{"id":"https://openalex.org/W4320011039","doi":"https://doi.org/10.1109/iccspa55860.2022.10018994","title":"Safe Reinforcement Learning using Data-Driven Predictive Control","display_name":"Safe Reinforcement Learning using Data-Driven Predictive Control","publication_year":2022,"publication_date":"2022-12-27","ids":{"openalex":"https://openalex.org/W4320011039","doi":"https://doi.org/10.1109/iccspa55860.2022.10018994"},"language":"en","primary_location":{"id":"doi:10.1109/iccspa55860.2022.10018994","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccspa55860.2022.10018994","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 5th International Conference on Communications, Signal Processing, and their Applications (ICCSPA)","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/A5046206548","display_name":"Mahmoud Selim","orcid":"https://orcid.org/0000-0002-9499-6480"},"institutions":[{"id":"https://openalex.org/I107720978","display_name":"Ain Shams University","ror":"https://ror.org/00cb9w016","country_code":"EG","type":"education","lineage":["https://openalex.org/I107720978"]}],"countries":["EG"],"is_corresponding":true,"raw_author_name":"Mahmoud Selim","raw_affiliation_strings":["Ain Shams University,Cairo,Egypt","Ain Shams University, Cairo, Egypt"],"affiliations":[{"raw_affiliation_string":"Ain Shams University,Cairo,Egypt","institution_ids":["https://openalex.org/I107720978"]},{"raw_affiliation_string":"Ain Shams University, Cairo, Egypt","institution_ids":["https://openalex.org/I107720978"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102709386","display_name":"Amr Alanwar","orcid":"https://orcid.org/0000-0003-2941-519X"},"institutions":[{"id":"https://openalex.org/I193619901","display_name":"Constructor University","ror":"https://ror.org/02yrs2n53","country_code":"DE","type":"education","lineage":["https://openalex.org/I193619901"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Amr Alanwar","raw_affiliation_strings":["Jacobs University,Bremen,Germany","Jacobs University, Bremen, Germany"],"affiliations":[{"raw_affiliation_string":"Jacobs University,Bremen,Germany","institution_ids":["https://openalex.org/I193619901"]},{"raw_affiliation_string":"Jacobs University, Bremen, Germany","institution_ids":["https://openalex.org/I193619901"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056943013","display_name":"M. Watheq El\u2010Kharashi","orcid":"https://orcid.org/0000-0002-6033-733X"},"institutions":[{"id":"https://openalex.org/I107720978","display_name":"Ain Shams University","ror":"https://ror.org/00cb9w016","country_code":"EG","type":"education","lineage":["https://openalex.org/I107720978"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"M. Watheq El-Kharashi","raw_affiliation_strings":["Ain Shams University,Cairo,Egypt","Ain Shams University, Cairo, Egypt"],"affiliations":[{"raw_affiliation_string":"Ain Shams University,Cairo,Egypt","institution_ids":["https://openalex.org/I107720978"]},{"raw_affiliation_string":"Ain Shams University, Cairo, Egypt","institution_ids":["https://openalex.org/I107720978"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004204048","display_name":"Hazem M. Abbas","orcid":"https://orcid.org/0000-0001-9128-3111"},"institutions":[{"id":"https://openalex.org/I107720978","display_name":"Ain Shams University","ror":"https://ror.org/00cb9w016","country_code":"EG","type":"education","lineage":["https://openalex.org/I107720978"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Hazem M. Abbas","raw_affiliation_strings":["Ain Shams University,Cairo,Egypt","Ain Shams University, Cairo, Egypt"],"affiliations":[{"raw_affiliation_string":"Ain Shams University,Cairo,Egypt","institution_ids":["https://openalex.org/I107720978"]},{"raw_affiliation_string":"Ain Shams University, Cairo, Egypt","institution_ids":["https://openalex.org/I107720978"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045975901","display_name":"Karl Henrik Johansson","orcid":"https://orcid.org/0000-0001-9940-5929"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Karl H. Johansson","raw_affiliation_strings":["KTH Royal Institute of Technology,Stockholm,Sweden","KTH Royal Institute of Technology, Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Stockholm,Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5046206548"],"corresponding_institution_ids":["https://openalex.org/I107720978"],"apc_list":null,"apc_paid":null,"fwci":0.5303,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.72026145,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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":0.9993000030517578,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9926999807357788,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8484961986541748},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7773313522338867},{"id":"https://openalex.org/keywords/intersection","display_name":"Intersection (aeronautics)","score":0.659561276435852},{"id":"https://openalex.org/keywords/reachability","display_name":"Reachability","score":0.5828685760498047},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5792518854141235},{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"Model predictive