{"id":"https://openalex.org/W4388642465","doi":"https://doi.org/10.1109/lra.2023.3332556","title":"Investigating Integral Reinforcement Learning to Achieve Asymptotic Stability in Underactuated Mechanical Systems","display_name":"Investigating Integral Reinforcement Learning to Achieve Asymptotic Stability in Underactuated Mechanical Systems","publication_year":2023,"publication_date":"2023-11-13","ids":{"openalex":"https://openalex.org/W4388642465","doi":"https://doi.org/10.1109/lra.2023.3332556"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2023.3332556","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2023.3332556","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-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/A5061127128","display_name":"Babak Salamat","orcid":"https://orcid.org/0000-0001-7262-3264"},"institutions":[{"id":"https://openalex.org/I4210106192","display_name":"Technische Hochschule Ingolstadt","ror":"https://ror.org/02bxzcy64","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210106192"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Babak Salamat","raw_affiliation_strings":["AImotion Institute, Technische Hochschule Ingolstadt, Ingolstadt, Germany"],"raw_orcid":"https://orcid.org/0000-0001-7262-3264","affiliations":[{"raw_affiliation_string":"AImotion Institute, Technische Hochschule Ingolstadt, Ingolstadt, Germany","institution_ids":["https://openalex.org/I4210106192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093255406","display_name":"Daniel Bencic","orcid":"https://orcid.org/0009-0007-3450-0803"},"institutions":[{"id":"https://openalex.org/I4210106192","display_name":"Technische Hochschule Ingolstadt","ror":"https://ror.org/02bxzcy64","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210106192"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Daniel Bencic","raw_affiliation_strings":["AImotion Institute, Technische Hochschule Ingolstadt, Ingolstadt, Germany"],"raw_orcid":"https://orcid.org/0009-0007-3450-0803","affiliations":[{"raw_affiliation_string":"AImotion Institute, Technische Hochschule Ingolstadt, Ingolstadt, Germany","institution_ids":["https://openalex.org/I4210106192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073722017","display_name":"Gerhard Elsbacher","orcid":"https://orcid.org/0000-0002-8297-5033"},"institutions":[{"id":"https://openalex.org/I4210106192","display_name":"Technische Hochschule Ingolstadt","ror":"https://ror.org/02bxzcy64","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210106192"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gerhard Elsbacher","raw_affiliation_strings":["AImotion Institute, Technische Hochschule Ingolstadt, Ingolstadt, Germany"],"raw_orcid":"https://orcid.org/0000-0002-8297-5033","affiliations":[{"raw_affiliation_string":"AImotion Institute, Technische Hochschule Ingolstadt, Ingolstadt, Germany","institution_ids":["https://openalex.org/I4210106192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101727436","display_name":"Christian Seidel","orcid":"https://orcid.org/0009-0001-2584-9698"},"institutions":[{"id":"https://openalex.org/I4210106192","display_name":"Technische Hochschule Ingolstadt","ror":"https://ror.org/02bxzcy64","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210106192"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian Seidel","raw_affiliation_strings":["AImotion Institute, Technische Hochschule Ingolstadt, Ingolstadt, Germany"],"raw_orcid":"https://orcid.org/0009-0001-2584-9698","affiliations":[{"raw_affiliation_string":"AImotion Institute, Technische Hochschule Ingolstadt, Ingolstadt, Germany","institution_ids":["https://openalex.org/I4210106192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046459259","display_name":"Andrea M. Tonello","orcid":"https://orcid.org/0000-0002-9873-2407"},"institutions":[{"id":"https://openalex.org/I4210166741","display_name":"University of Klagenfurt","ror":"https://ror.org/05q9m0937","country_code":"AT","type":"education","lineage":["https://openalex.org/I4210166741"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Andrea M. Tonello","raw_affiliation_strings":["Institute of Networked and Embedded Systems, Alpen-Adria University Klagenfurt, Klagenfurt, Austria"],"raw_orcid":"https://orcid.org/0000-0002-9873-2407","affiliations":[{"raw_affiliation_string":"Institute of Networked and Embedded Systems, Alpen-Adria University Klagenfurt, Klagenfurt, Austria","institution_ids":["https://openalex.org/I4210166741"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8178,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.7327171,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"9","issue":"1","first_page":"191","last_page":"198"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12772","display_name":"Control and Stability of Dynamical Systems","score":0.9970999956130981,"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/T12772","display_name":"Control and Stability of Dynamical Systems","score":0.9970999956130981,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9926999807357788,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9768999814987183,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8377058506011963},{"id":"https://openalex.org/keywords/underactuation","display_name":"Underactuation","score":0.8325868248939514},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.6258493065834045},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5988695025444031},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5766721367835999},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.563069224357605},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.5036985278129578},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.46016594767570496},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.4571627676486969},{"id":"https://openalex.org/keywords/exponential-stability","display_name":"Exponential