{"id":"https://openalex.org/W4415524283","doi":"https://doi.org/10.1109/humanoids65713.2025.11203093","title":"Attribute-Based Object Grounding and Robot Grasp Detection with Spatial Reasoning","display_name":"Attribute-Based Object Grounding and Robot Grasp Detection with Spatial Reasoning","publication_year":2025,"publication_date":"2025-09-30","ids":{"openalex":"https://openalex.org/W4415524283","doi":"https://doi.org/10.1109/humanoids65713.2025.11203093"},"language":null,"primary_location":{"id":"doi:10.1109/humanoids65713.2025.11203093","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids65713.2025.11203093","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE-RAS 24th International Conference on Humanoid Robots (Humanoids)","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/A5088122096","display_name":"Houjian Yu","orcid":"https://orcid.org/0000-0001-8869-5078"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Houjian Yu","raw_affiliation_strings":["Univ. of Minnesota,Department of Electrical and Computer Engineering,Minneapolis,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. of Minnesota,Department of Electrical and Computer Engineering,Minneapolis,USA","institution_ids":["https://openalex.org/I130238516"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112373330","display_name":"Zheming Zhou","orcid":"https://orcid.org/0000-0002-7549-1778"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zheming Zhou","raw_affiliation_strings":["Amazon Lab126,Sunnyvale,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Lab126,Sunnyvale,CA,USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110374901","display_name":"Min Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Min Sun","raw_affiliation_strings":["Amazon Lab126,Sunnyvale,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Lab126,Sunnyvale,CA,USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006094996","display_name":"Omid Ghasemalizadeh","orcid":"https://orcid.org/0000-0003-3142-8133"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Omid Ghasemalizadeh","raw_affiliation_strings":["Amazon Lab126,Sunnyvale,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Lab126,Sunnyvale,CA,USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102596172","display_name":"Yuyin Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuyin Sun","raw_affiliation_strings":["Amazon Lab126,Sunnyvale,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Lab126,Sunnyvale,CA,USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103028980","display_name":"Cheng\u2013Hao Kuo","orcid":"https://orcid.org/0000-0001-9464-9625"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cheng-Hao Kuo","raw_affiliation_strings":["Amazon Lab126,Sunnyvale,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Lab126,Sunnyvale,CA,USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053890173","display_name":"Arnie Sen","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arnie Sen","raw_affiliation_strings":["Amazon Lab126,Sunnyvale,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Lab126,Sunnyvale,CA,USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057994317","display_name":"Changhyun Choi","orcid":"https://orcid.org/0000-0003-4715-3576"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Changhyun Choi","raw_affiliation_strings":["Univ. of Minnesota,Department of Electrical and Computer Engineering,Minneapolis,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. of Minnesota,Department of Electrical and Computer Engineering,Minneapolis,USA","institution_ids":["https://openalex.org/I130238516"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.42082659,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1123","last_page":"1130"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13382","display_name":"Robotics and Automated Systems","score":0.9854000210762024,"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/T13382","display_name":"Robotics and Automated Systems","score":0.9854000210762024,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9575999975204468,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9532999992370605,"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/grasp","display_name":"GRASP","score":0.9650999903678894},{"id":"https://openalex.org/keywords/affordance","display_name":"Affordance","score":0.7146000266075134},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6969000101089478},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6234999895095825},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.5103999972343445},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.44690001010894775},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.39750000834465027}],"concepts":[{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.9650999903678894},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.722599983215332},{"id":"https://openalex.org/C194995250","wikidata":"https://www.wikidata.org/wiki/Q531136","display_name":"Affordance","level":2,"score":0.7146000266075134},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7117000222206116},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6969000101089478},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6234999895095825},