{"id":"https://openalex.org/W4401416649","doi":"https://doi.org/10.1109/icra57147.2024.10610103","title":"Symmetry-aware Reinforcement Learning for Robotic Assembly under Partial Observability with a Soft Wrist","display_name":"Symmetry-aware Reinforcement Learning for Robotic Assembly under Partial Observability with a Soft Wrist","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401416649","doi":"https://doi.org/10.1109/icra57147.2024.10610103"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10610103","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610103","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5000245484","display_name":"Nguy\u1ec5n Thanh H\u1ea3i","orcid":"https://orcid.org/0000-0003-3270-6975"},"institutions":[{"id":"https://openalex.org/I146230289","display_name":"Omron (Japan)","ror":"https://ror.org/00q0w1h45","country_code":"JP","type":"company","lineage":["https://openalex.org/I146230289"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hai Nguyen","raw_affiliation_strings":["OMRON SINIC X Corporation,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OMRON SINIC X Corporation,Tokyo,Japan","institution_ids":["https://openalex.org/I146230289"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070075141","display_name":"Tadashi Kozuno","orcid":"https://orcid.org/0000-0002-8820-1362"},"institutions":[{"id":"https://openalex.org/I146230289","display_name":"Omron (Japan)","ror":"https://ror.org/00q0w1h45","country_code":"JP","type":"company","lineage":["https://openalex.org/I146230289"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tadashi Kozuno","raw_affiliation_strings":["OMRON SINIC X Corporation,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OMRON SINIC X Corporation,Tokyo,Japan","institution_ids":["https://openalex.org/I146230289"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001592945","display_name":"Cristian C. Beltran-Hernandez","orcid":"https://orcid.org/0000-0002-1134-009X"},"institutions":[{"id":"https://openalex.org/I146230289","display_name":"Omron (Japan)","ror":"https://ror.org/00q0w1h45","country_code":"JP","type":"company","lineage":["https://openalex.org/I146230289"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Cristian C. Beltran-Hernandez","raw_affiliation_strings":["OMRON SINIC X Corporation,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OMRON SINIC X Corporation,Tokyo,Japan","institution_ids":["https://openalex.org/I146230289"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034718334","display_name":"Masashi Hamaya","orcid":"https://orcid.org/0000-0003-4189-8219"},"institutions":[{"id":"https://openalex.org/I146230289","display_name":"Omron (Japan)","ror":"https://ror.org/00q0w1h45","country_code":"JP","type":"company","lineage":["https://openalex.org/I146230289"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masashi Hamaya","raw_affiliation_strings":["OMRON SINIC X Corporation,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OMRON SINIC X Corporation,Tokyo,Japan","institution_ids":["https://openalex.org/I146230289"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I146230289"],"apc_list":null,"apc_paid":null,"fwci":11.1436,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.99058778,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"9369","last_page":"9375"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9968000054359436,"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":0.9968000054359436,"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/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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/T11159","display_name":"Manufacturing Process and Optimization","score":0.9763000011444092,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/observability","display_name":"Observability","score":0.9405088424682617},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6748292446136475},{"id":"https://openalex.org/keywords/soft-robotics","display_name":"Soft robotics","score":0.5888870358467102},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5652106404304504},{"id":"https://openalex.org/keywords/symmetry","display_name":"Symmetry (geometry)","score":0.5315952897071838},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49898815155029297},{"id":"https://openalex.org/keywords/wrist","display_name":"Wrist","score":0.4929478168487549},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.422394335269928},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.3566015958786011},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.3471713066101074},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.34191569685935974},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.20811215043067932},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20652607083320618},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.14310896396636963},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.11124315857887268}],"concepts":[{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.9405088424682617},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6748292446136475},{"id":"https://openalex.org/C2776058767","wikidata":"https://www.wikidata.org/wiki/Q24327151","display_name":"Soft