{"id":"https://openalex.org/W3104414074","doi":"https://doi.org/10.1109/iros51168.2021.9636477","title":"Joint Space Control via Deep Reinforcement Learning","display_name":"Joint Space Control via Deep Reinforcement Learning","publication_year":2021,"publication_date":"2021-09-27","ids":{"openalex":"https://openalex.org/W3104414074","doi":"https://doi.org/10.1109/iros51168.2021.9636477","mag":"3104414074"},"language":"en","primary_location":{"id":"doi:10.1109/iros51168.2021.9636477","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros51168.2021.9636477","pdf_url":null,"source":{"id":"https://openalex.org/S4363607734","display_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2011.06332","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073584166","display_name":"Visak Kumar","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Visak Kumar","raw_affiliation_strings":["Georgia Tech","NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Tech","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046670804","display_name":"David Hoeller","orcid":"https://orcid.org/0000-0001-8010-9011"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Hoeller","raw_affiliation_strings":["Georgia Tech","NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Tech","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053446613","display_name":"Balakumar Sundaralingam","orcid":"https://orcid.org/0000-0003-3106-4755"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Balakumar Sundaralingam","raw_affiliation_strings":["Georgia Tech","NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Tech","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052530128","display_name":"Jonathan Tremblay","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan Tremblay","raw_affiliation_strings":["Georgia Tech","NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Tech","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040617006","display_name":"Stan Birchfield","orcid":"https://orcid.org/0000-0001-7366-2441"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stan Birchfield","raw_affiliation_strings":["Georgia Tech","NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Tech","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3619","last_page":"3626"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9923999905586243,"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/T11023","display_name":"Prosthetics and Rehabilitation Robotics","score":0.9915000200271606,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/computer-science","display_name":"Computer science","score":0.7199744582176208},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.6978005766868591},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6393398642539978},{"id":"https://openalex.org/keywords/inverse-kinematics","display_name":"Inverse kinematics","score":0.6082343459129333},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5651304721832275},{"id":"https://openalex.org/keywords/kinematics","display_name":"Kinematics","score":0.5145217776298523},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5079041123390198},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5029959082603455},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.45257917046546936},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4452569782733917},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4043448269367218},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.2770875096321106},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12314280867576599}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7199744582176208},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6978005766868591},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6393398642539978},{"id":"https://openalex.org/C17816587","wikidata":"https://www.wikidata.org/wiki/Q1501872","display_name":"Inverse kinematics","level":3,"score":0.6082343459129333},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5651304721832275},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.5145217776298523},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5079041123390198},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5029959082603455},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.45257917046546936},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4452569782733917},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4043448269367218},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2770875096321106},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12314280867576599},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/iros51168.2021.9636477","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros51168.2021.9636477","pdf_url":null,"source":{"id":"https://openalex.org/S4363607734","display_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2011.06332","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.06332","pdf_url":"https://arxiv.org/pdf/2011.06332","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3104414074","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2011.06332","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2011.06332","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2011.06332","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