{"id":"https://openalex.org/W4383109037","doi":"https://doi.org/10.1109/icra48891.2023.10161548","title":"Safe Reinforcement Learning of Dynamic High-Dimensional Robotic Tasks: Navigation, Manipulation, Interaction","display_name":"Safe Reinforcement Learning of Dynamic High-Dimensional Robotic Tasks: Navigation, Manipulation, Interaction","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383109037","doi":"https://doi.org/10.1109/icra48891.2023.10161548"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10161548","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10161548","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 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/A5036597033","display_name":"Puze Liu","orcid":"https://orcid.org/0000-0001-6887-7704"},"institutions":[{"id":"https://openalex.org/I4210156583","display_name":"Laboratoire d'Informatique de Paris-Nord","ror":"https://ror.org/05g1zjw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I4210091279","https://openalex.org/I4210156583","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Puze Liu","raw_affiliation_strings":["Technical University Darmstadt,Computer Science Department","Computer Science Department, Technical University Darmstadt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University Darmstadt,Computer Science Department","institution_ids":["https://openalex.org/I4210156583"]},{"raw_affiliation_string":"Computer Science Department, Technical University Darmstadt","institution_ids":["https://openalex.org/I4210156583"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100440991","display_name":"Kuo Zhang","orcid":"https://orcid.org/0000-0002-2364-6790"},"institutions":[{"id":"https://openalex.org/I4210156583","display_name":"Laboratoire d'Informatique de Paris-Nord","ror":"https://ror.org/05g1zjw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I4210091279","https://openalex.org/I4210156583","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Kuo Zhang","raw_affiliation_strings":["Technical University Darmstadt,Computer Science Department","Computer Science Department, Technical University Darmstadt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University Darmstadt,Computer Science Department","institution_ids":["https://openalex.org/I4210156583"]},{"raw_affiliation_string":"Computer Science Department, Technical University Darmstadt","institution_ids":["https://openalex.org/I4210156583"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001304610","display_name":"Davide Tateo","orcid":"https://orcid.org/0000-0002-7193-923X"},"institutions":[{"id":"https://openalex.org/I4210156583","display_name":"Laboratoire d'Informatique de Paris-Nord","ror":"https://ror.org/05g1zjw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I4210091279","https://openalex.org/I4210156583","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Davide Tateo","raw_affiliation_strings":["Technical University Darmstadt,Computer Science Department","Computer Science Department, Technical University Darmstadt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University Darmstadt,Computer Science Department","institution_ids":["https://openalex.org/I4210156583"]},{"raw_affiliation_string":"Computer Science Department, Technical University Darmstadt","institution_ids":["https://openalex.org/I4210156583"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023965680","display_name":"Snehal Jauhri","orcid":"https://orcid.org/0000-0001-9134-3989"},"institutions":[{"id":"https://openalex.org/I4210156583","display_name":"Laboratoire d'Informatique de Paris-Nord","ror":"https://ror.org/05g1zjw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I4210091279","https://openalex.org/I4210156583","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Snehal Jauhri","raw_affiliation_strings":["Technical University Darmstadt,Computer Science Department","Computer Science Department, Technical University Darmstadt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University Darmstadt,Computer Science Department","institution_ids":["https://openalex.org/I4210156583"]},{"raw_affiliation_string":"Computer Science Department, Technical University Darmstadt","institution_ids":["https://openalex.org/I4210156583"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076053801","display_name":"Zhiyuan Hu","orcid":"https://orcid.org/0000-0003-2212-0268"},"institutions":[{"id":"https://openalex.org/I4210156583","display_name":"Laboratoire d'Informatique de Paris-Nord","ror":"https://ror.org/05g1zjw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I4210091279","https://openalex.org/I4210156583","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Zhiyuan Hu","raw_affiliation_strings":["Technical University Darmstadt,Computer Science Department","Computer Science Department, Technical University Darmstadt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University Darmstadt,Computer Science Department","institution_ids":["https://openalex.org/I4210156583"]},{"raw_affiliation_string":"Computer Science Department, Technical University