{"id":"https://openalex.org/W4383172134","doi":"https://doi.org/10.1109/icra48891.2023.10160739","title":"Efficient Bimanual Handover and Rearrangement via Symmetry-Aware Actor-Critic Learning","display_name":"Efficient Bimanual Handover and Rearrangement via Symmetry-Aware Actor-Critic Learning","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383172134","doi":"https://doi.org/10.1109/icra48891.2023.10160739"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10160739","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160739","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 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/A5100461869","display_name":"Yunfei Li","orcid":"https://orcid.org/0000-0003-1641-0234"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunfei Li","raw_affiliation_strings":["Institute of Inter-disciplinary Information Sciences, Tsinghua University,Beijing,China","Institute of Inter-disciplinary Information Sciences, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Inter-disciplinary Information Sciences, Tsinghua University,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Institute of Inter-disciplinary Information Sciences, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008464590","display_name":"Chaoyi Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaoyi Pan","raw_affiliation_strings":["Tsinghua University,Department of Electronic Engineering,Beijing,China","Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Electronic Engineering,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049093671","display_name":"Huazhe Xu","orcid":"https://orcid.org/0000-0001-8578-1261"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210122302","display_name":"ShangHai JiAi Genetics & IVF Institute","ror":"https://ror.org/02rgbry52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210122302"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huazhe Xu","raw_affiliation_strings":["Institute of Inter-disciplinary Information Sciences, Tsinghua University,Beijing,China","Institute of Inter-disciplinary Information Sciences, Tsinghua University, Beijing, China","Shanghai Artificial Intelligence Lab, Shanghai, China","Shanghai Qi Zhi Institute, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Inter-disciplinary Information Sciences, Tsinghua University,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Institute of Inter-disciplinary Information Sciences, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shanghai Artificial Intelligence Lab, Shanghai, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]},{"raw_affiliation_string":"Shanghai Qi Zhi Institute, Shanghai, China","institution_ids":["https://openalex.org/I4210122302"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100424275","display_name":"Xiaolong Wang","orcid":"https://orcid.org/0000-0003-3150-778X"},"institutions":[{"id":"https://openalex.org/I2800935791","display_name":"UC San Diego Health System","ror":"https://ror.org/01kbfgm16","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2800935791"]},{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaolong Wang","raw_affiliation_strings":["UC,Department of Electrical and Computer Engineering,San Diego,CA,USA","Department of Electrical and Computer Engineering, UC, San Diego, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC,Department of Electrical and Computer Engineering,San Diego,CA,USA","institution_ids":["https://openalex.org/I2800935791","https://openalex.org/I36258959"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, UC, San Diego, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101458171","display_name":"Yi Wu","orcid":"https://orcid.org/0000-0003-3838-7418"},"institutions":[{"id":"https://openalex.org/I4210122302","display_name":"ShangHai JiAi Genetics & IVF Institute","ror":"https://ror.org/02rgbry52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210122302"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Wu","raw_affiliation_strings":["Institute of Inter-disciplinary Information Sciences, Tsinghua University,Beijing,China","Institute of Inter-disciplinary Information Sciences, Tsinghua University, Beijing, China","Shanghai Qi Zhi Institute, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Inter-disciplinary Information Sciences, Tsinghua University,Beijing,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Institute of Inter-disciplinary Information Sciences, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shanghai Qi Zhi Institute, Shanghai, China","institution_ids":["https://openalex.org/I4210122302"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1779,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.89673922,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3867","last_page":"3874"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9973999857902527,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9696000218391418,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8055846691131592},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7460960149765015},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7161445617675781},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6631338000297546},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6308197379112244},{"id":"https://openalex.org/keywords/handover","display_name":"Handover","score":0.6139498949050903},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5527714490890503},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5373332500457764},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4614817500114441},{"id":"https://openalex.org/keywords/collision-avoidance","display_name":"Collision