{"id":"https://openalex.org/W7117475401","doi":"https://doi.org/10.1007/s40747-025-02169-0","title":"Enhancing task-oriented robotic grasping via 3D affordance grounding from vision-language models","display_name":"Enhancing task-oriented robotic grasping via 3D affordance grounding from vision-language models","publication_year":2025,"publication_date":"2025-12-29","ids":{"openalex":"https://openalex.org/W7117475401","doi":"https://doi.org/10.1007/s40747-025-02169-0"},"language":"en","primary_location":{"id":"doi:10.1007/s40747-025-02169-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-025-02169-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-025-02169-0.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex & Intelligent Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1007/s40747-025-02169-0.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014117737","display_name":"W. Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Wenkai Chen","raw_affiliation_strings":["Department of Informatics, Universit\u00e4t Hamburg, 22527, Hamburg, Germany"],"raw_orcid":"https://orcid.org/0000-0003-0169-8896","affiliations":[{"raw_affiliation_string":"Department of Informatics, Universit\u00e4t Hamburg, 22527, Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059241924","display_name":"Shang-Ching Liu","orcid":"https://orcid.org/0009-0001-3484-8646"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Shang-Ching Liu","raw_affiliation_strings":["Department of Informatics, Universit\u00e4t Hamburg, 22527, Hamburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, Universit\u00e4t Hamburg, 22527, Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121462798","display_name":"Qingdu Li","orcid":null},"institutions":[{"id":"https://openalex.org/I148128674","display_name":"University of Shanghai for Science and Technology","ror":"https://ror.org/00ay9v204","country_code":"CN","type":"education","lineage":["https://openalex.org/I148128674"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingdu Li","raw_affiliation_strings":["Institute of Machine Intelligence, University of Shanghai for Science and Technology, Shanghai, 200093, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Machine Intelligence, University of Shanghai for Science and Technology, Shanghai, 200093, China","institution_ids":["https://openalex.org/I148128674"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121515543","display_name":"Yung-Hui Li","orcid":null},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yung-Hui Li","raw_affiliation_strings":["Hon Hai Research Institute (HHRI), Taiwan, 236041, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hon Hai Research Institute (HHRI), Taiwan, 236041, China","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5121519017","display_name":"Jianwei Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jianwei Zhang","raw_affiliation_strings":["Department of Informatics, Universit\u00e4t Hamburg, 22527, Hamburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, Universit\u00e4t Hamburg, 22527, Hamburg, Germany","institution_ids":["https://openalex.org/I159176309"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5014117737"],"corresponding_institution_ids":["https://openalex.org/I159176309"],"apc_list":{"value":1320,"currency":"GBP","value_usd":1619},"apc_paid":{"value":1320,"currency":"GBP","value_usd":1619},"fwci":0.8926,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.81525403,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"12","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9663000106811523,"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":0.9663000106811523,"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/T10982","display_name":"Motor Control and Adaptation","score":0.00860000029206276,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.004000000189989805,"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/grasp","display_name":"GRASP","score":0.9625999927520752},{"id":"https://openalex.org/keywords/affordance","display_name":"Affordance","score":0.9538999795913696},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5187000036239624},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.49309998750686646},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.48579999804496765},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.36899998784065247},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.36629998683929443}],"concepts":[{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.9625999927520752},{"id":"https://openalex.org/C194995250","wikidata":"https://www.wikidata.org/wiki/Q531136","display_name":"Affordance","level":2,"score":0.9538999795913696},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6972000002861023},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6448000073432922},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5443000197410583},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5187000036239624},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.49309998750686646},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.48579999804496765},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.36899998784065247},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.36629998683929443},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3328999876976013},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.33090001344680786},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3269999921321869},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.257099986076355}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s40747-025-02169-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-025-02169-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-025-02169-0.