2011.06332","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.06332","pdf_url":"https://arxiv.org/pdf/2011.06332","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3104414074.pdf","grobid_xml":"https://content.openalex.org/works/W3104414074.grobid-xml"},"referenced_works_count":72,"referenced_works":["https://openalex.org/W1596951786","https://openalex.org/W2007347635","https://openalex.org/W2101524054","https://openalex.org/W2112474089","https://openalex.org/W2112783345","https://openalex.org/W2117280091","https://openalex.org/W2132558143","https://openalex.org/W2132984949","https://openalex.org/W2134159355","https://openalex.org/W2148330858","https://openalex.org/W2156689847","https://openalex.org/W2160863137","https://openalex.org/W2164032318","https://openalex.org/W2168921921","https://openalex.org/W2180150039","https://openalex.org/W2207061578","https://openalex.org/W2296073425","https://openalex.org/W2560609797","https://openalex.org/W2604698059","https://openalex.org/W2736601468","https://openalex.org/W2782876516","https://openalex.org/W2783192199","https://openalex.org/W2796290181","https://openalex.org/W2890803796","https://openalex.org/W2910787482","https://openalex.org/W2911087563","https://openalex.org/W2926516160","https://openalex.org/W2949924544","https://openalex.org/W2963121255","https://openalex.org/W2963276406","https://openalex.org/W2963311874","https://openalex.org/W2963484919","https://openalex.org/W2963641140","https://openalex.org/W2963713397","https://openalex.org/W2964036701","https://openalex.org/W2964161785","https://openalex.org/W2968095426","https://openalex.org/W2968116426","https://openalex.org/W2968945909","https://openalex.org/W2972758308","https://openalex.org/W2973930579","https://openalex.org/W2984756091","https://openalex.org/W3003629310","https://openalex.org/W3003669699","https://openalex.org/W3005431655","https://openalex.org/W3027372030","https://openalex.org/W3038245394","https://openalex.org/W3040707741","https://openalex.org/W3085438811","https://openalex.org/W3091444023","https://openalex.org/W3091552533","https://openalex.org/W3098499184","https://openalex.org/W3110059731","https://openalex.org/W6677118717","https://openalex.org/W6679390333","https://openalex.org/W6682849425","https://openalex.org/W6704571135","https://openalex.org/W6739778489","https://openalex.org/W6741002519","https://openalex.org/W6741302124","https://openalex.org/W6746914971","https://openalex.org/W6748012927","https://openalex.org/W6748202546","https://openalex.org/W6753243525","https://openalex.org/W6754615820","https://openalex.org/W6756742327","https://openalex.org/W6760278398","https://openalex.org/W6763422710","https://openalex.org/W6768513474","https://openalex.org/W6775683342","https://openalex.org/W6780559895","https://openalex.org/W6787124472"],"related_works":["https://openalex.org/W2521863123","https://openalex.org/W2997727809","https://openalex.org/W2056157338","https://openalex.org/W3207398607","https://openalex.org/W1550146030","https://openalex.org/W2785314333","https://openalex.org/W2054679891","https://openalex.org/W3111847214","https://openalex.org/W2032845773","https://openalex.org/W2921000986","https://openalex.org/W2168921921","https://openalex.org/W3152883941","https://openalex.org/W2275877455","https://openalex.org/W3194733831","https://openalex.org/W2785030475","https://openalex.org/W114497497","https://openalex.org/W2890728188","https://openalex.org/W2581351641","https://openalex.org/W3007715492","https://openalex.org/W2029105483"],"abstract_inverted_index":{"The":[0,80],"dominant":[1],"way":[2],"to":[3,44,49,61,85,92,125],"control":[4],"a":[5,22,109,137],"robot":[6,111],"manipulator":[7],"uses":[8],"hand-crafted":[9],"differential":[10,30],"equations":[11,31],"leveraging":[12],"some":[13],"form":[14],"of":[15,57,115,140],"inverse":[16],"kinematics":[17],"/":[18,77],"dynamics.":[19],"We":[20,119],"propose":[21],"simple,":[23],"versatile":[24],"joint-level":[25],"controller":[26],"that":[27,121],"dispenses":[28],"with":[29,95,136],"entirely.":[32],"A":[33],"deep":[34],"neural":[35],"network,":[36],"trained":[37],"via":[38,112],"model-free":[39],"reinforcement":[40],"learning,":[41],"is":[42,83,123],"used":[43],"map":[45],"from":[46],"task":[47],"space":[48],"joint":[50,73],"space.":[51],"Experiments":[52],"show":[53,120],"the":[54,67,90,93,98,116,133],"method":[55],"capable":[56],"achieving":[58],"similar":[59],"error":[60],"traditional":[62],"methods,":[63],"while":[64],"greatly":[65],"simplifying":[66],"process":[68],"by":[69,88],"automatically":[70],"handling":[71],"redundancy,":[72],"limits,":[74],"and":[75,107,132],"acceleration":[76],"deceleration":[78],"profiles.":[79],"basic":[81],"technique":[82],"extended":[84],"avoid":[86],"obstacles":[87],"augmenting":[89],"input":[91],"network":[94],"information":[96],"about":[97],"nearest":[99],"obstacles.":[100],"Results":[101],"are":[102],"shown":[103],"both":[104,129],"in":[105,130],"simulation":[106,131],"on":[108],"real":[110,134],"sim-to-real":[113],"transfer":[114],"learned":[117],"policy.":[118],"it":[122],"possible":[124],"achieve":[126],"sub-centimeter":[127],"accuracy,":[128],"world,":[135],"moderate":[138],"amount":[139],"training.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}