avoidance","score":0.4429110884666443},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.43710044026374817},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3534064292907715},{"id":"https://openalex.org/keywords/collision","display_name":"Collision","score":0.255939245223999},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.12067359685897827},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.10558846592903137}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8055846691131592},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7460960149765015},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7161445617675781},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6631338000297546},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6308197379112244},{"id":"https://openalex.org/C111852164","wikidata":"https://www.wikidata.org/wiki/Q1414679","display_name":"Handover","level":2,"score":0.6139498949050903},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5527714490890503},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5373332500457764},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4614817500114441},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.4429110884666443},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.43710044026374817},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3534064292907715},{"id":"https://openalex.org/C121704057","wikidata":"https://www.wikidata.org/wiki/Q352070","display_name":"Collision","level":2,"score":0.255939245223999},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.12067359685897827},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.10558846592903137},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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":1,"locations":[{"id":"doi:10.1109/icra48891.2023.10160739","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160739","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":78,"referenced_works":["https://openalex.org/W157644030","https://openalex.org/W567721252","https://openalex.org/W1533853869","https://openalex.org/W1564393562","https://openalex.org/W1594201624","https://openalex.org/W1688218840","https://openalex.org/W1994349244","https://openalex.org/W2015241127","https://openalex.org/W2109447584","https://openalex.org/W2147168033","https://openalex.org/W2151607042","https://openalex.org/W2155007355","https://openalex.org/W2415216611","https://openalex.org/W2781726626","https://openalex.org/W2807741983","https://openalex.org/W2902125520","https://openalex.org/W2947984804","https://openalex.org/W2964036701","https://openalex.org/W2967171277","https://openalex.org/W2968156685","https://openalex.org/W2970393539","https://openalex.org/W2970733386","https://openalex.org/W3007848632","https://openalex.org/W3008970887","https://openalex.org/W3009925493","https://openalex.org/W3021208093","https://openalex.org/W3039459278","https://openalex.org/W3040477237","https://openalex.org/W3090054427","https://openalex.org/W3097484130","https://openalex.org/W3100738175","https://openalex.org/W3106302274","https://openalex.org/W3120327542","https://openalex.org/W3169676024","https://openalex.org/W3173254652","https://openalex.org/W3186239158","https://openalex.org/W3204030880","https://openalex.org/W3207460231","https://openalex.org/W3207612633","https://openalex.org/W3210940825","https://openalex.org/W3213974477","https://openalex.org/W4225124528","https://openalex.org/W4226288547","https://openalex.org/W4287749615","https://openalex.org/W4295598622","https://openalex.org/W4297672293","https://openalex.org/W4300799055","https://openalex.org/W4385245566","https://openalex.org/W6606313953","https://openalex.org/W6616173779","https://openalex.org/W6635701881","https://openalex.org/W6637513772","https://openalex.org/W6682849425","https://openalex.org/W6692405165","https://openalex.org/W6739648434","https://openalex.org/W6739901393","https://openalex.org/W6740801417","https://openalex.org/W6747473740","https://openalex.org/W6748012927","https://openalex.org/W6749304979","https://openalex.org/W6752380930","https://openalex.org/W6756908582","https://openalex.org/W6759870248","https://openalex.org/W6766185457","https://openalex.org/W6767047803","https://openalex.org/W6774784542","https://openalex.org/W6774967489","https://openalex.org/W6784396901","https://openalex.org/W6784840303","https://openalex.org/W6785308759","https://openalex.org/W6785337696","https://openalex.org/W6788682413","https://openalex.org/W6795964365","https://openalex.org/W6797745118","https://openalex.org/W6800004206","https://openalex.org/W6802748332","https://openalex.org/W6810294026","https://openalex.org/W6810759771"],"related_works":["https://openalex.org/W2520149731","https://openalex.org/W1981519115","https://openalex.org/W3006634511","https://openalex.org/W1985631144","https://openalex.org/W2087123996","https://openalex.org/W2115561238","https://openalex.org/W2103264866","https://openalex.org/W2023203067","https://openalex.org/W1962476109","https://openalex.org/W53279813"],"abstract_inverted_index":{"Bimanual":[0],"manipulation":[1],"is":[2,46],"important":[3],"for":[4,48],"building":[5],"intelligent":[6],"robots":[7],"that":[8,73,116],"unlock":[9],"richer":[10],"skills":[11],"than":[12],"single":[13],"arms.":[14],"We":[15,67,132],"consider":[16],"a":[17,23,69,124,144],"multi-object":[18],"bimanual":[19,84],"rearrangement":[20],"task,":[21],"where":[22],"reinforcement":[24],"learning":[25],"(RL)":[26],"agent":[27,51],"aims":[28],"to":[29,34,53,87,120,136],"jointly":[30],"control":[31,65,85],"two":[32,80,137],"arms":[33,140],"rearrange":[35,118],"these":[36],"objects":[37,122],"as":[38,40],"fast":[39],"possible.":[41],"Solving":[42],"this":[43],"task":[44],"efficiently":[45],"challenging":[47],"an":[49,62,105,113],"RL":[50,114],"due":[52],"the":[54,75,79,83,89,95,134],"requirement":[55],"of":[56,78,127],"discovering":[57],"precise":[58],"intra-arm":[59],"coordination":[60],"in":[61,82,130],"exponentially":[63],"large":[64],"space.":[66,92],"develop":[68],"symmetry-aware":[70],"actor-critic":[71],"framework":[72],"leverages":[74],"interchangeable":[76],"roles":[77],"manipulators":[81],"setting":[86],"reduce":[88],"policy":[90,115,135],"search":[91],"To":[93],"handle":[94],"compositionality":[96],"over":[97,128],"multiple":[98],"objects,":[99],"we":[100],"augment":[101],"training":[102],"data":[103],"with":[104,123],"object-centric":[106],"relabeling":[107],"technique.":[108],"The":[109],"overall":[110],"approach":[111],"produces":[112],"can":[117,151],"up":[119],"8":[121],"success":[125],"rate":[126],"70%":[129],"simulation.":[131],"deploy":[133],"Franka":[138],"Panda":[139],"and":[141],"further":[142],"show":[143],"successful":[145],"demo":[146],"on":[147],"human-robot":[148],"collaboration.":[149],"Videos":[150],"be":[152],"found":[153],"at":[154],"https://sites.google.com/view/bimanual.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