Darmstadt","institution_ids":["https://openalex.org/I4210156583"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071367253","display_name":"Jan Peters","orcid":"https://orcid.org/0000-0002-5266-8091"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]},{"id":"https://openalex.org/I4210122262","display_name":"Institut des Sciences Cognitives Marc Jeannerod","ror":"https://ror.org/02he5dz58","country_code":"FR","type":"facility","lineage":["https://openalex.org/I100532134","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I203339264","https://openalex.org/I4210096427","https://openalex.org/I4210122262"]},{"id":"https://openalex.org/I4210156583","display_name":"Laboratoire d'Informatique de Paris-Nord","ror":"https://ror.org/05g1zjw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I4210091279","https://openalex.org/I4210156583","https://openalex.org/I4210159245"]}],"countries":["DE","FR"],"is_corresponding":false,"raw_author_name":"Jan Peters","raw_affiliation_strings":["Technical University Darmstadt,Computer Science Department","Centre for Cognitive Science","Computer Science Department, Technical University Darmstadt","Hessian.AI","Research Department: Systems AI for Robot Learning, German Research Center for AI (DFKI)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University Darmstadt,Computer Science Department","institution_ids":["https://openalex.org/I4210156583"]},{"raw_affiliation_string":"Centre for Cognitive Science","institution_ids":["https://openalex.org/I4210122262"]},{"raw_affiliation_string":"Computer Science Department, Technical University Darmstadt","institution_ids":["https://openalex.org/I4210156583"]},{"raw_affiliation_string":"Hessian.AI","institution_ids":[]},{"raw_affiliation_string":"Research Department: Systems AI for Robot Learning, German Research Center for AI (DFKI)","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026055366","display_name":"Georgia Chalvatzaki","orcid":"https://orcid.org/0000-0002-5055-199X"},"institutions":[{"id":"https://openalex.org/I4210156583","display_name":"Laboratoire d'Informatique de Paris-Nord","ror":"https://ror.org/05g1zjw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I4210091279","https://openalex.org/I4210156583","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Georgia Chalvatzaki","raw_affiliation_strings":["Technical University Darmstadt,Computer Science Department","Computer Science Department, Technical University Darmstadt","Hessian.AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University Darmstadt,Computer Science Department","institution_ids":["https://openalex.org/I4210156583"]},{"raw_affiliation_string":"Computer Science Department, Technical University Darmstadt","institution_ids":["https://openalex.org/I4210156583"]},{"raw_affiliation_string":"Hessian.AI","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9449","last_page":"9456"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9994000196456909,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9994000196456909,"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":0.9987999796867371,"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":0.994700014591217,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.804537296295166},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.693390429019928},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.6319189071655273},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5956604480743408},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5895695686340332},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.53177809715271},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5137652158737183},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.42057472467422485},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4130863547325134},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14243781566619873},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.1234351396560669}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.804537296295166},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.693390429019928},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6319189071655273},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5956604480743408},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5895695686340332},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.53177809715271},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5137652158737183},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.42057472467422485},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4130863547325134},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14243781566619873},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.1234351396560669},{"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/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48891.2023.10161548","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10161548","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3147430267","display_name":null,"funder_award_id":"201908080039","funder_id":"https://openalex.org/F4320322725","funder_display_name":"China