{"id":"https://openalex.org/W4405786528","doi":"https://doi.org/10.1109/iros58592.2024.10801352","title":"CoPa: General Robotic Manipulation through Spatial Constraints of Parts with Foundation Models","display_name":"CoPa: General Robotic Manipulation through Spatial Constraints of Parts with Foundation Models","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405786528","doi":"https://doi.org/10.1109/iros58592.2024.10801352"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10801352","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801352","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5022918672","display_name":"Haoxu Huang","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":true,"raw_author_name":"Haoxu Huang","raw_affiliation_strings":["Tsinghua University,Institute of Interdisciplinary Information Sciences"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Institute of Interdisciplinary Information Sciences","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015408302","display_name":"Fanqi Lin","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":"Fanqi Lin","raw_affiliation_strings":["Tsinghua University,Institute of Interdisciplinary Information Sciences"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Institute of Interdisciplinary Information Sciences","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006557002","display_name":"Yingdong Hu","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":"Yingdong Hu","raw_affiliation_strings":["Tsinghua University,Institute of Interdisciplinary Information Sciences"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Institute of Interdisciplinary Information Sciences","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100696961","display_name":"Shengjie Wang","orcid":"https://orcid.org/0000-0003-3990-5803"},"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":"Shengjie Wang","raw_affiliation_strings":["Tsinghua University,Institute of Interdisciplinary Information Sciences"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Institute of Interdisciplinary Information Sciences","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038207720","display_name":"Yang Gao","orcid":"https://orcid.org/0000-0002-2150-5986"},"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":"Yang Gao","raw_affiliation_strings":["Tsinghua University,Institute of Interdisciplinary Information Sciences"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Institute of Interdisciplinary Information Sciences","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5022918672"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":8.3479,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.98785506,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"9488","last_page":"9495"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9955999851226807,"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"}},"topics":[{"id":"https://openalex.org/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9955999851226807,"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":0.9932000041007996,"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"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9711999893188477,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.8069251775741577},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5459098815917969},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4821726679801941},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3572435975074768},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.11061057448387146}],"concepts":[{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.8069251775741577},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5459098815917969},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4821726679801941},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3572435975074768},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.11061057448387146},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros58592.2024.10801352","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801352","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":51,"referenced_works":["https://openalex.org/W1971086298","https://openalex.org/W2075577325","https://openalex.org/W2135639338","https://openalex.org/W2604382266","https://openalex.org/W3035198432","https://openalex.org/W3091471537","https://openalex.org/W4313026212","https://openalex.org/W4362722144","https://openalex.org/W4383097638","https://openalex.org/W4383108457","https://openalex.org/W4385403858","https://openalex.org/W4387764390","https://openalex.org/W4388660746","https://openalex.org/W4389665359","https://openalex.org/W4389667233","https://openalex.org/W4390874280","https://openalex.org/W4390874575","https://openalex.org/W4401417065","https://openalex.org/W4402354115","https://openalex.org/W4402890475","https://openalex.org/W6682849425","https://openalex.org/W6752818329","https://openalex.org/W6800751262","https://openalex.org/W6801810553","https://openalex.org/W6809509765","https://openalex.org/W6809646742","https://openalex.org/W6810080435","https://openalex.org/W6810327023","https://openalex.org/W6810640255","https://openalex.org/W6810655313","https://openalex.org/W6839928859","https://openalex.org/W6843759960","https://openalex.org/W6845226490","https://openalex.org/W6845793730","https://openalex.org/W6847224448","https://openalex.org/W6851416138","https://openalex.org/W6852136651","https://openalex.org/W6853053110","https://openalex.org/W6853289996","https://openalex.org/W6853743997","https://openalex.org/W6854738657","https://openalex.org/W6854929498","https://openalex.org/W6855890912","https://openalex.org/W6856535302","https://openalex.org/W6857151620","https://openalex.org/W6857229035","https://openalex.org/W6857397816","https://openalex.org/W6857660107","https://openalex.org/W6858576426","https://openalex.org/W6859175081","https://openalex.org/W6868136577"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2381393187","https://openalex.org/W2332779545","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W2358060160","https://openalex.org/W2035483685"],"abstract_inverted_index":{"Foundation":[0],"models":[1,71,108],"pre-trained":[2],"on":[3,33],"web-scale":[4],"data":[5,40],"are":[6,129,143],"shown":[7],"to":[8,72,110,132,146,164],"encapsulate":[9],"extensive":[10],"world":[11],"knowledge":[12,67],"beneficial":[13],"for":[14,80],"robotic":[15,82,161],"manipulation":[16,88],"in":[17],"the":[18,24,64,87,100,112,123,134],"form":[19],"of":[20,28,56,76,138,181,184],"task":[21],"planning.":[22,98],"However,":[23],"actual":[25],"physical":[26,179],"implementation":[27],"these":[29],"plans":[30],"often":[31],"relies":[32],"task-specific":[34],"learning":[35],"methods,":[36],"which":[37,142],"require":[38],"significant":[39],"collection":[41],"and":[42,95,188,194],"struggle":[43],"with":[44,159,190],"generalizability.":[45],"In":[46,99],"this":[47],"work,":[48],"we":[49,85,104],"introduce":[50],"Robotic":[51],"Manipulation":[52],"through":[53,116],"Spatial":[54],"Constraints":[55],"Parts":[57],"(CoPa),":[58],"a":[59,74,117,177],"novel":[60,118],"framework":[61],"that":[62,174],"leverages":[63],"common":[65],"sense":[66],"embedded":[68],"within":[69],"foundation":[70,106],"generate":[73],"sequence":[75],"6-DoF":[77],"end-effector":[78],"poses":[79],"open-world":[81],"manipulation.":[83],"Specifically,":[84],"decompose":[86],"process":[89],"into":[90],"two":[91],"phases:":[92],"task-oriented":[93,101],"grasping":[94,102,114],"task-aware":[96,124],"motion":[97,125],"phase,":[103,127],"employ":[105],"vision-language":[107],"(VLMs)":[109],"select":[111],"object\u2019s":[113],"part":[115],"coarse-to-fine":[119],"grounding":[120],"mechanism.":[121],"During":[122],"planning":[126,162],"VLMs":[128],"utilized":[130],"again":[131],"identify":[133],"spatial":[135],"geometry":[136],"constraints":[137],"task-relevant":[139],"object":[140],"parts,":[141],"then":[144],"used":[145],"derive":[147],"post-grasp":[148],"poses.":[149],"We":[150],"also":[151],"demonstrate":[152],"how":[153],"CoPa":[154,175],"can":[155],"be":[156],"seamlessly":[157],"integrated":[158],"existing":[160],"algorithms":[163],"accomplish":[165],"complex,":[166],"long-horizon":[167],"tasks.":[168],"Our":[169],"comprehensive":[170],"real-world":[171],"experiments":[172],"show":[173],"possesses":[176],"fine-grained":[178],"understanding":[180],"scenes,":[182],"capable":[183],"handling":[185],"open-set":[186],"instructions":[187],"objects":[189],"minimal":[191],"prompt":[192],"engineering":[193],"without":[195],"additional":[196],"training.":[197],"Project":[198],"page:":[199],"copa-2024.github.io":[200]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":35},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}
