{"id":"https://openalex.org/W7131905514","doi":"https://doi.org/10.1109/sii64115.2026.11404489","title":"Learning Dynamic Non-Prehensile Object Reorientation via Reinforcement Learning","display_name":"Learning Dynamic Non-Prehensile Object Reorientation via Reinforcement Learning","publication_year":2026,"publication_date":"2026-01-11","ids":{"openalex":"https://openalex.org/W7131905514","doi":"https://doi.org/10.1109/sii64115.2026.11404489"},"language":null,"primary_location":{"id":"doi:10.1109/sii64115.2026.11404489","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sii64115.2026.11404489","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/SICE International Symposium on System Integration (SII)","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/A5052725971","display_name":"Abdullah Mustafa","orcid":"https://orcid.org/0000-0002-1537-3868"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Abdullah Mustafa","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST),Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST),Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102871528","display_name":"Ryo Hanai","orcid":"https://orcid.org/0000-0003-4216-4866"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryo Hanai","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST),Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST),Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064317353","display_name":"Ixchel G. Ram\u00edrez-Alpizar","orcid":"https://orcid.org/0000-0002-7805-7539"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ixchel G. Ramirez-Alpizar","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST),Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST),Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028381240","display_name":"Floris Erich","orcid":"https://orcid.org/0000-0001-7576-9867"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Floris Erich","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST),Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST),Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029075114","display_name":"Ryoichi Nakajo","orcid":"https://orcid.org/0009-0006-3870-8508"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryoichi Nakajo","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST),Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST),Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051303516","display_name":"Yukiyasu DOMAE","orcid":null},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yukiyasu Domae","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology (AIST),Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology (AIST),Japan","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5121263256","display_name":"Tetsuya OGATA","orcid":null},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuya Ogata","raw_affiliation_strings":["Waseda University,Graduate School of Fundamental Science and Engineering,Tokyo,Japan,169-8555"],"affiliations":[{"raw_affiliation_string":"Waseda University,Graduate School of Fundamental Science and Engineering,Tokyo,Japan,169-8555","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5052725971"],"corresponding_institution_ids":["https://openalex.org/I73613424"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.9465928,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"50","last_page":"55"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.5199000239372253,"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":0.5199000239372253,"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":0.2126999944448471,"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/T10982","display_name":"Motor Control and Adaptation","score":0.02329999953508377,"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":0.7695000171661377},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.7458000183105469},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5983999967575073},{"id":"https://openalex.org/keywords/rotation","display_name":"Rotation (mathematics)","score":0.5709999799728394},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.47749999165534973},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.42010000348091125},{"id":"https://openalex.org/keywords/transfer-function","display_name":"Transfer function","score":0.388700008392334},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.38530001044273376}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7695000171661377},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.7458000183105469},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7127000093460083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6234999895095825},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5983999967575073},{"id":"https://openalex.org/C74050887","wikidata":"https://www.wikidata.org/wiki/Q848368","display_name":"Rotation (mathematics)","level":2,"score":0.5709999799728394},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.47749999165534973},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.42010000348091125},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3977999985218048},{"id":"https://openalex.org/C81299745","wikidata":"https://www.wikidata.org/wiki/Q334269","display_name":"Transfer function","level":2,"score":0.388700008392334},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.38530001044273376},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.29170000553131104},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.28870001435279846},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.28610000014305115},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C77405623","wikidata":"https://www.wikidata.org/wiki/Q598451","display_name":"System dynamics","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C20894473","wikidata":"https://www.wikidata.org/wiki/Q1116105","display_name":"Object model","level":3,"score":0.26339998841285706},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2612999975681305},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2563000023365021}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sii64115.2026.11404489","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sii64115.2026.11404489","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/SICE International Symposium on System Integration (SII)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5071359276771545}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1793265611","https://openalex.org/W2016765487","https://openalex.org/W2612144999","https://openalex.org/W2789539638","https://openalex.org/W2990747716","https://openalex.org/W3163158059","https://openalex.org/W3194048684","https://openalex.org/W4226344024","https://openalex.org/W4367016688","https://openalex.org/W4385430700","https://openalex.org/W4387623874","https://openalex.org/W4388901983","https://openalex.org/W4389667032","https://openalex.org/W4389667645","https://openalex.org/W4393139803","https://openalex.org/W4402354032","https://openalex.org/W4402354159","https://openalex.org/W4413917693","https://openalex.org/W4414079231"],"related_works":[],"abstract_inverted_index":{"This":[0],"work":[1],"proposes":[2],"a":[3,31,55],"learning-based":[4],"approach":[5],"to":[6,41,76],"dynamic":[7],"non-prehensile":[8],"object":[9,52],"reorientation,":[10],"enabling":[11],"fast":[12],"reorientation":[13],"of":[14],"large,":[15],"grasp-infeasible":[16],"objects":[17,91],"using":[18],"uni-manual":[19],"manipulation.":[20],"Our":[21],"policy":[22,60,73],"is":[23,74],"trained":[24],"in":[25],"simulation":[26,67],"via":[27],"reinforcement":[28],"learning,":[29],"utilizing":[30],"carefully":[32],"designed":[33],"observation":[34],"space,":[35,37],"action":[36],"and":[38,54,68,92],"reward":[39],"function":[40],"reorient":[42],"randomly":[43],"sized":[44],"cuboids":[45],"with":[46],"varied":[47],"physical":[48],"properties.":[49],"Given":[50],"an":[51],"model":[53],"target":[56],"rotation":[57,93],"direction,":[58],"the":[59,72],"plans":[61],"offline":[62],"trajectories":[63],"suitable":[64],"for":[65],"both":[66],"real-world":[69],"deployment.":[70],"Although":[71],"sensitive":[75],"modeling":[77,84],"uncertainties,":[78],"experimental":[79],"results":[80],"show":[81],"that":[82],"accurate":[83],"enables":[85],"successful":[86],"sim-to-real":[87],"transfer":[88],"across":[89],"different":[90],"directions.":[94],"Videos":[95],"are":[96],"available":[97],"at":[98],"https://tinyurl.com/DNPR2L.":[99]},"counts_by_year":[],"updated_date":"2026-03-01T06:05:34.837733","created_date":"2026-02-28T00:00:00"}
