{"id":"https://openalex.org/W4400080687","doi":"https://doi.org/10.1109/icit58233.2024.10570082","title":"A reinforcement learning based control framework for robot gear assembly with demonstration learning and force feedback","display_name":"A reinforcement learning based control framework for robot gear assembly with demonstration learning and force feedback","publication_year":2024,"publication_date":"2024-03-25","ids":{"openalex":"https://openalex.org/W4400080687","doi":"https://doi.org/10.1109/icit58233.2024.10570082"},"language":"en","primary_location":{"id":"doi:10.1109/icit58233.2024.10570082","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icit58233.2024.10570082","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Industrial Technology (ICIT)","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/A5065215412","display_name":"Wenjie Tang","orcid":"https://orcid.org/0000-0002-9752-4948"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenjie Tang","raw_affiliation_strings":["College of Robotics, Hunan University,ChangSha,China"],"affiliations":[{"raw_affiliation_string":"College of Robotics, Hunan University,ChangSha,China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067854210","display_name":"Yiming Jiang","orcid":"https://orcid.org/0000-0001-5963-2932"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiming Jiang","raw_affiliation_strings":["College of Robotics, Hunan University,ChangSha,China"],"affiliations":[{"raw_affiliation_string":"College of Robotics, Hunan University,ChangSha,China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101850794","display_name":"Chao Zeng","orcid":"https://orcid.org/0000-0003-3648-4644"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Chao Zeng","raw_affiliation_strings":["Universität Hamburg,Department of Informatics,Hamburg,Germany"],"affiliations":[{"raw_affiliation_string":"Universität Hamburg,Department of Informatics,Hamburg,Germany","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100323420","display_name":"Hui Zhang","orcid":"https://orcid.org/0000-0002-1803-3148"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Zhang","raw_affiliation_strings":["College of Robotics, Hunan University,ChangSha,China"],"affiliations":[{"raw_affiliation_string":"College of Robotics, Hunan University,ChangSha,China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084391120","display_name":"Hang Zhong","orcid":"https://orcid.org/0000-0001-5893-5026"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Zhong","raw_affiliation_strings":["College of Robotics, Hunan University,ChangSha,China"],"affiliations":[{"raw_affiliation_string":"College of Robotics, Hunan University,ChangSha,China","institution_ids":["https://openalex.org/I16609230"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5065215412"],"corresponding_institution_ids":["https://openalex.org/I16609230"],"apc_list":null,"apc_paid":null,"fwci":1.0484,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.76061541,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9842000007629395,"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":0.9842000007629395,"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":0.8432018756866455},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6354696750640869},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6143800020217896},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.5250939130783081},{"id":"https://openalex.org/keywords/feedback-control","display_name":"Feedback control","score":0.4988374710083008},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.47695958614349365},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.4400206208229065},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3600226640701294},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.26819339394569397},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.2664111256599426}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8432018756866455},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6354696750640869},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6143800020217896},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.5250939130783081},{"id":"https://openalex.org/C3018651601","wikidata":"https://www.wikidata.org/wiki/Q183635","display_name":"Feedback control","level":2,"score":0.4988374710083008},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.47695958614349365},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.4400206208229065},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3600226640701294},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.26819339394569397},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.2664111256599426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icit58233.2024.10570082","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icit58233.2024.10570082","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Industrial Technology (ICIT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6091940220","display_name":null,"funder_award_id":"62293514,62003136","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1977655452","https://openalex.org/W2082511574","https://openalex.org/W2155007355","https://openalex.org/W2158782408","https://openalex.org/W2280163991","https://openalex.org/W2607198029","https://openalex.org/W2736601468","https://openalex.org/W2741122588","https://openalex.org/W2767050701","https://openalex.org/W2796864868","https://openalex.org/W2898941002","https://openalex.org/W2904246096","https://openalex.org/W2963864421","https://openalex.org/W2968095426","https://openalex.org/W2968268581","https://openalex.org/W2976205474","https://openalex.org/W2990747716","https://openalex.org/W3012366945","https://openalex.org/W3101442004","https://openalex.org/W3127352841","https://openalex.org/W4225014119","https://openalex.org/W4313121131","https://openalex.org/W4316876974","https://openalex.org/W6682849425","https://openalex.org/W6684921986","https://openalex.org/W6695011786","https://openalex.org/W6741002519","https://openalex.org/W6742461812","https://openalex.org/W6764969207"],"related_works":["https://openalex.org/W2930863966","https://openalex.org/W2126211886","https://openalex.org/W3153786280","https://openalex.org/W3127551068","https://openalex.org/W2165180011","https://openalex.org/W3165944253","https://openalex.org/W4220829754","https://openalex.org/W2351343564","https://openalex.org/W2170052867","https://openalex.org/W3119422923"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"(RL)":[2],"has":[3],"found":[4],"extensive":[5],"application":[6],"in":[7,12,32,64,118,134,150],"robotic":[8,68],"manipulation":[9],"tasks,":[10],"particularly":[11],"scenarios":[13],"involving":[14],"contact-rich":[15],"activities":[16],"such":[17],"as":[18],"axis-hole":[19],"assembly":[20,75,138,153],"and":[21,45,51,107,129,145],"spot":[22],"welding.":[23],"However,":[24],"existing":[25],"methodologies":[26],"encounter":[27],"several":[28],"key":[29],"limitations:":[30],"difficulties":[31],"gathering":[33],"real-world":[34,135],"experimental":[35],"data,":[36],"slow":[37],"reward":[38],"convergence":[39],"leading":[40],"to":[41],"suboptimal":[42],"strategy":[43],"performance,":[44],"a":[46,56,79],"significant":[47],"disparity":[48],"between":[49],"simulation":[50,123],"reality.":[52],"This":[53],"paper":[54],"introduces":[55],"novel":[57],"framework":[58,149],"aimed":[59],"at":[60],"over-coming":[61],"these":[62],"limitations":[63],"the":[65,74,95,112,122,126,131,143],"context":[66],"of":[67,147],"gear":[69,136],"assembly.":[70],"Initially,":[71],"we":[72,110],"capture":[73],"trajectory":[76],"executed":[77],"by":[78],"human":[80],"expert":[81,88],"through":[82],"manual":[83],"guidance,":[84],"subsequently":[85],"incorporating":[86],"this":[87],"experience":[89,92],"into":[90],"an":[91],"pool.":[93],"Leveraging":[94],"Deep":[96],"Deterministic":[97],"Policy":[98],"Gradient":[99],"(DDPG)":[100],"algorithm,":[101],"along":[102],"with":[103],"demonstrations,":[104],"force":[105],"feedback,":[106],"domain":[108],"randomization,":[109],"train":[111],"policy":[113],"until":[114],"achieving":[115],"satisfactory":[116],"results":[117,141],"simulation.":[119],"We":[120],"establish":[121],"environment":[124],"within":[125],"MuJoCo":[127],"simulator":[128],"validate":[130],"proposed":[132],"method":[133],"shaft":[137],"tasks.":[139,154],"Experimental":[140],"showcase":[142],"robustness":[144],"efficacy":[146],"our":[148],"successfully":[151],"completing":[152]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}