{"id":"https://openalex.org/W3091691175","doi":"https://doi.org/10.1109/icra40945.2020.9196867","title":"Robust Model Predictive Shielding for Safe Reinforcement Learning with Stochastic Dynamics","display_name":"Robust Model Predictive Shielding for Safe Reinforcement Learning with Stochastic Dynamics","publication_year":2020,"publication_date":"2020-05-01","ids":{"openalex":"https://openalex.org/W3091691175","doi":"https://doi.org/10.1109/icra40945.2020.9196867","mag":"3091691175"},"language":"en","primary_location":{"id":"doi:10.1109/icra40945.2020.9196867","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra40945.2020.9196867","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","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/A5100386630","display_name":"Shuo Li","orcid":"https://orcid.org/0000-0002-5184-3230"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuo Li","raw_affiliation_strings":["GRASP Lab, University of Pennsylvania, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GRASP Lab, University of Pennsylvania, USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029243071","display_name":"Osbert Bastani","orcid":"https://orcid.org/0000-0001-9990-7566"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Osbert Bastani","raw_affiliation_strings":["Department of Computer and Information Science, University of Pennsylvania, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Science, University of Pennsylvania, USA","institution_ids":["https://openalex.org/I79576946"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I79576946"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":65,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7166","last_page":"7172"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9965999722480774,"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":0.9965999722480774,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9940999746322632,"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/backup","display_name":"Backup","score":0.802836000919342},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7489728331565857},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6661378145217896},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.6021237373352051},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5960313677787781},{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"Model predictive control","score":0.569866418838501},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5164546966552734},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.46390411257743835},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3514679968357086},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.33571505546569824},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.18737930059432983},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.15049579739570618}],"concepts":[{"id":"https://openalex.org/C2780945871","wikidata":"https://www.wikidata.org/wiki/Q194274","display_name":"Backup","level":2,"score":0.802836000919342},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7489728331565857},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6661378145217896},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.6021237373352051},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5960313677787781},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.569866418838501},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5164546966552734},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.46390411257743835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3514679968357086},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.33571505546569824},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.18737930059432983},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.15049579739570618},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra40945.2020.9196867","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra40945.2020.9196867","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","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":65,"referenced_works":["https://openalex.org/W1771410628","https://openalex.org/W1963790880","https://openalex.org/W1964307222","https://openalex.org/W2053572490","https://openalex.org/W2066425650","https://openalex.org/W2073787051","https://openalex.org/W2109804436","https://openalex.org/W2139430868","https://openalex.org/W2155968351","https://openalex.org/W2156909104","https://openalex.org/W2165150801","https://openalex.org/W2257979135","https://openalex.org/W2294151168","https://openalex.org/W2342840547","https://openalex.org/W2346460013","https://openalex.org/W2468927877","https://openalex.org/W2618318883","https://openalex.org/W2736601468","https://openalex.org/W2746553466","https://openalex.org/W2803974723","https://openalex.org/W2807662017","https://openalex.org/W2902690953","https://openalex.org/W2920498407","https://openalex.org/W2962775887","https://openalex.org/W2963277051","https://openalex.org/W2963314509","https://openalex.org/W2963575966","https://openalex.org/W2963796870","https://openalex.org/W2964043796","https://openalex.org/W2964130946","https://openalex.org/W2964231903","https://openalex.org/W2968547875","https://openalex.org/W2970620827","https://openalex.org/W2980176594","https://openalex.org/W2982041656","https://openalex.org/W2990747716","https://openalex.org/W3003648996","https://openalex.org/W3004235133","https://openalex.org/W3028801376","https://openalex.org/W3031236342","https://openalex.org/W3117881175","https://openalex.org/W4239944110","https://openalex.org/W4289236734","https://openalex.org/W4294555834","https://openalex.org/W4299285968","https://openalex.org/W4302570325","https://openalex.org/W4317466250","https://openalex.org/W6638018090","https://openalex.org/W6684205842","https://openalex.org/W6692846177","https://openalex.org/W6704559304","https://openalex.org/W6718092244","https://openalex.org/W6738483526","https://openalex.org/W6741002519","https://openalex.org/W6748501127","https://openalex.org/W6751437432","https://openalex.org/W6756687206","https://openalex.org/W6760047469","https://openalex.org/W6760725535","https://openalex.org/W6763711611","https://openalex.org/W6765484111","https://openalex.org/W6766224423","https://openalex.org/W6769598862","https://openalex.org/W6770858630","https://openalex.org/W6773859063"],"related_works":["https://openalex.org/W2955195711","https://openalex.org/W2354454611","https://openalex.org/W2993266126","https://openalex.org/W2392283887","https://openalex.org/W2351388597","https://openalex.org/W2939925694","https://openalex.org/W2829881200","https://openalex.org/W4241986464","https://openalex.org/W2184647741","https://openalex.org/W2000675896"],"abstract_inverted_index":{"We":[0,15,56,98,114,131],"propose":[1,99],"a":[2,44,53,67,89,102,146],"framework":[3],"for":[4],"safe":[5],"reinforcement":[6,49],"learning":[7,125],"that":[8,134],"can":[9,137],"handle":[10],"stochastic":[11,31,96,141],"nonlinear":[12,105],"dynamical":[13],"systems.":[14],"focus":[16],"on":[17,58],"the":[18,21,41,59,74,93,111,116],"setting":[19],"where":[20,66],"nominal":[22],"dynamics":[23],"are":[24,27],"known,":[25],"and":[26,145],"subject":[28],"to":[29,39,72,79,87,100,127],"additive":[30],"disturbances":[32],"with":[33,149],"known":[34],"distribution.":[35],"Our":[36],"goal":[37],"is":[38,70,85],"ensure":[40,80,138],"safety":[42,139],"of":[43,61,95],"control":[45],"policy":[46,76,91],"trained":[47],"using":[48,118],"learning,":[50],"e.g.,":[51],"in":[52,92,140],"simulated":[54],"environment.":[55],"build":[57],"idea":[60],"model":[62,106],"predictive":[63,107],"shielding":[64],"(MPS),":[65],"backup":[68,90,112],"controller":[69,108],"used":[71],"override":[73],"learned":[75],"as":[77,110],"needed":[78],"safety.":[81],"The":[82],"key":[83],"challenge":[84],"how":[86],"compute":[88],"context":[94],"dynamics.":[97],"use":[101],"tube-based":[103],"robust":[104],"(NMPC)":[109],"controller.":[113],"estimate":[115],"tubes":[117],"sampled":[119],"trajectories,":[120],"leveraging":[121],"ideas":[122],"from":[123],"statistical":[124],"theory":[126],"obtain":[128],"high-probability":[129],"guarantees.":[130],"empirically":[132],"demonstrate":[133],"our":[135],"approach":[136],"systems,":[142],"including":[143],"cart-pole":[144],"non-holonomic":[147],"particle":[148],"random":[150],"obstacles.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}