{"id":"https://openalex.org/W3210663387","doi":"https://doi.org/10.1109/ecmr50962.2021.9568848","title":"Null Space Based Efficient Reinforcement Learning with Hierarchical Safety Constraints","display_name":"Null Space Based Efficient Reinforcement Learning with Hierarchical Safety Constraints","publication_year":2021,"publication_date":"2021-08-01","ids":{"openalex":"https://openalex.org/W3210663387","doi":"https://doi.org/10.1109/ecmr50962.2021.9568848","mag":"3210663387"},"language":"en","primary_location":{"id":"doi:10.1109/ecmr50962.2021.9568848","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ecmr50962.2021.9568848","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 European Conference on Mobile Robots (ECMR)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:oru:diva-95146","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021059709","display_name":"Quantao Yang","orcid":"https://orcid.org/0000-0001-5655-0990"},"institutions":[{"id":"https://openalex.org/I26437253","display_name":"\u00d6rebro University","ror":"https://ror.org/05kytsw45","country_code":"SE","type":"education","lineage":["https://openalex.org/I26437253"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Quantao Yang","raw_affiliation_strings":["Autonomous Mobile Manipulation Lab (AMM), \u00d6rebro University, Sweden"],"affiliations":[{"raw_affiliation_string":"Autonomous Mobile Manipulation Lab (AMM), \u00d6rebro University, Sweden","institution_ids":["https://openalex.org/I26437253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023785357","display_name":"Johannes A. Stork","orcid":"https://orcid.org/0000-0003-3958-6179"},"institutions":[{"id":"https://openalex.org/I26437253","display_name":"\u00d6rebro University","ror":"https://ror.org/05kytsw45","country_code":"SE","type":"education","lineage":["https://openalex.org/I26437253"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Johannes A. Stork","raw_affiliation_strings":["Autonomous Mobile Manipulation Lab (AMM), \u00d6rebro University, Sweden"],"affiliations":[{"raw_affiliation_string":"Autonomous Mobile Manipulation Lab (AMM), \u00d6rebro University, Sweden","institution_ids":["https://openalex.org/I26437253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044352907","display_name":"Todor Stoyanov","orcid":"https://orcid.org/0000-0002-6013-4874"},"institutions":[{"id":"https://openalex.org/I26437253","display_name":"\u00d6rebro University","ror":"https://ror.org/05kytsw45","country_code":"SE","type":"education","lineage":["https://openalex.org/I26437253"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Todor Stoyanov","raw_affiliation_strings":["Autonomous Mobile Manipulation Lab (AMM), \u00d6rebro University, Sweden"],"affiliations":[{"raw_affiliation_string":"Autonomous Mobile Manipulation Lab (AMM), \u00d6rebro University, Sweden","institution_ids":["https://openalex.org/I26437253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5021059709"],"corresponding_institution_ids":["https://openalex.org/I26437253"],"apc_list":null,"apc_paid":null,"fwci":0.4079,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.6951359,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"16","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":0.9969000220298767,"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":0.9969000220298767,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9962999820709229,"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/T11023","display_name":"Prosthetics and Rehabilitation Robotics","score":0.964900016784668,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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":0.8900660276412964},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7196820974349976},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6333035230636597},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.629608690738678},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5793485641479492},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5623419880867004},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.46454906463623047},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45045122504234314},{"id":"https://openalex.org/keywords/null","display_name":"Null (SQL)","score":0.4403223693370819},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4325055181980133},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4107248783111572},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18049001693725586},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16508406400680542},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.13876262307167053}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8900660276412964},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7196820974349976},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6333035230636597},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.629608690738678},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5793485641479492},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5623419880867004},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.46454906463623047},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45045122504234314},{"id":"https://openalex.org/C203763787","wikidata":"https://www.wikidata.org/wiki/Q371029","display_name":"Null (SQL)","level":2,"score":0.4403223693370819},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4325055181980133},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4107248783111572},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18049001693725586},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16508406400680542},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.13876262307167053},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ecmr50962.2021.9568848","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ecmr50962.2021.9568848","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 European Conference on Mobile Robots (ECMR)","raw_type":"proceedings-article"},{"id":"pmh:oai:DiVA.org:oru-95146","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:oru:diva-95146","pdf_url":null,"source":{"id":"https://openalex.org/S4306400154","display_name":"\u00d6rebro University Library (\u00d6rebro University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I26437253","host_organization_name":"\u00d6rebro University","host_organization_lineage":["https://openalex.org/I26437253"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:DiVA.org:oru-95146","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:oru:diva-95146","pdf_url":null,"source":{"id":"https://openalex.org/S4306400154","display_name":"\u00d6rebro University Library (\u00d6rebro University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I26437253","host_organization_name":"\u00d6rebro University","host_organization_lineage":["https://openalex.org/I26437253"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1518931405","https://openalex.org/W1522301498","https://openalex.org/W1771410628","https://openalex.org/W1845972764","https://openalex.org/W1996625075","https://openalex.org/W2017957151","https://openalex.org/W2019606703","https://openalex.org/W2121863487","https://openalex.org/W2167340365","https://openalex.org/W2173248099","https://openalex.org/W2605102758","https://openalex.org/W2736457169","https://openalex.org/W2736601468","https://openalex.org/W2884228673","https://openalex.org/W2892521964","https://openalex.org/W2894708207","https://openalex.org/W2909612327","https://openalex.org/W2911305319","https://openalex.org/W2950471160","https://openalex.org/W2950912723","https://openalex.org/W2953431737","https://openalex.org/W2962803570","https://openalex.org/W2963864421","https://openalex.org/W2964121744","https://openalex.org/W2970749192","https://openalex.org/W2994446013","https://openalex.org/W3089710958","https://openalex.org/W3090600213","https://openalex.org/W3101442004","https://openalex.org/W3176971532","https://openalex.org/W4293545785","https://openalex.org/W6631190155","https://openalex.org/W6638018090","https://openalex.org/W6684921986","https://openalex.org/W6696324988","https://openalex.org/W6737893269","https://openalex.org/W6741002519","https://openalex.org/W6758165564","https://openalex.org/W6764346552","https://openalex.org/W6780961163","https://openalex.org/W6966558720"],"related_works":["https://openalex.org/W2951287487","https://openalex.org/W1570309050","https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W2768698792"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,11,56,89,97,135,157],"is":[2,30,93],"inherently":[3],"unsafe":[4],"for":[5,111,127],"use":[6],"in":[7,34,58,99,147],"physical":[8],"systems,":[9],"as":[10],"by":[12,95],"trial-and-error":[13],"can":[14,159],"cause":[15],"harm":[16],"to":[17,26,31,38,69,117,132],"the":[18,21,35,40,100,119,134],"environment":[19],"or":[20],"robot":[22,41,120],"itself.":[23],"One":[24],"way":[25],"avoid":[27],"unpredictable":[28],"exploration":[29,92],"add":[32,124],"constraints":[33,131],"action":[36,61],"space":[37,50,102,154],"restrict":[39],"behavior.":[42],"In":[43],"this":[44],"paper,":[45],"we":[46,123],"propose":[47],"a":[48,65],"null":[49,101,153],"based":[51,155],"framework":[52,68],"of":[53,103],"integrating":[54],"reinforcement":[55,88,156],"methods":[57],"constrained":[59],"continuous":[60],"spaces.":[62],"We":[63,137],"leverage":[64],"hierarchical":[66],"control":[67],"decompose":[70],"target":[71],"robotic":[72,145],"skills":[73],"into":[74],"higher":[75,104,129],"ranked":[76,87,130],"tasks":[77,146],"(e.":[78],"g.,":[79],"joint":[80],"limits":[81],"and":[82,85,149,161,164],"obstacle":[83],"avoidance)":[84],"lower":[86],"task.":[90],"Safe":[91],"guaranteed":[94],"only":[96],"policies":[98],"prioritized":[105],"constraints.":[106],"Meanwhile":[107],"multiple":[108],"constraint":[109],"phases":[110],"different":[112,143],"operational":[113],"spaces":[114],"are":[115],"constructed":[116],"guide":[118],"exploration.":[121],"Also,":[122],"penalty":[125],"loss":[126],"violating":[128],"accelerate":[133],"procedure.":[136],"have":[138],"evaluated":[139],"our":[140,152],"method":[141,158],"on":[142],"redundant":[144],"simulation":[148],"show":[150],"that":[151],"explore":[160],"learn":[162],"safely":[163],"efficiently.":[165]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}