{"id":"https://openalex.org/W4413945820","doi":"https://doi.org/10.1109/icra55743.2025.11127792","title":"Composing Dextrous Grasping and In-Hand Manipulation via Scoring with a Reinforcement Learning Critic","display_name":"Composing Dextrous Grasping and In-Hand Manipulation via Scoring with a Reinforcement Learning Critic","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413945820","doi":"https://doi.org/10.1109/icra55743.2025.11127792"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11127792","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127792","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.13253","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047970921","display_name":"Lennart R\u00f6stel","orcid":null},"institutions":[{"id":"https://openalex.org/I2898391981","display_name":"Deutsches Zentrum f\u00fcr Luft- und Raumfahrt e. V. (DLR)","ror":"https://ror.org/04bwf3e34","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I2898391981"]},{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["DE","US"],"is_corresponding":true,"raw_author_name":"Lennart R\u00f6stel","raw_affiliation_strings":["Technical University of Munich (aidx-lab.org), and the DLR Institute of Robotics & Mechatronics (German Aerospace Center),Learning AI for Dextrous Robots Lab"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich (aidx-lab.org), and the DLR Institute of Robotics & Mechatronics (German Aerospace Center),Learning AI for Dextrous Robots Lab","institution_ids":["https://openalex.org/I4210116723","https://openalex.org/I2898391981"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059182147","display_name":"Dominik Winkelbauer","orcid":"https://orcid.org/0000-0001-7443-1071"},"institutions":[{"id":"https://openalex.org/I2898391981","display_name":"Deutsches Zentrum f\u00fcr Luft- und Raumfahrt e. V. (DLR)","ror":"https://ror.org/04bwf3e34","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I2898391981"]},{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Dominik Winkelbauer","raw_affiliation_strings":["Technical University of Munich (aidx-lab.org), and the DLR Institute of Robotics & Mechatronics (German Aerospace Center),Learning AI for Dextrous Robots Lab"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich (aidx-lab.org), and the DLR Institute of Robotics & Mechatronics (German Aerospace Center),Learning AI for Dextrous Robots Lab","institution_ids":["https://openalex.org/I4210116723","https://openalex.org/I2898391981"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075436631","display_name":"Johannes Pitz","orcid":null},"institutions":[{"id":"https://openalex.org/I2898391981","display_name":"Deutsches Zentrum f\u00fcr Luft- und Raumfahrt e. V. (DLR)","ror":"https://ror.org/04bwf3e34","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I2898391981"]},{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Johannes Pitz","raw_affiliation_strings":["Technical University of Munich (aidx-lab.org), and the DLR Institute of Robotics & Mechatronics (German Aerospace Center),Learning AI for Dextrous Robots Lab"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich (aidx-lab.org), and the DLR Institute of Robotics & Mechatronics (German Aerospace Center),Learning AI for Dextrous Robots Lab","institution_ids":["https://openalex.org/I4210116723","https://openalex.org/I2898391981"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043414969","display_name":"Leon Sievers","orcid":"https://orcid.org/0000-0001-6430-4618"},"institutions":[{"id":"https://openalex.org/I2898391981","display_name":"Deutsches Zentrum f\u00fcr Luft- und Raumfahrt e. V. (DLR)","ror":"https://ror.org/04bwf3e34","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I2898391981"]},{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Leon Sievers","raw_affiliation_strings":["Technical University of Munich (aidx-lab.org), and the DLR Institute of Robotics & Mechatronics (German Aerospace Center),Learning AI for Dextrous Robots Lab"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich (aidx-lab.org), and the DLR Institute of Robotics & Mechatronics (German Aerospace Center),Learning AI for Dextrous Robots Lab","institution_ids":["https://openalex.org/I4210116723","https://openalex.org/I2898391981"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058972548","display_name":"Berthold B\u00e4uml","orcid":"https://orcid.org/0000-0002-4545-4765"},"institutions":[{"id":"https://openalex.org/I2898391981","display_name":"Deutsches Zentrum f\u00fcr Luft- und Raumfahrt e. V. (DLR)","ror":"https://ror.org/04bwf3e34","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I2898391981"]},{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Berthold B\u00e4uml","raw_affiliation_strings":["Technical University of Munich (aidx-lab.org), and the DLR Institute of Robotics & Mechatronics (German Aerospace Center),Learning AI for Dextrous Robots Lab"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich (aidx-lab.org), and the DLR Institute of Robotics & Mechatronics (German Aerospace Center),Learning AI for Dextrous Robots Lab","institution_ids":["https://openalex.org/I4210116723","https://openalex.org/I2898391981"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5047970921"],"corresponding_institution_ids":["https://openalex.org/I2898391981","https://openalex.org/I4210116723"],"apc_list":null,"apc_paid":null,"fwci":2.2075,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.89210595,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"11683","last_page":"11690"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9890000224113464,"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":0.9890000224113464,"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/T10789","display_name":"Interactive