robotics","level":3,"score":0.5888870358467102},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5652106404304504},{"id":"https://openalex.org/C2779886137","wikidata":"https://www.wikidata.org/wiki/Q21030012","display_name":"Symmetry (geometry)","level":2,"score":0.5315952897071838},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49898815155029297},{"id":"https://openalex.org/C2778216619","wikidata":"https://www.wikidata.org/wiki/Q185706","display_name":"Wrist","level":2,"score":0.4929478168487549},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.422394335269928},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3566015958786011},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3471713066101074},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.34191569685935974},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.20811215043067932},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20652607083320618},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.14310896396636963},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.11124315857887268},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10610103","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610103","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","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":44,"referenced_works":["https://openalex.org/W1541084404","https://openalex.org/W2011418219","https://openalex.org/W2074816318","https://openalex.org/W2158782408","https://openalex.org/W2168359464","https://openalex.org/W2553722312","https://openalex.org/W2738453049","https://openalex.org/W2913446864","https://openalex.org/W2938807566","https://openalex.org/W2967427547","https://openalex.org/W2968095426","https://openalex.org/W2990708646","https://openalex.org/W3036541334","https://openalex.org/W3037969311","https://openalex.org/W3081200565","https://openalex.org/W3088304681","https://openalex.org/W3089337217","https://openalex.org/W3101875589","https://openalex.org/W3129803046","https://openalex.org/W3133009843","https://openalex.org/W3174427284","https://openalex.org/W3195211831","https://openalex.org/W4221161303","https://openalex.org/W4231648933","https://openalex.org/W4280631854","https://openalex.org/W4298392935","https://openalex.org/W4308945982","https://openalex.org/W4310789520","https://openalex.org/W4383108530","https://openalex.org/W4383108552","https://openalex.org/W4383172134","https://openalex.org/W4385482460","https://openalex.org/W4389665367","https://openalex.org/W6747473740","https://openalex.org/W6761327112","https://openalex.org/W6767104088","https://openalex.org/W6770307204","https://openalex.org/W6779557894","https://openalex.org/W6782766965","https://openalex.org/W6784403730","https://openalex.org/W6840371028","https://openalex.org/W6846841888","https://openalex.org/W6847064673","https://openalex.org/W6873125313"],"related_works":["https://openalex.org/W2046459260","https://openalex.org/W2765830098","https://openalex.org/W2967463586","https://openalex.org/W1971989957","https://openalex.org/W2517338020","https://openalex.org/W3157641275","https://openalex.org/W4312300846","https://openalex.org/W4206221578","https://openalex.org/W3029572990","https://openalex.org/W2615757685"],"abstract_inverted_index":{"This":[0],"study":[1],"tackles":[2],"the":[3,45,99,106,115,120,148,158],"representative":[4],"yet":[5],"challenging":[6],"contact-rich":[7],"peg-in-hole":[8],"task":[9],"of":[10],"robotic":[11],"assembly,":[12],"using":[13],"a":[14,28,35,52,64,91,143],"soft":[15],"wrist":[16],"that":[17,67,132],"can":[18,136],"operate":[19],"more":[20],"safely":[21],"and":[22,56,72,84,109],"tolerate":[23],"lower-frequency":[24],"control":[25],"signals":[26],"than":[27],"rigid":[29],"one.":[30],"Previous":[31],"studies":[32],"often":[33],"use":[34,51],"fully":[36],"observable":[37,54],"formulation,":[38],"requiring":[39],"external":[40],"setups":[41],"or":[42,140],"estimators":[43],"for":[44,88,101],"peg-to-hole":[46],"pose.":[47],"In":[48,146],"contrast,":[49],"we":[50,95],"partially":[53],"formulation":[55],"deep":[57],"reinforcement":[58],"learning":[59],"from":[60],"demonstrations":[61],"to":[62,97,113,117,119,139,154],"learn":[63,155],"memory-based":[65],"agent":[66,116,135],"acts":[68],"purely":[69],"on":[70,157],"haptic":[71],"proprioceptive":[73],"signals.":[74],"Moreover,":[75],"previous":[76],"works":[77],"do":[78],"not":[79],"incorporate":[80],"potential":[81],"domain":[82],"symmetry":[83,100],"thus":[85],"must":[86],"search":[87],"solutions":[89],"in":[90,123],"bigger":[92],"space.":[93],"Instead,":[94],"propose":[96],"leverage":[98],"sample":[102,149],"efficiency":[103,150],"by":[104],"augmenting":[105],"training":[107],"data":[108],"constructing":[110],"auxiliary":[111],"losses":[112],"force":[114],"adhere":[118],"symmetry.":[121],"Results":[122],"simulation":[124],"with":[125],"five":[126],"different":[127],"symmetric":[128],"peg":[129],"shapes":[130],"show":[131],"our":[133],"proposed":[134],"be":[137],"comparable":[138],"even":[141],"outperform":[142],"state-based":[144],"agent.":[145],"particular,":[147],"also":[151],"allows":[152],"us":[153],"directly":[156],"real":[159],"robot":[160],"within":[161],"3":[162],"hours.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}