{"id":"https://openalex.org/W4414432380","doi":"https://doi.org/10.1109/case58245.2025.11164076","title":"Re4MPC: Reactive Nonlinear MPC for Multi-model Motion Planning via Deep Reinforcement Learning","display_name":"Re4MPC: Reactive Nonlinear MPC for Multi-model Motion Planning via Deep Reinforcement Learning","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4414432380","doi":"https://doi.org/10.1109/case58245.2025.11164076"},"language":"en","primary_location":{"id":"doi:10.1109/case58245.2025.11164076","is_oa":false,"landing_page_url":"https://doi.org/10.1109/case58245.2025.11164076","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 21st International Conference on Automation Science and Engineering (CASE)","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/A5054801149","display_name":"Ne\u015fet \u00dcnver Akmandor","orcid":null},"institutions":[{"id":"https://openalex.org/I4210133016","display_name":"Motion Control (United States)","ror":"https://ror.org/03yjg6e54","country_code":"US","type":"company","lineage":["https://openalex.org/I4210133016"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ne\u015fet \u00dcnver Akmandor","raw_affiliation_strings":["Motional AD Inc.,Boston,MA,USA"],"affiliations":[{"raw_affiliation_string":"Motional AD Inc.,Boston,MA,USA","institution_ids":["https://openalex.org/I4210133016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006689663","display_name":"Sarvesh Prajapati","orcid":null},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sarvesh Prajapati","raw_affiliation_strings":["Northeastern University,Institute for Experiential Robotics,Boston,Massachusetts,USA"],"affiliations":[{"raw_affiliation_string":"Northeastern University,Institute for Experiential Robotics,Boston,Massachusetts,USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075977414","display_name":"Mark Zolotas","orcid":"https://orcid.org/0000-0002-7672-940X"},"institutions":[{"id":"https://openalex.org/I1293612202","display_name":"Toyota Motor Corporation (Switzerland)","ror":"https://ror.org/05p0pbv75","country_code":"CH","type":"company","lineage":["https://openalex.org/I1293612202","https://openalex.org/I4210125472","https://openalex.org/I4210137853"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Mark Zolotas","raw_affiliation_strings":["Toyota Research Institute (TRI),Cambridge,MA,USA"],"affiliations":[{"raw_affiliation_string":"Toyota Research Institute (TRI),Cambridge,MA,USA","institution_ids":["https://openalex.org/I1293612202"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009032681","display_name":"Ta\u015fk\u0131n Pad\u0131r","orcid":"https://orcid.org/0000-0001-5123-5801"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ta\u015fk\u0131n Pad\u0131r","raw_affiliation_strings":["Electrical and Computer Engineering at Northeastern University and as an Amazon Scholar"],"affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering at Northeastern University and as an Amazon Scholar","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5054801149"],"corresponding_institution_ids":["https://openalex.org/I4210133016"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34213406,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1728","last_page":"1735"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9839000105857849,"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":0.9839000105857849,"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":0.930400013923645,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7055000066757202},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6456000208854675},{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"Model predictive control","score":0.6413000226020813},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.5995000004768372},{"id":"https://openalex.org/keywords/nonlinear-model","display_name":"Nonlinear model","score":0.5601999759674072},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5407000184059143},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.5157999992370605},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.48890000581741333}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7055000066757202},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6539000272750854},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6456000208854675},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.6413000226020813},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.5995000004768372},{"id":"https://openalex.org/C2984755018","wikidata":"https://www.wikidata.org/wiki/Q17118374","display_name":"Nonlinear model","level":3,"score":0.5601999759674072},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5407000184059143},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5291000008583069},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.5157999992370605},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.48890000581741333},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4595000147819519},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4580000042915344},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.43160000443458557},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4187999963760376},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.4059000015258789},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.39590001106262207},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3377000093460083},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3050000071525574},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.30329999327659607},{"id":"https://openalex.org/C91581856","wikidata":"https://www.wikidata.org/wiki/Q2707001","display_name":"Nonlinear control","level":3,"score":0.274399995803833},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.26249998807907104},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2567000091075897}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/case58245.2025.11164076","is_oa":false,"landing_page_url":"https://doi.org/10.1109/case58245.2025.11164076","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 21st International Conference on Automation Science and Engineering (CASE)","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":27,"referenced_works":["https://openalex.org/W1531755431","https://openalex.org/W2121523122","https://openalex.org/W2145339207","https://openalex.org/W2168359464","https://openalex.org/W2760335198","https://openalex.org/W2772821814","https://openalex.org/W2968953689","https://openalex.org/W3005451807","https://openalex.org/W3042402313","https://openalex.org/W3094470387","https://openalex.org/W3129896193","https://openalex.org/W3142410314","https://openalex.org/W3180158572","https://openalex.org/W3199379010","https://openalex.org/W3205388776","https://openalex.org/W3205566932","https://openalex.org/W3206530605","https://openalex.org/W3206619562","https://openalex.org/W4210703677","https://openalex.org/W4280592755","https://openalex.org/W4312368247","https://openalex.org/W4327733733","https://openalex.org/W4365790399","https://openalex.org/W4376891105","https://openalex.org/W4383108995","https://openalex.org/W4399412814","https://openalex.org/W4402299984"],"related_works":[],"abstract_inverted_index":{"Traditional":[0],"motion":[1,28],"planning":[2,29],"methods":[3],"for":[4,17,74],"robots":[5],"with":[6],"many":[7],"degrees-of-freedom,":[8],"such":[9],"as":[10],"mobile":[11,119],"manipulators,":[12],"are":[13],"often":[14],"computationally":[15,47,128],"prohibitive":[16],"real-world":[18],"settings.":[19],"In":[20],"this":[21,75,96],"paper,":[22],"we":[23,106],"propose":[24],"a":[25,46,81,89,114,118],"novel":[26],"multi-model":[27],"pipeline,":[30],"termed":[31],"Re4MPC,":[32],"which":[33,143],"computes":[34,144],"trajectories":[35,44,146],"using":[36],"Nonlinear":[37],"Model":[38],"Predictive":[39],"Control":[40],"(NMPC).":[41],"Re4MPC":[42,125],"generates":[43],"in":[45,113,135],"efficient":[48,129],"manner":[49],"by":[50],"reactively":[51],"selecting":[52],"the":[53,59,64,67,140],"model,":[54],"cost,":[55],"and":[56,69,103,110,130],"constraints":[57],"of":[58,66],"NMPC":[60,94,141],"problem":[61],"depending":[62],"on":[63],"complexity":[65],"task":[68],"robot":[70],"state.":[71],"The":[72],"policy":[73],"reactive":[76],"decision-making":[77],"is":[78,126],"learned":[79],"via":[80],"Deep":[82],"Reinforcement":[83],"Learning":[84],"(DRL)":[85],"framework.":[86,98],"We":[87],"introduce":[88],"mathematical":[90],"formulation":[91],"to":[92],"integrate":[93],"into":[95],"DRL":[97,108],"To":[99],"validate":[100],"our":[101,148],"methodology":[102],"design":[104],"choices,":[105],"evaluate":[107],"training":[109],"test":[111],"outcomes":[112],"physics-based":[115],"simulation":[116],"involving":[117],"manipulator.":[120],"Experimental":[121],"results":[122],"demonstrate":[123],"that":[124],"more":[127],"achieves":[131],"higher":[132],"success":[133],"rates":[134],"reaching":[136],"end-effector":[137],"goals":[138],"than":[139],"baseline,":[142],"whole-body":[145],"without":[147],"learning":[149],"mechanism.":[150]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}