{"id":"https://openalex.org/W4225603049","doi":"https://doi.org/10.1109/cdc45484.2021.9683750","title":"MPC-based Reinforcement Learning for a Simplified Freight Mission of Autonomous Surface Vehicles","display_name":"MPC-based Reinforcement Learning for a Simplified Freight Mission of Autonomous Surface Vehicles","publication_year":2021,"publication_date":"2021-12-14","ids":{"openalex":"https://openalex.org/W4225603049","doi":"https://doi.org/10.1109/cdc45484.2021.9683750"},"language":"en","primary_location":{"id":"doi:10.1109/cdc45484.2021.9683750","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc45484.2021.9683750","pdf_url":null,"source":{"id":"https://openalex.org/S4363607724","display_name":"2021 60th IEEE Conference on Decision and Control (CDC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 60th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5102767332","display_name":"Wenqi Cai","orcid":"https://orcid.org/0009-0003-2796-9030"},"institutions":[{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Wenqi Cai","raw_affiliation_strings":["Norwegian University of Science and Technology (NTNU), Trondheim, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Norwegian University of Science and Technology (NTNU), Trondheim, Norway","institution_ids":["https://openalex.org/I204778367"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033874726","display_name":"Arash Bahari Kordabad","orcid":"https://orcid.org/0000-0001-8931-5372"},"institutions":[{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Arash B. Kordabad","raw_affiliation_strings":["Norwegian University of Science and Technology (NTNU), Trondheim, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Norwegian University of Science and Technology (NTNU), Trondheim, Norway","institution_ids":["https://openalex.org/I204778367"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011634446","display_name":"Hossein Nejatbakhsh Esfahani","orcid":"https://orcid.org/0000-0003-3515-1645"},"institutions":[{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Hossein N. Esfahani","raw_affiliation_strings":["Norwegian University of Science and Technology (NTNU), Trondheim, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Norwegian University of Science and Technology (NTNU), Trondheim, Norway","institution_ids":["https://openalex.org/I204778367"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060217700","display_name":"Anastasios M. Lekkas","orcid":"https://orcid.org/0000-0001-6885-6372"},"institutions":[{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Anastasios M. Lekkas","raw_affiliation_strings":["Norwegian University of Science and Technology (NTNU), Trondheim, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Norwegian University of Science and Technology (NTNU), Trondheim, Norway","institution_ids":["https://openalex.org/I204778367"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049645185","display_name":"S\u00e9bastien Gros","orcid":"https://orcid.org/0000-0001-6054-2133"},"institutions":[{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Sebastien Gros","raw_affiliation_strings":["Norwegian University of Science and Technology (NTNU), Trondheim, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Norwegian University of Science and Technology (NTNU), Trondheim, Norway","institution_ids":["https://openalex.org/I204778367"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204778367"],"apc_list":null,"apc_paid":null,"fwci":7.6499,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.98888678,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2990","last_page":"2995"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.9864000082015991,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9864000082015991,"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":0.9688000082969666,"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/T10768","display_name":"Electric Vehicles and Infrastructure","score":0.9593999981880188,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.9079905152320862},{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"Model predictive control","score":0.6398022174835205},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5755078792572021},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5473560690879822},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.5413783192634583},{"id":"https://openalex.org/keywords/collision","display_name":"Collision","score":0.5025014877319336},{"id":"https://openalex.org/keywords/vehicle-dynamics","display_name":"Vehicle dynamics","score":0.45616111159324646},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.4457632601261139},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.419474720954895},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.28678837418556213},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.2746858596801758},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25622427463531494},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18531113862991333},{"id":"https://openalex.org/keywords/aerospace-engineering","display_name":"Aerospace engineering","score":0.1448826789855957}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9079905152320862},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.6398022174835205},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5755078792572021},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5473560690879822},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.5413783192634583},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.5025014877319336},{"id":"https://openalex.org/C79487989","wikidata":"https://www.wikidata.org/wiki/Q934680","display_name":"Vehicle dynamics","level":2,"score":0.45616111159324646},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.4457632601261139},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.419474720954895},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.28678837418556213},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2746858596801758},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25622427463531494},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18531113862991333},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.1448826789855957},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc45484.2021.9683750","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc45484.2021.9683750","pdf_url":null,"source":{"id":"https://openalex.org/S4363607724","display_name":"2021 60th IEEE Conference on Decision and Control (CDC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 60th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1971984830","https://openalex.org/W2155027007","https://openalex.org/W2168285891","https://openalex.org/W2586680856","https://openalex.org/W2614079548","https://openalex.org/W2930426397","https://openalex.org/W2948652605","https://openalex.org/W2963631491","https://openalex.org/W3103230881","https://openalex.org/W3153654730","https://openalex.org/W4226319110","https://openalex.org/W4285379000","https://openalex.org/W4285446252","https://openalex.org/W4302570325","https://openalex.org/W6683204974","https://openalex.org/W6684205842","https://openalex.org/W6763565325"],"related_works":["https://openalex.org/W1990079087","https://openalex.org/W3202234113","https://openalex.org/W4306904969","https://openalex.org/W2101188133","https://openalex.org/W3113932901","https://openalex.org/W650625605","https://openalex.org/W4248731570","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W128654086"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3],"propose":[4],"a":[5,33,44,51],"Model":[6],"Predictive":[7],"Control":[8],"(MPC)-based":[9],"Reinforcement":[10],"Learning":[11],"(RL)":[12],"method":[13,81,99],"for":[14,107],"Autonomous":[15],"Surface":[16],"Vehicles":[17],"(ASVs).":[18],"The":[19,71],"objective":[20],"is":[21,82],"to":[22,54,85],"find":[23],"an":[24],"optimal":[25,57],"policy":[26,88],"that":[27,94],"minimizes":[28],"the":[29,56,87,95,102,108],"closed-loop":[30,103],"performance":[31,104],"of":[32,112],"simplified":[34],"freight":[35,109],"mission,":[36],"including":[37],"collision-free":[38],"path":[39],"following,":[40],"autonomous":[41],"docking,":[42],"and":[43,63],"skillful":[45],"transition":[46],"between":[47],"them.":[48],"We":[49],"use":[50],"parametrized":[52],"MPC-scheme":[53],"approximate":[55],"policy,":[58],"which":[59],"considers":[60],"path-following/docking":[61],"costs":[62],"states":[64],"(position,":[65],"velocity)/inputs":[66],"(thruster":[67],"force,":[68],"angle)":[69],"constraints.":[70],"Least":[72],"Squares":[73],"Temporal":[74],"Difference":[75],"(LSTD)-based":[76],"Deterministic":[77],"Policy":[78],"Gradient":[79],"(DPG)":[80],"then":[83],"applied":[84],"update":[86],"parameters.":[89],"Our":[90],"simulation":[91],"results":[92],"demonstrate":[93],"proposed":[96],"MPC-LSTD-based":[97],"DPG":[98],"could":[100],"improve":[101],"during":[105],"learning":[106],"mission":[110],"problem":[111],"ASV.":[113]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
