{"id":"https://openalex.org/W3206448035","doi":"https://doi.org/10.1109/icra48506.2021.9561147","title":"FISAR: Forward Invariant Safe Reinforcement Learning with a Deep Neural Network-Based Optimizer","display_name":"FISAR: Forward Invariant Safe Reinforcement Learning with a Deep Neural Network-Based Optimizer","publication_year":2021,"publication_date":"2021-05-30","ids":{"openalex":"https://openalex.org/W3206448035","doi":"https://doi.org/10.1109/icra48506.2021.9561147","mag":"3206448035"},"language":"en","primary_location":{"id":"doi:10.1109/icra48506.2021.9561147","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561147","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/1721.1/145372","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051533554","display_name":"Chuangchuang Sun","orcid":"https://orcid.org/0000-0003-3049-5828"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]},{"id":"https://openalex.org/I4210143601","display_name":"Decision Systems (United States)","ror":"https://ror.org/0434dpa13","country_code":"US","type":"company","lineage":["https://openalex.org/I4210143601"]},{"id":"https://openalex.org/I4210126846","display_name":"Information Technology Laboratory","ror":"https://ror.org/0440c3437","country_code":"US","type":"government","lineage":["https://openalex.org/I1321296531","https://openalex.org/I1343035065","https://openalex.org/I4210126846"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chuangchuang Sun","raw_affiliation_strings":["Massachusetts Institute of Technology,Laboratory for Information & Decision Systems (LIDS),Cambridge,MA,02139","Laboratory for Information &#x0026"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology,Laboratory for Information & Decision Systems (LIDS),Cambridge,MA,02139","institution_ids":["https://openalex.org/I4210143601","https://openalex.org/I63966007"]},{"raw_affiliation_string":"Laboratory for Information &#x0026","institution_ids":["https://openalex.org/I4210126846"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033449275","display_name":"Dong Ki Kim","orcid":"https://orcid.org/0000-0002-5195-7852"},"institutions":[{"id":"https://openalex.org/I4210143601","display_name":"Decision Systems (United States)","ror":"https://ror.org/0434dpa13","country_code":"US","type":"company","lineage":["https://openalex.org/I4210143601"]},{"id":"https://openalex.org/I4210126846","display_name":"Information Technology Laboratory","ror":"https://ror.org/0440c3437","country_code":"US","type":"government","lineage":["https://openalex.org/I1321296531","https://openalex.org/I1343035065","https://openalex.org/I4210126846"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong-Ki Kim","raw_affiliation_strings":["Massachusetts Institute of Technology,Laboratory for Information & Decision Systems (LIDS),Cambridge,MA,02139","Laboratory for Information &#x0026"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology,Laboratory for Information & Decision Systems (LIDS),Cambridge,MA,02139","institution_ids":["https://openalex.org/I4210143601","https://openalex.org/I63966007"]},{"raw_affiliation_string":"Laboratory for Information &#x0026","institution_ids":["https://openalex.org/I4210126846"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011665886","display_name":"Jonathan P. How","orcid":"https://orcid.org/0000-0001-8576-1930"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]},{"id":"https://openalex.org/I4210143601","display_name":"Decision Systems (United States)","ror":"https://ror.org/0434dpa13","country_code":"US","type":"company","lineage":["https://openalex.org/I4210143601"]},{"id":"https://openalex.org/I4210126846","display_name":"Information Technology Laboratory","ror":"https://ror.org/0440c3437","country_code":"US","type":"government","lineage":["https://openalex.org/I1321296531","https://openalex.org/I1343035065","https://openalex.org/I4210126846"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan P. How","raw_affiliation_strings":["Massachusetts Institute of Technology,Laboratory for Information & Decision Systems (LIDS),Cambridge,MA,02139","Laboratory for Information &#x0026"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology,Laboratory for Information & Decision Systems (LIDS),Cambridge,MA,02139","institution_ids":["https://openalex.org/I4210143601","https://openalex.org/I63966007"]},{"raw_affiliation_string":"Laboratory for Information &#x0026","institution_ids":["https://openalex.org/I4210126846"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5051533554"],"corresponding_institution_ids":["https://openalex.org/I4210126846","https://openalex.org/I4210143601","https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":0.5597,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.73931469,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"10617","last_page":"10624"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.998199999332428,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.998199999332428,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9853000044822693,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T10524","display_name":"Traffic control and