{"id":"https://openalex.org/W4383108836","doi":"https://doi.org/10.1109/icra48891.2023.10161041","title":"A Joint Modeling of Vision-Language-Action for Target-oriented Grasping in Clutter","display_name":"A Joint Modeling of Vision-Language-Action for Target-oriented Grasping in Clutter","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383108836","doi":"https://doi.org/10.1109/icra48891.2023.10161041"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10161041","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10161041","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":"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/A5062930488","display_name":"Kechun Xu","orcid":"https://orcid.org/0000-0002-3632-917X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kechun Xu","raw_affiliation_strings":["Zhejiang University,Hangzhou,China","Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100929934","display_name":"Shuqi Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuqi Zhao","raw_affiliation_strings":["Zhejiang University,Hangzhou,China","Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010285977","display_name":"Zhongxiang Zhou","orcid":"https://orcid.org/0000-0003-1952-7147"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongxiang Zhou","raw_affiliation_strings":["Zhejiang University,Hangzhou,China","Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022254711","display_name":"Zizhang Li","orcid":"https://orcid.org/0000-0001-7818-5162"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zizhang Li","raw_affiliation_strings":["Zhejiang University,Hangzhou,China","Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030835838","display_name":"Huaijin Pi","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaijin Pi","raw_affiliation_strings":["Zhejiang University,Hangzhou,China","Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103412109","display_name":"Yifeng Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifeng Zhu","raw_affiliation_strings":["University of Texas at Austin,United States","University of Texas at Austin, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin,United States","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"University of Texas at Austin, United States","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100371992","display_name":"Yue Wang","orcid":"https://orcid.org/0000-0002-0981-935X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Wang","raw_affiliation_strings":["Zhejiang University,Hangzhou,China","Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019081110","display_name":"Rong Xiong","orcid":"https://orcid.org/0000-0001-9318-9014"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rong Xiong","raw_affiliation_strings":["Zhejiang University,Hangzhou,China","Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5062930488"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":8.7515,"has_fulltext":false,"cited_by_count":49,"citation_normalized_percentile":{"value":0.98408016,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"11597","last_page":"11604"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9958999752998352,"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"}},{"id":"https://openalex.org/T10868","display_name":"Soft Robotics and Applications","score":0.9811000227928162,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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":0.8458635210990906},{"id":"https://openalex.org/keywords/grasp","display_name":"GRASP","score":0.8134118318557739},{"id":"https://openalex.org/keywords/clutter","display_name":"Clutter","score":0.6732248067855835},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6488193273544312},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6204379200935364},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.600995659828186},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5125898718833923},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5075737237930298},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5059248805046082},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5027220249176025},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4601792097091675},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.44746431708335876},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.40225109457969666},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3275802731513977},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08918413519859314},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07916003465652466}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8458635210990906},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.8134118318557739},{"id":"https://openalex.org/C132094186","wikidata":"https://www.wikidata.org/wiki/Q641585","display_name":"Clutter","level":3,"score":0.6732248067855835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6488193273544312},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6204379200935364},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.600995659828186},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5125898718833923},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5075737237930298},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5059248805046082},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5027220249176025},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4601792097091675},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.44746431708335876},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.40225109457969666},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3275802731513977},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08918413519859314},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07916003465652466},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48891.2023.10161041","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10161041","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":[{"display_name":"Quality