Scholarship Council"}],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":75,"referenced_works":["https://openalex.org/W15411808","https://openalex.org/W1840625103","https://openalex.org/W1967181149","https://openalex.org/W1967554269","https://openalex.org/W2027579135","https://openalex.org/W2053572490","https://openalex.org/W2069624410","https://openalex.org/W2082227348","https://openalex.org/W2208391220","https://openalex.org/W2586067474","https://openalex.org/W2784465508","https://openalex.org/W2788084076","https://openalex.org/W2804791273","https://openalex.org/W2892521964","https://openalex.org/W2904246096","https://openalex.org/W2913300629","https://openalex.org/W2963017537","https://openalex.org/W2963293747","https://openalex.org/W2963525569","https://openalex.org/W2963575966","https://openalex.org/W2963627347","https://openalex.org/W2966735560","https://openalex.org/W2968104655","https://openalex.org/W2968547875","https://openalex.org/W2968945909","https://openalex.org/W2992833799","https://openalex.org/W2995484204","https://openalex.org/W2996196387","https://openalex.org/W2998544442","https://openalex.org/W2998619042","https://openalex.org/W3008953696","https://openalex.org/W3011042361","https://openalex.org/W3090211586","https://openalex.org/W3093169645","https://openalex.org/W3126321819","https://openalex.org/W3127916076","https://openalex.org/W3135301907","https://openalex.org/W3150718622","https://openalex.org/W3194569790","https://openalex.org/W3195968524","https://openalex.org/W3204691825","https://openalex.org/W3205212549","https://openalex.org/W4211202104","https://openalex.org/W4221161370","https://openalex.org/W4226355781","https://openalex.org/W4285102237","https://openalex.org/W4285102519","https://openalex.org/W4285233190","https://openalex.org/W4287725923","https://openalex.org/W4293545785","https://openalex.org/W4294555834","https://openalex.org/W4294562617","https://openalex.org/W4297780563","https://openalex.org/W4297799385","https://openalex.org/W4312660220","https://openalex.org/W4312817202","https://openalex.org/W4313196885","https://openalex.org/W6600644339","https://openalex.org/W6682367392","https://openalex.org/W6683149736","https://openalex.org/W6733118196","https://openalex.org/W6737893269","https://openalex.org/W6738483526","https://openalex.org/W6747790125","https://openalex.org/W6751535212","https://openalex.org/W6751725685","https://openalex.org/W6757592117","https://openalex.org/W6758924645","https://openalex.org/W6772100842","https://openalex.org/W6774406872","https://openalex.org/W6780587392","https://openalex.org/W6801971982","https://openalex.org/W6809656622","https://openalex.org/W6811221485","https://openalex.org/W7018863775"],"related_works":["https://openalex.org/W96612179","https://openalex.org/W2770234245","https://openalex.org/W2566006169","https://openalex.org/W2987774938","https://openalex.org/W632915154","https://openalex.org/W4229499248","https://openalex.org/W4378874356","https://openalex.org/W2055733372","https://openalex.org/W2369811061","https://openalex.org/W3089997100"],"abstract_inverted_index":{"Safety":[0],"is":[1,34],"a":[2,38,43,49,90,143],"fundamental":[3],"property":[4],"for":[5,55,76],"the":[6,22,26,59,63,69,73,110,131],"real-world":[7,136],"deployment":[8,137],"of":[9,52,62,72,93,112,138],"robotic":[10,56,94,113],"platforms.":[11],"Any":[12],"control":[13],"policy":[14],"should":[15],"avoid":[16],"dangerous":[17],"actions":[18],"that":[19,66,102],"could":[20],"harm":[21],"environment,":[23],"humans,":[24],"or":[25],"robot":[27],"itself.":[28],"In":[29],"reinforcement":[30],"learning":[31],"(RL),":[32],"safety":[33,79,100],"crucial":[35],"when":[36],"exploring":[37],"new":[39,44,50],"environment":[40],"to":[41,85,89,98],"learn":[42],"skill.":[45],"This":[46],"paper":[47],"introduces":[48],"formulation":[51],"safe":[53,135],"exploration":[54],"RL":[57,74],"in":[58,109,121,151],"tangent":[60],"space":[61,71],"constraint":[64],"manifold":[65],"effectively":[67],"transforms":[68],"action":[70],"agent":[75],"always":[77],"respecting":[78],"constraints":[80,101],"locally.":[81],"We":[82,133],"show":[83,134],"how":[84,97],"apply":[86],"this":[87],"approach":[88,117],"wide":[91],"range":[92],"platforms":[95],"and":[96,124,153],"define":[99],"represent":[103],"dynamic":[104,125],"articulated":[105],"objects":[106],"like":[107],"humans":[108],"context":[111],"RL.":[114],"Our":[115],"proposed":[116],"achieves":[118],"state-of-the-art":[119],"performance":[120,150],"simulated":[122],"high-dimensional":[123],"tasks":[126],"while":[127],"avoiding":[128],"collisions":[129],"with":[130],"environment.":[132],"our":[139],"learned":[140],"controller":[141],"on":[142],"<tex":[144],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[145],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\text{TIAGo}++$</tex>":[146],"robot,":[147],"achieving":[148],"remarkable":[149],"manipulation":[152],"human-robot":[154],"interaction":[155],"tasks.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":4}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}