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.5103999972343445},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4961000084877014},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.44690001010894775},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.39750000834465027},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3702000081539154},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.34220001101493835},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.33149999380111694},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3264999985694885},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.29980000853538513},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2879999876022339},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25859999656677246},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.25609999895095825}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/humanoids65713.2025.11203093","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids65713.2025.11203093","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE-RAS 24th International Conference on Humanoid Robots (Humanoids)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2778330481","display_name":null,"funder_award_id":"Lab126","funder_id":"https://openalex.org/F4320316620","funder_display_name":"Amazon Catalyst"}],"funders":[{"id":"https://openalex.org/F4320316620","display_name":"Amazon Catalyst","ror":"https://ror.org/04mv4n011"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1505952289","https://openalex.org/W2082511574","https://openalex.org/W2194775991","https://openalex.org/W2302548814","https://openalex.org/W2605127024","https://openalex.org/W2760103357","https://openalex.org/W2798556392","https://openalex.org/W3130885760","https://openalex.org/W3138516171","https://openalex.org/W3216551675","https://openalex.org/W4200631575","https://openalex.org/W4285102435","https://openalex.org/W4312615341","https://openalex.org/W4383108836","https://openalex.org/W4383109478","https://openalex.org/W4386076034","https://openalex.org/W4389665522","https://openalex.org/W4389667112","https://openalex.org/W4389667706","https://openalex.org/W4390830078","https://openalex.org/W4390871886","https://openalex.org/W4390873528","https://openalex.org/W4402702930"],"related_works":[],"abstract_inverted_index":{"Enabling":[0],"robots":[1],"to":[2,74,134,193],"grasp":[3,51,81,118,189],"objects":[4,34,77],"specified":[5],"through":[6],"natural":[7],"language":[8,27,68,158],"is":[9],"essential":[10],"for":[11,46],"effective":[12],"human-robot":[13],"interaction,":[14],"yet":[15],"it":[16,162],"remains":[17],"a":[18,62,123,168],"significant":[19],"challenge.":[20],"Existing":[21],"approaches":[22],"often":[23],"struggle":[24],"with":[25,115,155],"open-form":[26,67],"expressions":[28,69],"and":[29,50,58,70,78,105,128,141,188,213],"typically":[30],"assume":[31],"unambiguous":[32],"target":[33,76],"without":[35],"duplicates.":[36],"Moreover,":[37],"they":[38],"frequently":[39],"rely":[40],"on":[41,167],"costly,":[42],"dense":[43],"pixel-wise":[44,102],"annotations":[45],"both":[47,139,211],"object":[48,88],"grounding":[49,140,187],"configuration.":[52],"We":[53,90],"present":[54],"Attribute-based":[55],"Object":[56],"Grounding":[57],"Robotic":[59],"Grasping":[60],"(OGRG),":[61],"novel":[63],"framework":[64],"that":[65,147],"interprets":[66],"performs":[71],"spatial":[72,157,221],"reasoning":[73,222],"ground":[75],"predict":[79],"planar":[80],"poses,":[82],"even":[83],"in":[84,93,152,178,210],"scenes":[85,154],"containing":[86],"duplicated":[87],"instances.":[89],"investigate":[91],"OGRG":[92,148,204],"two":[94],"settings:":[95],"(1)":[96],"Referring":[97,107],"Grasp":[98,108],"Synthesis":[99],"(RGS)":[100],"under":[101],"full":[103],"supervision,":[104],"(2)":[106],"Affordance":[109],"(RGA)":[110],"using":[111],"weakly":[112,200],"supervised":[113,201],"learning":[114],"only":[116],"single-pixel":[117],"annotations.":[119],"Key":[120],"contributions":[121],"include":[122],"bi-directional":[124],"vision-language":[125],"fusion":[126],"module":[127],"the":[129,195,199,217],"integration":[130],"of":[131,219],"depth":[132],"information":[133],"enhance":[135],"geometric":[136],"reasoning,":[137],"improving":[138],"grasping":[142],"performance.":[143],"Experiment":[144],"results":[145],"show":[146],"outperforms":[149],"strong":[150],"baselines":[151,196],"tabletop":[153],"diverse":[156],"instructions.":[159],"In":[160],"RGS,":[161],"operates":[163],"at":[164],"17.59":[165],"FPS":[166],"single":[169],"NVIDIA":[170],"RTX":[171],"2080":[172],"Ti":[173],"GPU,":[174],"enabling":[175],"potential":[176],"use":[177],"closed-loop":[179],"or":[180],"multi-object":[181],"sequential":[182],"grasping,":[183],"while":[184],"delivering":[185],"superior":[186],"prediction":[190],"accuracy":[191],"compared":[192],"all":[194],"considered.":[197],"Under":[198],"RGA":[202],"setting,":[203],"also":[205],"surpasses":[206],"baseline":[207],"grasp-success":[208],"rates":[209],"simulation":[212],"real-robot":[214],"trials,":[215],"underscoring":[216],"effectiveness":[218],"its":[220],"design.":[223],"Project":[224],"page:":[225],"https://z.umn.edu/ogrg.":[226]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-24T00:00:00"}