{"id":"https://openalex.org/W2963940579","doi":"https://doi.org/10.1109/iros.2017.8202244","title":"Deep reinforcement learning for high precision assembly tasks","display_name":"Deep reinforcement learning for high precision assembly tasks","publication_year":2017,"publication_date":"2017-09-01","ids":{"openalex":"https://openalex.org/W2963940579","doi":"https://doi.org/10.1109/iros.2017.8202244","mag":"2963940579"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2017.8202244","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2017.8202244","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5107232188","display_name":"Tadanobu Inoue","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tadanobu Inoue","raw_affiliation_strings":["IBM Research - Tokyo, IBM Japan, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - Tokyo, IBM Japan, Japan","institution_ids":["https://openalex.org/I4210145865"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024150653","display_name":"Giovanni De Magistris","orcid":"https://orcid.org/0000-0002-5040-0884"},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Giovanni De Magistris","raw_affiliation_strings":["IBM Research - Tokyo, IBM Japan, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - Tokyo, IBM Japan, Japan","institution_ids":["https://openalex.org/I4210145865"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101843778","display_name":"Asim Munawar","orcid":"https://orcid.org/0000-0002-9101-9545"},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Asim Munawar","raw_affiliation_strings":["IBM Research - Tokyo, IBM Japan, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - Tokyo, IBM Japan, Japan","institution_ids":["https://openalex.org/I4210145865"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077087802","display_name":"Tsuyoshi Yokoya","orcid":null},"institutions":[{"id":"https://openalex.org/I119487337","display_name":"Yaskawa Electric (Japan)","ror":"https://ror.org/037qwc103","country_code":"JP","type":"company","lineage":["https://openalex.org/I119487337"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tsuyoshi Yokoya","raw_affiliation_strings":["Tsukuba Research Laboratory, Yaskawa electric corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsukuba Research Laboratory, Yaskawa electric corporation, Japan","institution_ids":["https://openalex.org/I119487337"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013412274","display_name":"Ryuki Tachibana","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryuki Tachibana","raw_affiliation_strings":["IBM Research - Tokyo, IBM Japan, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - Tokyo, IBM Japan, Japan","institution_ids":["https://openalex.org/I4210145865"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":18.3665,"has_fulltext":false,"cited_by_count":301,"citation_normalized_percentile":{"value":0.99517294,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"819","last_page":"825"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9998999834060669,"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":0.9998999834060669,"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/T10571","display_name":"Robotic Mechanisms and Dynamics","score":0.9890999794006348,"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":0.9871000051498413,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8321652412414551},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7868160009384155},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7412087321281433},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6844559907913208},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6050939559936523},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5772281885147095},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5469763875007629},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5044249296188354},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.35188984870910645},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16722607612609863}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8321652412414551},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7868160009384155},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7412087321281433},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6844559907913208},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6050939559936523},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5772281885147095},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5469763875007629},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5044249296188354},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.35188984870910645},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16722607612609863},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros.2017.8202244","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2017.8202244","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/W6908809","https://openalex.org/W1757796397","https://openalex.org/W1977655452","https://openalex.org/W1984859415","https://openalex.org/W2096533821","https://openalex.org/W2103261336","https://openalex.org/W2115617434","https://openalex.org/W2121092017","https://openalex.org/W2131119817","https://openalex.org/W2173248099","https://openalex.org/W2201912979","https://openalex.org/W2244849828","https://openalex.org/W2539574638","https://openalex.org/W2553722312","https://openalex.org/W2575705757","https://openalex.org/W2612327946","https://openalex.org/W2747522088","https://openalex.org/W2962736495","https://openalex.org/W2962938178","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W4293864724","https://openalex.org/W4298857966","https://openalex.org/W6637967152","https://openalex.org/W6674304311","https://openalex.org/W6675366449","https://openalex.org/W6677939520","https://openalex.org/W6690960878","https://openalex.org/W6692846177","https://openalex.org/W6697071109"],"related_works":["https://openalex.org/W96612179","https://openalex.org/W2770234245","https://openalex.org/W2566006169","https://openalex.org/W2987774938","https://openalex.org/W4256492088","https://openalex.org/W632915154","https://openalex.org/W4229499248","https://openalex.org/W4378874356","https://openalex.org/W2055733372","https://openalex.org/W2369811061"],"abstract_inverted_index":{"The":[0,85,106],"high":[1],"precision":[2,8],"assembly":[3],"of":[4,12,98,108],"mechanical":[5],"parts":[6],"requires":[7],"that":[9,11],"exceeds":[10],"robots.":[13],"Conventional":[14],"part-mating":[15],"methods":[16],"used":[17],"in":[18],"the":[19,61,82,91,96,103],"current":[20],"manufacturing":[21],"require":[22],"numerous":[23],"parameters":[24],"to":[25,57,89,101],"be":[26],"tediously":[27],"tuned":[28],"before":[29],"deployment.":[30],"We":[31],"show":[32],"how":[33],"a":[34,39,43,48,66,71,99,116],"robot":[35,100,119],"can":[36],"successfully":[37],"perform":[38],"peg-in-hole":[40,83],"task":[41],"with":[42,52,70],"tight":[44],"clearance":[45,73],"through":[46],"training":[47],"recurrent":[49],"neural":[50,86],"network":[51,87],"reinforcement":[53],"learning.":[54],"In":[55],"addition":[56],"reducing":[58],"manual":[59],"effort,":[60],"proposed":[62,110],"method":[63,111],"also":[64],"shows":[65],"better":[67],"fitting":[68],"performance":[69],"tighter":[72],"and":[74,78],"robustness":[75],"against":[76],"positional":[77],"angular":[79],"errors":[80],"for":[81],"task.":[84],"learns":[88],"take":[90],"optimal":[92],"action":[93],"by":[94],"observing":[95],"sensors":[97],"estimate":[102],"system":[104],"state.":[105],"advantages":[107],"our":[109],"are":[112],"validated":[113],"experimentally":[114],"on":[115],"7-axis":[117],"articulated":[118],"arm.":[120]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":28},{"year":2024,"cited_by_count":28},{"year":2023,"cited_by_count":49},{"year":2022,"cited_by_count":43},{"year":2021,"cited_by_count":61},{"year":2020,"cited_by_count":45},{"year":2019,"cited_by_count":31},{"year":2018,"cited_by_count":13},{"year":2017,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}