control","score":0.5563120245933533},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5458124876022339},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5404916405677795},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4716821312904358},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.46949341893196106},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4466083347797394},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.444046288728714},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.43615269660949707},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41803646087646484},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3251872956752777},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12087798118591309},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09354761242866516}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8484961986541748},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7773313522338867},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.659561276435852},{"id":"https://openalex.org/C136643341","wikidata":"https://www.wikidata.org/wiki/Q1361526","display_name":"Reachability","level":2,"score":0.5828685760498047},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5792518854141235},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.5563120245933533},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5458124876022339},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5404916405677795},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4716821312904358},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.46949341893196106},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4466083347797394},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.444046288728714},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.43615269660949707},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41803646087646484},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3251872956752777},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12087798118591309},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09354761242866516},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccspa55860.2022.10018994","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccspa55860.2022.10018994","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 5th International Conference on Communications, Signal Processing, and their Applications (ICCSPA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7200000286102295,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W134786152","https://openalex.org/W1424654272","https://openalex.org/W1515851193","https://openalex.org/W1585575029","https://openalex.org/W1845972764","https://openalex.org/W1975720701","https://openalex.org/W1996625075","https://openalex.org/W2051110650","https://openalex.org/W2101075098","https://openalex.org/W2169206416","https://openalex.org/W2293539771","https://openalex.org/W2427917354","https://openalex.org/W2750147881","https://openalex.org/W2784465508","https://openalex.org/W2887154784","https://openalex.org/W2913756371","https://openalex.org/W2947861305","https://openalex.org/W2963780574","https://openalex.org/W2967193622","https://openalex.org/W2990212897","https://openalex.org/W2999840070","https://openalex.org/W3029901419","https://openalex.org/W3080564557","https://openalex.org/W3081975785","https://openalex.org/W3132557532","https://openalex.org/W3133498163","https://openalex.org/W3135301907","https://openalex.org/W3142005321","https://openalex.org/W3143477657","https://openalex.org/W3160457970","https://openalex.org/W3171392489","https://openalex.org/W3196118096","https://openalex.org/W4206058163","https://openalex.org/W4281550413","https://openalex.org/W4285818823","https://openalex.org/W4293545785","https://openalex.org/W4297780563","https://openalex.org/W4297799385","https://openalex.org/W4324116431","https://openalex.org/W6639175102","https://openalex.org/W6685043521","https://openalex.org/W6751725685","https://openalex.org/W6785757768","https://openalex.org/W6796910599","https://openalex.org/W6801971982"],"related_works":["https://openalex.org/W2136512912","https://openalex.org/W2127267268","https://openalex.org/W2156446763","https://openalex.org/W2067910792","https://openalex.org/W2150194458","https://openalex.org/W2143461633","https://openalex.org/W2889071233","https://openalex.org/W4321471459","https://openalex.org/W4221156924","https://openalex.org/W2380814829"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"(RL)":[2],"algorithms":[3,17],"can":[4],"achieve":[5],"state-of-the-art":[6,164],"performance":[7],"in":[8,177,182],"decision-making":[9],"and":[10,43,83,147,179],"continuous":[11],"control":[12],"tasks.":[13],"However,":[14],"applying":[15],"RL":[16,34,79,87,139,166],"on":[18,168],"safety-critical":[19],"systems":[20],"still":[21],"needs":[22],"to":[23,28,74,123,129],"be":[24],"well":[25],"justified":[26],"due":[27],"the":[29,38,41,44,97,107,111,114,119,125,130,138,142,151,156,169],"exploration":[30],"nature":[31],"of":[32,40,110],"many":[33],"algorithms,":[35],"especially":[36],"when":[37],"model":[39],"robot":[42,112],"environment":[45],"are":[46],"unknown.":[47],"To":[48],"address":[49],"this":[50],"challenge,":[51],"we":[52,117,158],"propose":[53],"a":[54,61,70,174,180],"data-driven":[55,71,98,120],"safety":[56,67,76,135],"layer":[57,68,136],"that":[58,92,160],"acts":[59],"as":[60],"filter":[62],"for":[63,78,173],"unsafe":[64,132,146],"actions.":[65],"The":[66,86,134],"uses":[69],"predictive":[72,121],"controller":[73,122],"enforce":[75],"guarantees":[77],"policies":[80],"during":[81],"training":[82],"after":[84],"deployment.":[85],"agent":[88,140],"proposes":[89],"an":[90,104],"action":[91,128,144],"is":[93,103,145],"verified":[94],"by":[95],"computing":[96],"reachability":[99],"analysis.":[100],"If":[101],"there":[102],"intersection":[105],"between":[106],"reachable":[108],"set":[109],"using":[113],"proposed":[115,131,143],"action,":[116],"call":[118],"find":[124],"closest":[126,152],"safe":[127,153,165],"action.":[133],"penalizes":[137],"if":[141],"replaces":[148],"it":[149],"with":[150],"one.":[154],"In":[155],"simulation,":[157],"show":[159],"our":[161],"method":[162],"outperforms":[163],"methods":[167],"robotics":[170],"navigation":[171],"problem":[172],"Turtlebot":[175],"3":[176],"Gazebo":[178],"quadrotor":[181],"Unreal":[183],"Engine":[184],"4":[185],"(UE4).":[186]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}