{"id":"https://openalex.org/W4403534818","doi":"https://doi.org/10.1109/codit62066.2024.10708424","title":"Model-based Reinforcement Learning for Sim-to-Real Transfer in Robotics using HTM neural networks","display_name":"Model-based Reinforcement Learning for Sim-to-Real Transfer in Robotics using HTM neural networks","publication_year":2024,"publication_date":"2024-07-01","ids":{"openalex":"https://openalex.org/W4403534818","doi":"https://doi.org/10.1109/codit62066.2024.10708424"},"language":"en","primary_location":{"id":"doi:10.1109/codit62066.2024.10708424","is_oa":false,"landing_page_url":"https://doi.org/10.1109/codit62066.2024.10708424","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 10th International Conference on Control, Decision and Information Technologies (CoDIT)","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/A5027199748","display_name":"Mochammad Rizky Diprasetya","orcid":"https://orcid.org/0000-0001-5879-4657"},"institutions":[{"id":"https://openalex.org/I3130920692","display_name":"South Westphalia University of Applied Sciences","ror":"https://ror.org/04t5phd24","country_code":"DE","type":"education","lineage":["https://openalex.org/I3130920692"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"M. R. Diprasetya","raw_affiliation_strings":["South Westphalia University of Applied Sciences,Department of Automation Technology and Learning Systems,Soest,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South Westphalia University of Applied Sciences,Department of Automation Technology and Learning Systems,Soest,Germany","institution_ids":["https://openalex.org/I3130920692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099029646","display_name":"Ali Nafih Pullani","orcid":null},"institutions":[{"id":"https://openalex.org/I3130920692","display_name":"South Westphalia University of Applied Sciences","ror":"https://ror.org/04t5phd24","country_code":"DE","type":"education","lineage":["https://openalex.org/I3130920692"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"A. N. Pullani","raw_affiliation_strings":["South Westphalia University of Applied Sciences,Department of Automation Technology and Learning Systems,Soest,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South Westphalia University of Applied Sciences,Department of Automation Technology and Learning Systems,Soest,Germany","institution_ids":["https://openalex.org/I3130920692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025397538","display_name":"Andreas Schwung","orcid":"https://orcid.org/0000-0001-8405-0977"},"institutions":[{"id":"https://openalex.org/I3130920692","display_name":"South Westphalia University of Applied Sciences","ror":"https://ror.org/04t5phd24","country_code":"DE","type":"education","lineage":["https://openalex.org/I3130920692"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"A. Schwung","raw_affiliation_strings":["South Westphalia University of Applied Sciences,Department of Automation Technology and Learning Systems,Soest,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South Westphalia University of Applied Sciences,Department of Automation Technology and Learning Systems,Soest,Germany","institution_ids":["https://openalex.org/I3130920692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002731863","display_name":"Dorothea Schwung","orcid":null},"institutions":[{"id":"https://openalex.org/I83041830","display_name":"Deggendorf Institute of Technology","ror":"https://ror.org/02kw5st29","country_code":"DE","type":"education","lineage":["https://openalex.org/I83041830"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"D. Schwung","raw_affiliation_strings":["Hochschule Düsseldorf University of Applied Sciences,Department of Artificial Intelligence and Data Science,Düsseldorf,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hochschule Düsseldorf University of Applied Sciences,Department of Artificial Intelligence and Data Science,Düsseldorf,Germany","institution_ids":["https://openalex.org/I83041830"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"97","issue":null,"first_page":"43","last_page":"48"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9136000275611877,"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":0.9136000275611877,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9014999866485596,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8137858510017395},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7222647666931152},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.7160646915435791},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6515302658081055},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.6425904035568237},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5547849535942078},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4396991729736328},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4281075596809387}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8137858510017395},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7222647666931152},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.7160646915435791},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6515302658081055},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.6425904035568237},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5547849535942078},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4396991729736328},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4281075596809387}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/codit62066.2024.10708424","is_oa":false,"landing_page_url":"https://doi.org/10.1109/codit62066.2024.10708424","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 10th International Conference on Control, Decision and Information Technologies (CoDIT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1540685400","https://openalex.org/W1979071892","https://openalex.org/W1988071341","https://openalex.org/W2045012281","https://openalex.org/W2139053308","https://openalex.org/W2158782408","https://openalex.org/W2575705757","https://openalex.org/W2736601468","https://openalex.org/W2766447205","https://openalex.org/W2767050701","https://openalex.org/W2768255130","https://openalex.org/W2792514232","https://openalex.org/W2920835151","https://openalex.org/W2963293747","https://openalex.org/W3003902235","https://openalex.org/W3008535267","https://openalex.org/W3101103779","https://openalex.org/W3101442004","https://openalex.org/W3126176913","https://openalex.org/W3132082252","https://openalex.org/W3132557532","https://openalex.org/W4249244053","https://openalex.org/W4313564071","https://openalex.org/W4383108554","https://openalex.org/W6632235069","https://openalex.org/W6696324988","https://openalex.org/W6741002519","https://openalex.org/W6749146968","https://openalex.org/W6760474688","https://openalex.org/W6785713589"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571"],"abstract_inverted_index":{"In":[0],"this":[1],"work":[2],"we":[3,22],"propose":[4,23],"a":[5,26,35,125],"novel":[6],"approach":[7,63],"based":[8],"on":[9,69],"model-based":[10],"Reinforcement":[11],"Learning":[12],"(RL)":[13],"for":[14,94],"the":[15,40,45,50,62,74,77,106,109,116,121],"sim-to-real":[16],"transfer":[17],"of":[18,49,76,108],"industrial":[19,67],"robots.":[20],"Specifically,":[21],"to":[24,65,96],"employ":[25],"recently":[27],"developed":[28],"kinematics-informed,":[29],"modular":[30],"neural":[31],"network":[32],"serving":[33],"as":[34],"learnable":[36],"environment":[37],"model":[38,42,52],"within":[39,73,120],"world":[41,51,136],"framework.":[43],"Using":[44,84],"kinematics-informed":[46],"model,":[47],"training":[48,90,98,115],"is":[53],"made":[54],"more":[55],"efficient":[56],"resulting":[57],"in":[58,124,131],"faster":[59],"training.":[60],"Furthermore,":[61],"allows":[64,93],"train":[66],"robots":[68],"specific":[70],"tasks":[71],"solely":[72,119],"simulation":[75,133],"system":[78],"thereby":[79],"saving":[80],"time":[81],"and":[82,88,92,134],"energy-consumption.":[83],"simulations":[85],"ensures":[86],"safe":[87],"controlled":[89],"implementation":[91],"parallelization":[95],"increase":[97],"speed.":[99],"We":[100,112],"conduct":[101],"various":[102],"experiments":[103],"which":[104],"underline":[105],"effectiveness":[107],"proposed":[110],"method.":[111],"show":[113],"that":[114],"RL":[117],"algorithm":[118],"simulation,":[122],"results":[123],"hundred":[126],"percent":[127],"task":[128],"completion":[129],"rate":[130],"both":[132],"real":[135],"experiments.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}