{"id":"https://openalex.org/W3195288600","doi":"https://doi.org/10.1109/aim46487.2021.9517356","title":"Towards Real-World Force-Sensitive Robotic Assembly through Deep Reinforcement Learning in Simulations","display_name":"Towards Real-World Force-Sensitive Robotic Assembly through Deep Reinforcement Learning in Simulations","publication_year":2021,"publication_date":"2021-07-12","ids":{"openalex":"https://openalex.org/W3195288600","doi":"https://doi.org/10.1109/aim46487.2021.9517356","mag":"3195288600"},"language":"en","primary_location":{"id":"doi:10.1109/aim46487.2021.9517356","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aim46487.2021.9517356","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM)","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/A5069879139","display_name":"Marius Hebecker","orcid":null},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Marius Hebecker","raw_affiliation_strings":["Chair Industry Grade Networks and Clouds, Technische Universit\u00e4t Berlin, Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"Chair Industry Grade Networks and Clouds, Technische Universit\u00e4t Berlin, Berlin, Germany","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002499102","display_name":"Jens Lambrecht","orcid":"https://orcid.org/0000-0002-1017-9548"},"institutions":[{"id":"https://openalex.org/I4577782","display_name":"Technische Universit\u00e4t Berlin","ror":"https://ror.org/03v4gjf40","country_code":"DE","type":"education","lineage":["https://openalex.org/I4577782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jens Lambrecht","raw_affiliation_strings":["Chair Industry Grade Networks and Clouds, Technische Universit\u00e4t Berlin, Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"Chair Industry Grade Networks and Clouds, Technische Universit\u00e4t Berlin, Berlin, Germany","institution_ids":["https://openalex.org/I4577782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016551376","display_name":"Markus Schmitz","orcid":"https://orcid.org/0000-0002-6450-4502"},"institutions":[{"id":"https://openalex.org/I1283382300","display_name":"BMW (Germany)","ror":"https://ror.org/05vs9tj88","country_code":"DE","type":"company","lineage":["https://openalex.org/I1283382300","https://openalex.org/I4210156768"]},{"id":"https://openalex.org/I4210156768","display_name":"BMW Group (Germany)","ror":"https://ror.org/044kkbh92","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210156768"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Markus Schmitz","raw_affiliation_strings":["BMW Group and the Chair of IT-Management, FAU Erlangen-N\u00fcrnberg, N\u00fcrnberg, Germany"],"affiliations":[{"raw_affiliation_string":"BMW Group and the Chair of IT-Management, FAU Erlangen-N\u00fcrnberg, N\u00fcrnberg, Germany","institution_ids":["https://openalex.org/I1283382300","https://openalex.org/I4210156768"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5069879139"],"corresponding_institution_ids":["https://openalex.org/I4577782"],"apc_list":null,"apc_paid":null,"fwci":1.5107,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.82275258,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1045","last_page":"1051"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9968000054359436,"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/T11159","display_name":"Manufacturing Process and Optimization","score":0.9789999723434448,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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":0.8608521819114685},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.7384182810783386},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6683763265609741},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6406927108764648},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5605334043502808},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5456803441047668},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.501950740814209},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4803125262260437},{"id":"https://openalex.org/keywords/grippers","display_name":"Grippers","score":0.4528258442878723},{"id":"https://openalex.org/keywords/robotic-arm","display_name":"Robotic arm","score":0.42320170998573303},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4219202399253845},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.36834847927093506},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.3680502772331238},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3631601929664612},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.20375794172286987},{"id":"https://openalex.org/keywords/mechanical-engineering","display_name":"Mechanical