex.org/W2963689432","https://openalex.org/W2982316857","https://openalex.org/W2992833799","https://openalex.org/W3040334549","https://openalex.org/W3046709980","https://openalex.org/W3093922502","https://openalex.org/W3104876774","https://openalex.org/W3120459386","https://openalex.org/W3131040061","https://openalex.org/W3131850807","https://openalex.org/W3177010373","https://openalex.org/W3185165122","https://openalex.org/W3195968524","https://openalex.org/W3208245705","https://openalex.org/W4200630212","https://openalex.org/W4205430897","https://openalex.org/W4220840735","https://openalex.org/W4255875169","https://openalex.org/W4283262038","https://openalex.org/W4285117968","https://openalex.org/W4285163488","https://openalex.org/W4285446140","https://openalex.org/W4286224728","https://openalex.org/W4286372820","https://openalex.org/W4298427820","https://openalex.org/W4312717465","https://openalex.org/W4383109228","https://openalex.org/W4385430747","https://openalex.org/W4386075826","https://openalex.org/W4386285856","https://openalex.org/W4386718967","https://openalex.org/W4401415577","https://openalex.org/W4401417288","https://openalex.org/W6607786297","https://openalex.org/W6683204974","https://openalex.org/W6754302822","https://openalex.org/W6772082531","https://openalex.org/W6782364735","https://openalex.org/W6802625470","https://openalex.org/W6840335140","https://openalex.org/W6847345055","https://openalex.org/W6847678589","https://openalex.org/W6922480057"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W1990079087","https://openalex.org/W2390279801","https://openalex.org/W2101188133","https://openalex.org/W3202234113","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W4248731570","https://openalex.org/W2556120871"],"abstract_inverted_index":{"An":[0],"open":[1],"research":[2],"question":[3],"in":[4,24,122],"robotics":[5],"is":[6,58],"how":[7],"to":[8,59,163],"combine":[9],"the":[10,29,73,81,98,105,109,126,140,157,161],"benefits":[11,110],"of":[12,35,78,87,111,160,167],"model-free":[13],"reinforcement":[14],"learning":[15],"(RL)\u2014known":[16],"for":[17],"its":[18],"strong":[19],"task":[20],"performance":[21],"and":[22,31,83,101,115,125,153,155],"flexibility":[23],"optimizing":[25],"general":[26],"reward":[27],"formulations\u2014with":[28],"robustness":[30],"online":[32],"replanning":[33],"capabilities":[34,77],"model":[36],"predictive":[37,75,158],"control":[38,114,146],"(MPC).":[39],"This":[40],"paper":[41],"provides":[42],"an":[43,65],"answer":[44],"by":[45],"introducing":[46],"a":[47,61,130],"new":[48],"framework":[49],"called":[50],"Actor-Critic":[51],"Model":[52],"Predictive":[53],"Control.":[54],"The":[55,69,89],"key":[56],"idea":[57],"embed":[60],"differentiable":[62],"MPC":[63,79,162],"within":[64],"actor-critic":[66],"RL":[67],"framework.":[68],"proposed":[70,141],"approach":[71],"leverages":[72],"short-term":[74,95],"optimization":[76],"with":[80,129],"exploratory":[82],"end-to-end":[84,116],"training":[85],"properties":[86,159],"RL.":[88],"resulting":[90],"policy":[91],"effectively":[92],"manages":[93],"both":[94,112,123],"decisions":[96],"through":[97],"MPC-based":[99],"actor":[100],"long-term":[102],"prediction":[103],"via":[104,151],"critic":[106],"network,":[107],"unifying":[108],"model-based":[113],"learning.":[117],"We":[118,137],"validate":[119],"our":[120],"method":[121],"simulation":[124],"real":[127],"world":[128],"quadcopter":[131],"platform":[132],"across":[133],"various":[134],"high-level":[135],"tasks.":[136],"show":[138],"that":[139],"architecture":[142],"can":[143],"achieve":[144],"real-time":[145],"performance,":[147],"learn":[148],"complex":[149],"behaviors":[150],"trial":[152],"error,":[154],"retain":[156],"better":[164],"handle":[165],"out":[166],"distribution":[168],"behaviour.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":36},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-06T13:50:29.536080","created_date":"2025-10-10T00:00:00"}