stability","score":0.41431230306625366},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.41067802906036377},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.36830297112464905},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28587907552719116},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.23093977570533752},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2225598692893982},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.19459819793701172},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.13516831398010254},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09994691610336304},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.060590893030166626}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8377058506011963},{"id":"https://openalex.org/C88337583","wikidata":"https://www.wikidata.org/wiki/Q7883433","display_name":"Underactuation","level":3,"score":0.8325868248939514},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.6258493065834045},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5988695025444031},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5766721367835999},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.563069224357605},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.5036985278129578},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.46016594767570496},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.4571627676486969},{"id":"https://openalex.org/C167964875","wikidata":"https://www.wikidata.org/wiki/Q17011487","display_name":"Exponential stability","level":3,"score":0.41431230306625366},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.41067802906036377},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.36830297112464905},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28587907552719116},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.23093977570533752},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2225598692893982},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.19459819793701172},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.13516831398010254},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09994691610336304},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.060590893030166626},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2023.3332556","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2023.3332556","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.8600000143051147,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W194456869","https://openalex.org/W1578294898","https://openalex.org/W1983523797","https://openalex.org/W1991119064","https://openalex.org/W2077981455","https://openalex.org/W2081727243","https://openalex.org/W2102263452","https://openalex.org/W2125968092","https://openalex.org/W2134024695","https://openalex.org/W2154077222","https://openalex.org/W2189990206","https://openalex.org/W2310008819","https://openalex.org/W2321292752","https://openalex.org/W2571295508","https://openalex.org/W2772589676","https://openalex.org/W3105444552","https://openalex.org/W3111327451","https://openalex.org/W3120441334","https://openalex.org/W3184620837","https://openalex.org/W3200299012","https://openalex.org/W4225492787","https://openalex.org/W4226143977","https://openalex.org/W4231367092","https://openalex.org/W4240790602","https://openalex.org/W4294732341","https://openalex.org/W4322576803","https://openalex.org/W4387129583"],"related_works":["https://openalex.org/W587013945","https://openalex.org/W4288862394","https://openalex.org/W1485310626","https://openalex.org/W4292915238","https://openalex.org/W4285553839","https://openalex.org/W3011477119","https://openalex.org/W2371440471","https://openalex.org/W2075135955","https://openalex.org/W3135136999","https://openalex.org/W4293094921"],"abstract_inverted_index":{"This":[0],"letter":[1],"introduces":[2],"an":[3,36,52],"innovative":[4],"data-driven":[5],"integral":[6],"reinforcement":[7],"learning":[8,31],"(IRL)":[9],"algorithm":[10],"for":[11],"the":[12,32,65,86,89,99,103],"control":[13,104],"of":[14,17,35,88,102],"a":[15,23,44,69],"class":[16],"underactuated":[18,37],"mechanical":[19],"systems.":[20],"We":[21],"propose":[22,62],"novel":[24],"value":[25,66],"function":[26,67],"that":[27,55],"allows":[28],"shaping":[29],"and":[30,39,75,94],"potential":[33,47],"energy":[34],"system":[38],"to":[40,43,63],"drive":[41],"it":[42],"desired":[45],"closed-loop":[46],"energy.":[48],"Consequently,":[49],"we":[50,61,84],"derive":[51],"actor-control":[53],"policy":[54],"ensures":[56],"asymptotic":[57],"stability.":[58],"In":[59],"addition,":[60],"parameterize":[64],"with":[68],"multi-layered":[70],"perceptron":[71],"(with":[72],"0,":[73],"1,":[74],"2":[76],"hidden":[77],"layers),":[78],"exploring":[79],"various":[80],"parameter":[81],"configurations.":[82],"Eventually,":[83],"assess":[85],"performance":[87],"proposed":[90],"IRL":[91],"through":[92],"simulations":[93],"experimental":[95],"results,":[96],"thus":[97],"confirming":[98],"practical":[100],"effectiveness":[101],"design":[105],"approach.":[106]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}