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex & Intelligent Systems","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:39534fe6528a4eaf9bb784cadd0e2bc4","is_oa":true,"landing_page_url":"https://doaj.org/article/39534fe6528a4eaf9bb784cadd0e2bc4","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Complex & Intelligent Systems, Vol 12, Iss 1, Pp 1-15 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s40747-025-02169-0","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-025-02169-0","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-025-02169-0.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex & Intelligent Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.7643789052963257}],"awards":[{"id":"https://openalex.org/G2470284001","display_name":null,"funder_award_id":"6206113600","funder_id":"https://openalex.org/F4320335568","funder_display_name":"International Cooperation and Exchange Programme"},{"id":"https://openalex.org/G3449269236","display_name":null,"funder_award_id":"DFG TRR-169","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G5244829453","display_name":null,"funder_award_id":"TRR-169","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7226905331","display_name":null,"funder_award_id":"TRR-169","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G7857932966","display_name":null,"funder_award_id":"92048205","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323381","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956"},{"id":"https://openalex.org/F4320335568","display_name":"International Cooperation and Exchange Programme","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7117475401.pdf","grobid_xml":"https://content.openalex.org/works/W7117475401.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W2889969363","https://openalex.org/W2914996824","https://openalex.org/W2970710335","https://openalex.org/W2986303149","https://openalex.org/W3135359526","https://openalex.org/W3175450634","https://openalex.org/W3206683563","https://openalex.org/W4214627646","https://openalex.org/W4280615982","https://openalex.org/W4312270234","https://openalex.org/W4312363187","https://openalex.org/W4313003756","https://openalex.org/W4367663485","https://openalex.org/W4382366145","https://openalex.org/W4396782959","https://openalex.org/W4401414292","https://openalex.org/W4402916210","https://openalex.org/W4402961666","https://openalex.org/W4404370916","https://openalex.org/W4409346529","https://openalex.org/W4410027736","https://openalex.org/W4416750218"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Existing":[1],"task-oriented":[2,102],"grasping":[3,63],"approaches":[4],"often":[5],"rely":[6],"on":[7,41,55,121],"2D":[8],"pixel-wise":[9],"affordance":[10,88,94,111,123],"segmentation":[11],"or":[12],"predefined":[13],"part":[14],"annotations,":[15],"limiting":[16],"their":[17],"applicability":[18],"in":[19,50,135],"unstructured":[20],"3D":[21,93],"environments":[22],"and":[23,70,80,100,130,137,152],"constraining":[24],"the":[25],"grasp":[26,38,83,103,107,115,131],"planning":[27],"space.":[28,53],"To":[29],"overcome":[30],"these":[31],"limitations,":[32],"we":[33,58],"introduce":[34],"a":[35,51,60,86,101],"novel":[36],"affordance-labeled":[37],"dataset":[39],"constructed":[40],"simulation,":[42],"capturing":[43],"diverse":[44,150],"functional":[45],"interactions":[46],"across":[47,149],"object":[48],"categories":[49],"6-DoF":[52],"Building":[54],"this":[56],"foundation,":[57],"propose":[59],"unified,":[61],"language-guided":[62],"framework":[64],"that":[65,141],"takes":[66],"partial":[67],"point":[68],"clouds":[69],"natural":[71],"language":[72],"instructions":[73],"as":[74],"input":[75],"to":[76],"generate":[77],"semantically":[78],"meaningful":[79],"geometrically":[81],"feasible":[82],"poses.":[84],"Specifically,":[85],"vision-language":[87],"grounding":[89],"module":[90],"produces":[91],"dense":[92],"maps":[95],"aligned":[96],"with":[97,109],"task":[98],"semantics,":[99],"pipeline":[104],"predicts":[105],"coarse":[106,114],"candidates":[108],"implicit":[110],"cues.":[112],"The":[113],"proposals":[116],"are":[117],"subsequently":[118],"refined":[119],"based":[120],"visual":[122],"guidance,":[124],"significantly":[125],"enhancing":[126],"both":[127],"semantic":[128],"alignment":[129],"practicality.":[132],"Extensive":[133],"experiments":[134],"synthetic":[136],"real-world":[138],"scenarios":[139],"demonstrate":[140],"our":[142],"method":[143],"outperforms":[144],"state-of-the-art":[145],"approaches,":[146],"effectively":[147],"generalizing":[148],"objects":[151],"tasks.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-12-29T00:00:00"}