management","score":0.9847000241279602,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.811178982257843},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6790831089019775},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6473944783210754},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.6351773738861084},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5085142850875854},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15724346041679382}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.811178982257843},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6790831089019775},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6473944783210754},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.6351773738861084},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5085142850875854},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15724346041679382},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icra48506.2021.9561147","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561147","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:dspace.mit.edu:1721.1/145372","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/145372","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv","raw_type":"http://purl.org/eprint/type/ConferencePaper"}],"best_oa_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/145372","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/145372","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv","raw_type":"http://purl.org/eprint/type/ConferencePaper"},"sustainable_development_goals":[{"score":0.47999998927116394,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":71,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1191599655","https://openalex.org/W1518931405","https://openalex.org/W1522301498","https://openalex.org/W1845972764","https://openalex.org/W1880805667","https://openalex.org/W1985123706","https://openalex.org/W2064675550","https://openalex.org/W2093229781","https://openalex.org/W2121863487","https://openalex.org/W2155027007","https://openalex.org/W2171505650","https://openalex.org/W2560504659","https://openalex.org/W2575705757","https://openalex.org/W2602585184","https://openalex.org/W2618318883","https://openalex.org/W2624086852","https://openalex.org/W2742093937","https://openalex.org/W2784465508","https://openalex.org/W2787908307","https://openalex.org/W2885381174","https://openalex.org/W2936995161","https://openalex.org/W2951634833","https://openalex.org/W2962803570","https://openalex.org/W2963082979","https://openalex.org/W2963184621","https://openalex.org/W2963575966","https://openalex.org/W2963775850","https://openalex.org/W2964121744","https://openalex.org/W2964161785","https://openalex.org/W2964340170","https://openalex.org/W2966735560","https://openalex.org/W2970927156","https://openalex.org/W2981915592","https://openalex.org/W2990866132","https://openalex.org/W3012839911","https://openalex.org/W3015606043","https://openalex.org/W3016534272","https://openalex.org/W3037804676","https://openalex.org/W3038180127","https://openalex.org/W3041244724","https://openalex.org/W3098925401","https://openalex.org/W3141595720","https://openalex.org/W3162902207","https://openalex.org/W3163842339","https://openalex.org/W3173921802","https://openalex.org/W4287725923","https://openalex.org/W4289709949","https://openalex.org/W4293545785","https://openalex.org/W4294555834","https://openalex.org/W4294562617","https://openalex.org/W6627932998","https://openalex.org/W6631190155","https://openalex.org/W6683204974","https://openalex.org/W6687063787","https://openalex.org/W6717367658","https://openalex.org/W6735618850","https://openalex.org/W6737893269","https://openalex.org/W6738483526","https://openalex.org/W6739653404","https://openalex.org/W6742288159","https://openalex.org/W6743563064","https://openalex.org/W6747790125","https://openalex.org/W6751535212","https://openalex.org/W6753691991","https://openalex.org/W6761030284","https://openalex.org/W6767486501","https://openalex.org/W6775359006","https://openalex.org/W6776331362","https://openalex.org/W6780312303","https://openalex.org/W6780587392"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4306904969","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2138720691","https://openalex.org/W2376932109","https://openalex.org/W4362501864","https://openalex.org/W2001405890"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"reinforcement":[3],"learning":[4],"with":[5,117,137],"constraints,":[6,111],"which":[7,112],"are":[8,55,70],"indispensable":[9],"in":[10],"safety-critical":[11],"environments.":[12],"To":[13,74,122],"drive":[14],"the":[15,23,34,42,51,58,63,90,94,123,130,138,152,157,170],"constraint":[16,153],"violation":[17,154],"to":[18,79,88,150],"decrease":[19,151],"monotonically,":[20],"we":[21,77],"take":[22],"constraints":[24,32,54],"as":[25],"Lyapunov":[26],"functions":[27],"and":[28,155,166],"impose":[29],"new":[30,52],"linear":[31,95,109],"on":[33,57,162],"policy":[35,65,149],"parameters’":[36],"updating":[37,59],"dynamics.":[38],"As":[39],"a":[40,81,104,148],"result,":[41],"original":[43,64],"safety":[44],"set":[45],"can":[46,113],"be":[47,114],"forward-invariant.":[48],"However,":[49],"because":[50],"guaranteed-feasible":[53],"imposed":[56],"dynamics":[60],"instead":[61],"of":[62,125],"parameters,":[66],"classic":[67],"optimization":[68,136,165],"algorithms":[69],"no":[71],"longer":[72],"applicable.":[73],"address":[75],"this,":[76],"propose":[78],"learn":[80],"generic":[82],"deep":[83],"neural":[84],"network":[85],"(DNN)-based":[86],"optimizer":[87,133,146],"optimize":[89],"objective":[91],"while":[92],"satisfying":[93],"constraints.":[96],"The":[97],"constraint-satisfaction":[98],"is":[99,129],"achieved":[100],"via":[101],"projection":[102],"onto":[103],"polytope":[105],"formulated":[106],"by":[107],"multiple":[108],"inequality":[110],"solved":[115],"analytically":[116],"our":[118,126,145],"newly":[119],"designed":[120],"metric.":[121],"best":[124],"knowledge,":[127],"this":[128],"first":[131],"DNN-based":[132],"for":[134],"constrained":[135,164],"forward":[139],"invariance":[140],"guarantee.":[141],"We":[142],"show":[143],"that":[144],"trains":[147],"maximize":[156],"cumulative":[158],"reward":[159],"monotonically.":[160],"Results":[161],"numerical":[163],"obstacle-avoidance":[167],"navigation":[168],"validate":[169],"theoretical":[171],"findings.":[172]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}