{"id":"https://openalex.org/W3210579454","doi":"https://doi.org/10.1109/icra46639.2022.9811973","title":"Learning Insertion Primitives with Discrete-Continuous Hybrid Action Space for Robotic Assembly Tasks","display_name":"Learning Insertion Primitives with Discrete-Continuous Hybrid Action Space for Robotic Assembly Tasks","publication_year":2022,"publication_date":"2022-05-23","ids":{"openalex":"https://openalex.org/W3210579454","doi":"https://doi.org/10.1109/icra46639.2022.9811973","mag":"3210579454"},"language":"en","primary_location":{"id":"doi:10.1109/icra46639.2022.9811973","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra46639.2022.9811973","pdf_url":null,"source":{"id":"https://openalex.org/S4363607759","display_name":"2022 International Conference on Robotics and Automation (ICRA)","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":"2022 International Conference on Robotics and Automation (ICRA)","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/A5047827691","display_name":"Xiang Zhang","orcid":"https://orcid.org/0000-0001-7900-5127"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiang Zhang","raw_affiliation_strings":["UC Berkeley,Department of Mechanical Engineering,CA,USA,94720"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley,Department of Mechanical Engineering,CA,USA,94720","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050808028","display_name":"Shiyu Jin","orcid":"https://orcid.org/0000-0002-6475-5942"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shiyu Jin","raw_affiliation_strings":["UC Berkeley,Department of Mechanical Engineering,CA,USA,94720"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley,Department of Mechanical Engineering,CA,USA,94720","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100709173","display_name":"Changhao Wang","orcid":"https://orcid.org/0000-0002-5753-1991"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Changhao Wang","raw_affiliation_strings":["UC Berkeley,Department of Mechanical Engineering,CA,USA,94720"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley,Department of Mechanical Engineering,CA,USA,94720","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101715656","display_name":"Xinghao Zhu","orcid":"https://orcid.org/0009-0002-8078-1531"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinghao Zhu","raw_affiliation_strings":["UC Berkeley,Department of Mechanical Engineering,CA,USA,94720"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley,Department of Mechanical Engineering,CA,USA,94720","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064077634","display_name":"Masayoshi Tomizuka","orcid":"https://orcid.org/0000-0003-0206-6639"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Masayoshi Tomizuka","raw_affiliation_strings":["UC Berkeley,Department of Mechanical Engineering,CA,USA,94720"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley,Department of Mechanical Engineering,CA,USA,94720","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":10.5227,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.99295633,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"9881","last_page":"9887"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9961000084877014,"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/T11159","display_name":"Manufacturing Process and Optimization","score":0.987500011920929,"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/computer-science","display_name":"Computer science","score":0.7473509907722473},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.691006600856781},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.6049138903617859},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5279383063316345},{"id":"https://openalex.org/keywords/discretization","display_name":"Discretization","score":0.49309560656547546},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4535828232765198},{"id":"https://openalex.org/keywords/shared-space","display_name":"Shared space","score":0.4407649636268616},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4401251971721649},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4336296319961548},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4256143271923065},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.26905357837677},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16257831454277039},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14441058039665222}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7473509907722473},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.691006600856781},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.6049138903617859},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5279383063316345},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.49309560656547546},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4535828232765198},{"id":"https://openalex.org/C2777311342","wikidata":"https://www.wikidata.org/wiki/Q578801","display_name":"Shared