engineering","score":0.10424330830574036}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8608521819114685},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.7384182810783386},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6683763265609741},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6406927108764648},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5605334043502808},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5456803441047668},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.501950740814209},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4803125262260437},{"id":"https://openalex.org/C2775960376","wikidata":"https://www.wikidata.org/wiki/Q1435859","display_name":"Grippers","level":2,"score":0.4528258442878723},{"id":"https://openalex.org/C150415221","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic arm","level":2,"score":0.42320170998573303},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4219202399253845},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.36834847927093506},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.3680502772331238},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3631601929664612},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.20375794172286987},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.10424330830574036},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"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/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/aim46487.2021.9517356","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aim46487.2021.9517356","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W130216483","https://openalex.org/W1988071341","https://openalex.org/W2030363462","https://openalex.org/W2034477801","https://openalex.org/W2064675550","https://openalex.org/W2112036188","https://openalex.org/W2112474089","https://openalex.org/W2133932631","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2171080843","https://openalex.org/W2173248099","https://openalex.org/W2257979135","https://openalex.org/W2291973609","https://openalex.org/W2736601468","https://openalex.org/W2767050701","https://openalex.org/W2779040504","https://openalex.org/W2963864421","https://openalex.org/W2963940579","https://openalex.org/W2964335069","https://openalex.org/W2967466692","https://openalex.org/W2981030070","https://openalex.org/W3007745042","https://openalex.org/W3012366945","https://openalex.org/W3013146177","https://openalex.org/W3046809911","https://openalex.org/W3081200565","https://openalex.org/W3091957856","https://openalex.org/W3101442004","https://openalex.org/W3101875589","https://openalex.org/W3102870931","https://openalex.org/W3130451601","https://openalex.org/W3132082252","https://openalex.org/W4287824211","https://openalex.org/W6741002519","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W2357124094","https://openalex.org/W2387399993","https://openalex.org/W2389739210","https://openalex.org/W2348924972","https://openalex.org/W2365736347","https://openalex.org/W2047454415","https://openalex.org/W2070040999","https://openalex.org/W2387293848","https://openalex.org/W3121791438","https://openalex.org/W2250140200"],"abstract_inverted_index":{"In":[0],"manufacturing":[1],"industries,":[2],"vast":[3],"potential":[4],"exists":[5],"in":[6,45,145],"regards":[7],"to":[8,28,86,134,165,177],"the":[9,22,30,58,88,106,110,117,120,154,158,163,166],"adaptability":[10],"of":[11,24,32,57,112,151,153],"automated":[12],"systems":[13],"through":[14,68,105],"efficient":[15],"robotic":[16,63],"skill":[17],"acquisition.":[18],"This":[19],"paper":[20],"examines":[21],"use":[23,43,53],"deep":[25,70],"reinforcement":[26,71],"learning":[27,72],"automate":[29],"process":[31],"contact":[33],"rich":[34],"compliant":[35,180],"assembly.":[36,47],"Thereby,":[37],"we":[38,52,80,115,170],"consider":[39],"an":[40],"exemplary":[41],"real-world":[42],"case":[44],"car":[46],"To":[48],"obtain":[49,125,178],"training":[50,98],"data,":[51],"a":[54,62,69,82],"simulated":[55,94],"representation":[56],"production":[59],"system":[60,84],"comprising":[61],"arm":[64],"which":[65,103,131],"is":[66,175],"controlled":[67],"agent":[73],"trained":[74],"with":[75,148],"proximal":[76],"policy":[77],"optimization.":[78],"Furthermore,":[79],"conduct":[81],"basic":[83],"analysis":[85],"improve":[87],"similarity":[89],"between":[90],"our":[91],"physical":[92,121,167],"and":[93,99,109,157],"environments.":[95,136],"After":[96],"iteratively":[97],"evaluating":[100],"different":[101],"models,":[102],"distinguish":[104],"reward":[107],"design":[108],"grade":[111],"environment":[113],"variation,":[114],"validate":[116],"results":[118],"on":[119],"hardware.":[122],"We":[123],"successfully":[124],"agents":[126],"that":[127,172],"generate":[128],"expedient":[129],"trajectories,":[130],"can":[132,142],"generalize":[133],"changing":[135],"Success":[137],"rates":[138],"clearly":[139],"above":[140],"90%":[141],"be":[143],"achieved":[144],"simulation":[146],"even":[147],"high":[149],"grades":[150],"variation":[152],"target":[155],"position":[156],"parts\u2019":[159],"surface":[160],"friction.":[161],"For":[162],"transfer":[164],"assembly":[168],"system,":[169],"conclude":[171],"further":[173],"optimization":[174],"necessary":[176],"truly":[179],"behavior.":[181]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}