and Immersive Displays","score":0.9793000221252441,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T10914","display_name":"Tactile and Sensory Interactions","score":0.9513999819755554,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7880183458328247},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6535597443580627},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5301212668418884},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5144384503364563},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4612715244293213},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.25222378969192505}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7880183458328247},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6535597443580627},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5301212668418884},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5144384503364563},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4612715244293213},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.25222378969192505},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icra55743.2025.11127792","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127792","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:elib.dlr.de:218580","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ICRA55743.2025.11127792>.","pdf_url":null,"source":{"id":"https://openalex.org/S4377196266","display_name":"elib (German Aerospace Center)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2898391981","host_organization_name":"Deutsches Zentrum f\u00fcr Luft- und Raumfahrt e. V. (DLR)","host_organization_lineage":["https://openalex.org/I2898391981"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},{"id":"pmh:oai:arXiv.org:2505.13253","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.13253","pdf_url":"https://arxiv.org/pdf/2505.13253","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.13253","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.13253","pdf_url":"https://arxiv.org/pdf/2505.13253","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413945820.pdf","grobid_xml":"https://content.openalex.org/works/W4413945820.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1503925285","https://openalex.org/W1794703952","https://openalex.org/W1964523947","https://openalex.org/W1984228873","https://openalex.org/W1987985958","https://openalex.org/W1999156278","https://openalex.org/W2025612888","https://openalex.org/W2042022466","https://openalex.org/W2042538399","https://openalex.org/W2049410986","https://openalex.org/W2049981393","https://openalex.org/W2085545845","https://openalex.org/W2090149479","https://openalex.org/W2106628124","https://openalex.org/W2109163007","https://openalex.org/W2112036576","https://openalex.org/W2116817751","https://openalex.org/W2123079020","https://openalex.org/W2127833308","https://openalex.org/W2134167019","https://openalex.org/W2153091458","https://openalex.org/W2155892387","https://openalex.org/W2160821342","https://openalex.org/W2205950488","https://openalex.org/W4206247072","https://openalex.org/W4210590759","https://openalex.org/W4285047691","https://openalex.org/W4285102398","https://openalex.org/W4312254766","https://openalex.org/W4312286102","https://openalex.org/W4312410889","https://openalex.org/W4313562881","https://openalex.org/W4383108265","https://openalex.org/W4383109140","https://openalex.org/W4388901983","https://openalex.org/W4390480936","https://openalex.org/W4390480960","https://openalex.org/W4390481298","https://openalex.org/W4401417123","https://openalex.org/W4401900163","https://openalex.org/W4405786148"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856"],"abstract_inverted_index":{"In-hand":[0],"manipulation":[1,16,61,91,111,125],"and":[2,94,134],"grasping":[3,133],"are":[4,29],"fundamental":[5],"yet":[6,31],"often":[7,38],"separately":[8],"addressed":[9],"tasks":[10],"in":[11,33,47],"robotics.":[12],"For":[13],"deriving":[14],"in-hand":[15,60,90,110],"policies,":[17],"reinforcement":[18,85],"learning":[19,86],"has":[20],"recently":[21],"shown":[22],"great":[23],"success.":[24],"However,":[25],"the":[26,45,58,80,106],"derived":[27],"controllers":[28],"not":[30],"useful":[32],"real-world":[34,129],"scenarios":[35],"because":[36],"they":[37],"require":[39],"a":[40,72,84,122,128],"human":[41],"operator":[42],"to":[43,92],"place":[44],"objects":[46],"suitable":[48],"initial":[49,96],"(grasping)":[50],"states.":[51],"Finding":[52],"stable":[53],"grasps":[54],"that":[55,101],"also":[56,117],"promote":[57],"desired":[59],"goal":[62],"is":[63],"an":[64,119],"open":[65],"problem.":[66],"In":[67],"this":[68,76,102],"work,":[69],"we":[70],"propose":[71],"method":[73,103],"for":[74,89],"bridging":[75],"gap":[77],"by":[78],"leveraging":[79],"critic":[81],"network":[82],"of":[83,109,121,137],"agent":[87],"trained":[88],"score":[93],"select":[95],"grasps.":[97],"Our":[98],"experiments":[99],"show":[100],"significantly":[104],"increases":[105],"success":[107],"rate":[108],"without":[112],"requiring":[113],"additional":[114],"training.":[115],"We":[116],"present":[118],"implementation":[120],"full":[123],"grasp":[124],"pipeline":[126],"on":[127],"system,":[130],"enabling":[131],"autonomous":[132],"reorientation":[135],"even":[136],"un-wieldy":[138],"objects.":[139],"Website:":[140],"aidx-lab.":[141],"org/manipulation/icra25":[142]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}