Education","score":0.7799999713897705,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2201912979","https://openalex.org/W2229480318","https://openalex.org/W2489434015","https://openalex.org/W2551182329","https://openalex.org/W2600030077","https://openalex.org/W2733441458","https://openalex.org/W2736534894","https://openalex.org/W2760103357","https://openalex.org/W2773721443","https://openalex.org/W2896457183","https://openalex.org/W2904246096","https://openalex.org/W2910747522","https://openalex.org/W2962716343","https://openalex.org/W2962837436","https://openalex.org/W2963349093","https://openalex.org/W2966615203","https://openalex.org/W2969014098","https://openalex.org/W2981037657","https://openalex.org/W3004047800","https://openalex.org/W3035198432","https://openalex.org/W3090814639","https://openalex.org/W3098201885","https://openalex.org/W3109585842","https://openalex.org/W3132114951","https://openalex.org/W3166396011","https://openalex.org/W3174510143","https://openalex.org/W3176770340","https://openalex.org/W3203511201","https://openalex.org/W3204876017","https://openalex.org/W3205420310","https://openalex.org/W3207187156","https://openalex.org/W3210327237","https://openalex.org/W3212977909","https://openalex.org/W3213354518","https://openalex.org/W3217655018","https://openalex.org/W4224912544","https://openalex.org/W4281730135","https://openalex.org/W4283211057","https://openalex.org/W4285102225","https://openalex.org/W4285102324","https://openalex.org/W4285428875","https://openalex.org/W4292779060","https://openalex.org/W4299942985","https://openalex.org/W4385245566","https://openalex.org/W6723035356","https://openalex.org/W6739901393","https://openalex.org/W6740972095","https://openalex.org/W6741140343","https://openalex.org/W6745096383","https://openalex.org/W6746713385","https://openalex.org/W6752460670","https://openalex.org/W6755207826","https://openalex.org/W6757592117","https://openalex.org/W6758314495","https://openalex.org/W6769218391","https://openalex.org/W6774631009","https://openalex.org/W6778883912","https://openalex.org/W6784155536","https://openalex.org/W6791353385","https://openalex.org/W6801810553","https://openalex.org/W6802786969","https://openalex.org/W6810640255","https://openalex.org/W6838959477","https://openalex.org/W6839928859"],"related_works":["https://openalex.org/W2163296013","https://openalex.org/W165915117","https://openalex.org/W2326995835","https://openalex.org/W2743859443","https://openalex.org/W2657478029","https://openalex.org/W3146859979","https://openalex.org/W4224220472","https://openalex.org/W2080808138","https://openalex.org/W2626503888","https://openalex.org/W4387962997"],"abstract_inverted_index":{"We":[0],"focus":[1],"on":[2,22],"the":[3,18,34,64,103,107,120],"task":[4,148],"of":[5,66,132,154,166],"language-conditioned":[6],"grasping":[7],"in":[8,10,60,136],"clutter,":[9],"which":[11,55],"a":[12,23,39],"robot":[13],"is":[14,86,116,123,164],"supposed":[15],"to":[16,32,74,169],"grasp":[17,40,112],"target":[19,35],"object":[20,48],"based":[21],"language":[24,67,78,91,159,175],"instruction.":[25],"Previous":[26],"works":[27,46],"separately":[28],"conduct":[29],"visual":[30,51,97],"grounding":[31,98],"localize":[33],"object,":[36],"and":[37,62,79,93,111,119,138,174],"generate":[38],"for":[41,53,57,128],"that":[42,142],"object.":[43],"However,":[44],"these":[45],"require":[47],"labels":[49],"or":[50],"attributes":[52],"grounding,":[54],"calls":[56],"handcrafted":[58],"rules":[59],"planner":[61],"restricts":[63],"range":[65],"instructions.":[68,160,176],"In":[69],"this":[70],"paper,":[71],"we":[72],"propose":[73],"jointly":[75],"model":[76,110],"vision,":[77],"action":[80],"with":[81,171],"object-centric":[82],"representation.":[83],"Our":[84],"method":[85,144,163],"applicable":[87],"under":[88,156],"more":[89,157],"flexible":[90,158],"instructions,":[92],"not":[94],"limited":[95],"by":[96,101,151],"error.":[99],"Besides,":[100],"utilizing":[102],"powerful":[104],"priors":[105],"from":[106],"pre-trained":[108],"multi-modal":[109],"model,":[113],"sample":[114],"efficiency":[115],"effectively":[117],"improved":[118],"sim2real":[121],"problem":[122],"relived":[124],"without":[125],"additional":[126],"data":[127],"transfer.":[129],"A":[130],"series":[131],"experiments":[133],"carried":[134],"out":[135],"simulation":[137],"real":[139],"world":[140],"indicate":[141],"our":[143,162],"can":[145],"achieve":[146],"better":[147,168],"success":[149],"rate":[150],"less":[152],"times":[153],"motion":[155],"Moreover,":[161],"capable":[165],"generalizing":[167],"scenarios":[170],"unseen":[172],"objects":[173]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":29},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":2}],"updated_date":"2026-05-02T08:42:23.175194","created_date":"2025-10-10T00:00:00"}