{"id":"https://openalex.org/W4226075155","doi":"https://doi.org/10.1109/robio54168.2021.9739435","title":"Direct Policy Optimization with Differentiable Physical Consistency for Dexterous Manipulation","display_name":"Direct Policy Optimization with Differentiable Physical Consistency for Dexterous Manipulation","publication_year":2021,"publication_date":"2021-12-27","ids":{"openalex":"https://openalex.org/W4226075155","doi":"https://doi.org/10.1109/robio54168.2021.9739435"},"language":"en","primary_location":{"id":"doi:10.1109/robio54168.2021.9739435","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio54168.2021.9739435","pdf_url":null,"source":{"id":"https://openalex.org/S4363607846","display_name":"2021 IEEE International Conference on Robotics and Biomimetics (ROBIO)","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 International Conference on Robotics and Biomimetics (ROBIO)","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/A5075179620","display_name":"Philipp Ruppel","orcid":"https://orcid.org/0000-0002-1336-8483"},"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":true,"raw_author_name":"Philipp Ruppel","raw_affiliation_strings":["Universit&#x00E4;t Hamburg,Department of Informatics,Hamburg,Germany"],"affiliations":[{"raw_affiliation_string":"Universit&#x00E4;t Hamburg,Department of Informatics,Hamburg,Germany","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086095248","display_name":"Norman Hendrich","orcid":"https://orcid.org/0000-0003-0499-886X"},"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":"Norman Hendrich","raw_affiliation_strings":["Universit&#x00E4;t Hamburg,Department of Informatics,Hamburg,Germany"],"affiliations":[{"raw_affiliation_string":"Universit&#x00E4;t Hamburg,Department of Informatics,Hamburg,Germany","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100326970","display_name":"Jianwei Zhang","orcid":"https://orcid.org/0000-0002-7856-5760"},"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":"Jianwei Zhang","raw_affiliation_strings":["Universit&#x00E4;t Hamburg,Department of Informatics,Hamburg,Germany"],"affiliations":[{"raw_affiliation_string":"Universit&#x00E4;t Hamburg,Department of Informatics,Hamburg,Germany","institution_ids":["https://openalex.org/I159176309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5075179620"],"corresponding_institution_ids":["https://openalex.org/I159176309"],"apc_list":null,"apc_paid":null,"fwci":1.309,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.80646163,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"70","issue":null,"first_page":"650","last_page":"655"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9991999864578247,"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":0.9991999864578247,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12290","display_name":"Human Motion and Animation","score":0.9980000257492065,"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/consistency","display_name":"Consistency (knowledge bases)","score":0.7491760849952698},{"id":"https://openalex.org/keywords/maxima-and-minima","display_name":"Maxima and minima","score":0.7379217147827148},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7163269519805908},{"id":"https://openalex.org/keywords/classification-of-discontinuities","display_name":"Classification of discontinuities","score":0.6717031598091125},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.5971580743789673},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5621605515480042},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5323315858840942},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37685757875442505},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3303382992744446},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10319718718528748},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09000840783119202}],"concepts":[{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.7491760849952698},{"id":"https://openalex.org/C186633575","wikidata":"https://www.wikidata.org/wiki/Q845060","display_name":"Maxima and minima","level":2,"score":0.7379217147827148},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7163269519805908},{"id":"https://openalex.org/C15627037","wikidata":"https://www.wikidata.org/wiki/Q541961","display_name":"Classification of discontinuities","level":2,"score":0.6717031598091125},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.5971580743789673},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5621605515480042},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5323315858840942},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37685757875442505},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3303382992744446},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10319718718528748},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09000840783119202},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/robio54168.2021.9739435","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio54168.2021.9739435","pdf_url":null,"source":{"id":"https://openalex.org/S4363607846","display_name":"2021 IEEE International Conference on Robotics and Biomimetics (ROBIO)","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 International Conference on Robotics and Biomimetics (ROBIO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5299999713897705,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1630678085","https://openalex.org/W2042408133","https://openalex.org/W2142224528","https://openalex.org/W2161819990","https://openalex.org/W2205340216","https://openalex.org/W2885163910","https://openalex.org/W2891122218","https://openalex.org/W2913668833","https://openalex.org/W2952376685","https://openalex.org/W2968042644","https://openalex.org/W2977371611","https://openalex.org/W2981603589","https://openalex.org/W2995253198","https://openalex.org/W3003010287","https://openalex.org/W3194488868","https://openalex.org/W4212774754","https://openalex.org/W4247541366","https://openalex.org/W6636808768","https://openalex.org/W6683526187","https://openalex.org/W6739785051","https://openalex.org/W6756486208","https://openalex.org/W6767977373","https://openalex.org/W6769017845","https://openalex.org/W6785380616"],"related_works":["https://openalex.org/W2375684291","https://openalex.org/W2354676191","https://openalex.org/W3188646203","https://openalex.org/W2909957174","https://openalex.org/W4246278799","https://openalex.org/W136674370","https://openalex.org/W2105527480","https://openalex.org/W1972096828","https://openalex.org/W2529137940","https://openalex.org/W2052387497"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,24,42,68,73,77],"gradient-based":[3],"direct":[4],"policy":[5],"optimization":[6],"method":[7,58],"for":[8,32,64],"efficiently":[9],"learning":[10],"dexterous":[11],"manipulation":[12],"tasks":[13],"in":[14],"simulation.":[15],"To":[16],"overcome":[17],"local":[18],"minima":[19],"and":[20,35,52],"discontinuities,":[21],"we":[22],"use":[23],"physical":[25,55],"consistency":[26],"loss":[27],"with":[28,67],"additional":[29],"control":[30],"variables":[31],"contact":[33],"points":[34],"forces.":[36],"During":[37],"training,":[38],"the":[39],"weights":[40],"of":[41],"neural":[43],"network":[44],"are":[45],"optimized":[46],"to":[47,53,61],"simultaneously":[48],"fulfill":[49],"task":[50],"goals":[51],"minimize":[54],"inconsistencies.":[56],"Our":[57],"is":[59],"able":[60],"learn":[62],"policies":[63],"manipulating":[65],"objects":[66],"humanoid":[69],"hand-arm":[70],"system":[71],"within":[72],"few":[74],"minutes":[75],"on":[76],"single":[78],"CPU.":[79]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