space","level":3,"score":0.4407649636268616},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4401251971721649},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4336296319961548},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4256143271923065},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26905357837677},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16257831454277039},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14441058039665222},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra46639.2022.9811973","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra46639.2022.9811973","pdf_url":null,"source":{"id":"https://openalex.org/S4363607759","display_name":"2022 International Conference on Robotics and Automation (ICRA)","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":"2022 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":42,"referenced_works":["https://openalex.org/W1757796397","https://openalex.org/W2035957498","https://openalex.org/W2158782408","https://openalex.org/W2173248099","https://openalex.org/W2256420211","https://openalex.org/W2787938642","https://openalex.org/W2897417898","https://openalex.org/W2904246096","https://openalex.org/W2944306386","https://openalex.org/W2963257680","https://openalex.org/W2963312729","https://openalex.org/W2963616477","https://openalex.org/W2963864421","https://openalex.org/W2963940579","https://openalex.org/W2964227312","https://openalex.org/W2965757358","https://openalex.org/W2975504670","https://openalex.org/W2990708646","https://openalex.org/W2997756832","https://openalex.org/W3090054427","https://openalex.org/W3091037773","https://openalex.org/W3130466728","https://openalex.org/W3130500701","https://openalex.org/W3130717831","https://openalex.org/W3130984490","https://openalex.org/W3132045372","https://openalex.org/W3206432993","https://openalex.org/W3207601508","https://openalex.org/W4287907838","https://openalex.org/W4298857966","https://openalex.org/W6637967152","https://openalex.org/W6684921986","https://openalex.org/W6691861496","https://openalex.org/W6748839928","https://openalex.org/W6754843927","https://openalex.org/W6755326576","https://openalex.org/W6757592117","https://openalex.org/W6762592680","https://openalex.org/W6770307204","https://openalex.org/W6772421901","https://openalex.org/W6772562993","https://openalex.org/W6776542378"],"related_works":["https://openalex.org/W2051058708","https://openalex.org/W154868527","https://openalex.org/W1494268238","https://openalex.org/W1983207144","https://openalex.org/W2490706771","https://openalex.org/W1976468483","https://openalex.org/W2480116122","https://openalex.org/W2563912921","https://openalex.org/W2407611282","https://openalex.org/W4255576661"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3,93,112],"discrete-continuous":[4],"action":[5],"space":[6],"to":[7,141,187,193],"learn":[8,62,122],"insertion":[9,71,124],"primitives":[10,72,174,184],"for":[11,98,156],"robotic":[12],"assembly":[13,64,195],"tasks.":[14],"Primitives":[15],"are":[16,148,185,213],"sequences":[17],"of":[18,39,79,95,136],"elementary":[19],"actions":[20,77],"with":[21,88,138,171,175,207],"certain":[22],"exit":[23],"conditions,":[24],"such":[25,197],"as":[26,73,198],"\u201cpushing":[27],"down":[28],"the":[29,34,50,89,101,143,151],"peg":[30],"until":[31],"contact\u201d.":[32],"Since":[33],"primitive":[35,81,85,109],"is":[36,116],"an":[37,133],"abstraction":[38],"robot":[40,63],"control":[41],"commands":[42],"and":[43,53,83,119,153,178,190,202],"encodes":[44],"human":[45],"prior":[46],"knowledge,":[47],"it":[48],"reduces":[49],"exploration":[51],"difficulty":[52],"yields":[54],"better":[55],"learning":[56],"efficiency.":[57],"In":[58],"this":[59],"paper,":[60],"we":[61,69,126],"skills":[65],"via":[66],"primitives.":[67],"Specifically,":[68],"formulate":[70],"parameterized":[74,172],"actions:":[75],"hybrid":[76],"consisting":[78],"discrete":[80,176],"types":[82],"continuous":[84,113,179],"parameters.":[86],"Compared":[87],"previous":[90],"work":[91],"using":[92],"set":[94],"discretized":[96],"parameters":[97,110],"each":[99],"primitive,":[100],"agent":[102],"in":[103,150],"our":[104,161],"method":[105],"can":[106,191],"freely":[107],"choose":[108],"from":[111],"space,":[114],"which":[115],"more":[117],"flexible":[118],"efficient.":[120],"To":[121],"these":[123],"primitives,":[125],"propose":[127],"Twin-Smoothed":[128],"Multi-pass":[129],"Deep":[130],"Q-Network":[131],"(TS-MP-DQN),":[132],"advanced":[134],"version":[135],"MP-DQN":[137,170],"twin":[139],"Q-network":[140],"reduce":[142],"Q-value":[144],"over-estimation.":[145],"Extensive":[146],"experiments":[147],"conducted":[149],"simulation":[152],"real":[154],"world":[155],"validation.":[157],"From":[158],"experiment":[159],"results,":[160],"approach":[162],"achieves":[163],"higher":[164],"success":[165,209],"rates":[166],"than":[167],"three":[168],"baselines:":[169],"actions,":[173],"parameters,":[177],"velocity":[180],"control.":[181],"Furthermore,":[182],"learned":[183],"robust":[186],"sim-to-real":[188],"transfer":[189],"generalize":[192],"challenging":[194],"tasks":[196],"tight":[199],"round":[200],"peg-hole":[201],"complex":[203],"shaped":[204],"electric":[205],"connectors":[206],"promising":[208],"rates.":[210],"Experiment":[211],"videos":[212],"available":[214],"at":[215],"https://msc.berkeley.edu/research/insertion-primitives.html.":[216]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":11}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}