{"id":"https://openalex.org/W4416747768","doi":"https://doi.org/10.1109/iros60139.2025.11246481","title":"PhyGrasp: Generalizing Robotic Grasping with Physics-informed Large Multimodal Models","display_name":"PhyGrasp: Generalizing Robotic Grasping with Physics-informed Large Multimodal Models","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416747768","doi":"https://doi.org/10.1109/iros60139.2025.11246481"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246481","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246481","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5025330943","display_name":"Dingkun Guo","orcid":null},"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":"Dingkun Guo","raw_affiliation_strings":["University of California,Department of Mechanical Engineering,Berkeley,USA,94720"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Department of Mechanical Engineering,Berkeley,USA,94720","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066942670","display_name":"Yuqi Xiang","orcid":null},"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":"Yuqi Xiang","raw_affiliation_strings":["University of California,Department of Mechanical Engineering,Berkeley,USA,94720"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Department of Mechanical Engineering,Berkeley,USA,94720","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100929934","display_name":"Shuqi Zhao","orcid":null},"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":"Shuqi Zhao","raw_affiliation_strings":["University of California,Department of Mechanical Engineering,Berkeley,USA,94720"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Department of Mechanical Engineering,Berkeley,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":["University of California,Department of Mechanical Engineering,Berkeley,USA,94720"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Department of Mechanical Engineering,Berkeley,USA,94720","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","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":["University of California,Department of Mechanical Engineering,Berkeley,USA,94720"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Department of Mechanical Engineering,Berkeley,USA,94720","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022382771","display_name":"Mingyu Ding","orcid":"https://orcid.org/0000-0001-6556-8359"},"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":"Mingyu Ding","raw_affiliation_strings":["University of California,Department of Mechanical Engineering,Berkeley,USA,94720"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Department of Mechanical Engineering,Berkeley,USA,94720","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":null,"display_name":"Wei Zhan","orcid":null},"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":"Wei Zhan","raw_affiliation_strings":["University of California,Department of Mechanical Engineering,Berkeley,USA,94720"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Department of Mechanical Engineering,Berkeley,USA,94720","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"14915","last_page":"14922"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9065999984741211,"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":0.9065999984741211,"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":0.051899999380111694,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.007799999788403511,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6538000106811523},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6172999739646912},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5745999813079834},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5533000230789185},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5127999782562256},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.47940000891685486},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.4307999908924103},{"id":"https://openalex.org/keywords/natural-language-understanding","display_name":"Natural language understanding","score":0.4043999910354614},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3912999927997589}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7484999895095825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6710000038146973},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6538000106811523},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6172999739646912},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5745999813079834},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5533000230789185},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5127999782562256},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.47940000891685486},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4433000087738037},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.4307999908924103},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.4043999910354614},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3912999927997589},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3702000081539154},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36980000138282776},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.367900013923645},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.3488999903202057},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.34200000762939453},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.31369999051094055},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.30809998512268066},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.26820001006126404},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C131979681","wikidata":"https://www.wikidata.org/wiki/Q1899648","display_name":"Point cloud","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C2993724205","wikidata":"https://www.wikidata.org/wiki/Q315","display_name":"Human language","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246481","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246481","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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":38,"referenced_works":["https://openalex.org/W1510835000","https://openalex.org/W1920022804","https://openalex.org/W2098304071","https://openalex.org/W2109163007","https://openalex.org/W2211722331","https://openalex.org/W2600030077","https://openalex.org/W2613576910","https://openalex.org/W2789839425","https://openalex.org/W2798897443","https://openalex.org/W2910474428","https://openalex.org/W2950069298","https://openalex.org/W2963294969","https://openalex.org/W2963503775","https://openalex.org/W2963677766","https://openalex.org/W2986303149","https://openalex.org/W3035198432","https://openalex.org/W3164862896","https://openalex.org/W3175388581","https://openalex.org/W3204858942","https://openalex.org/W3207349876","https://openalex.org/W4382366145","https://openalex.org/W4383097638","https://openalex.org/W4383108296","https://openalex.org/W4383108457","https://openalex.org/W4383108895","https://openalex.org/W4385430679","https://openalex.org/W4386001306","https://openalex.org/W4386065742","https://openalex.org/W4386247688","https://openalex.org/W4389520366","https://openalex.org/W4390874280","https://openalex.org/W4401416532","https://openalex.org/W4401417048","https://openalex.org/W4402354003","https://openalex.org/W4402727764","https://openalex.org/W4402754134","https://openalex.org/W4402951641","https://openalex.org/W4404446892"],"related_works":[],"abstract_inverted_index":{"Robotic":[0],"grasping,":[1,82],"crucial":[2],"for":[3],"robot":[4],"interaction":[5],"with":[6,10,25,127,138,142],"objects,":[7],"still":[8],"struggles":[9],"counter-intuitive":[11],"or":[12],"long-tailed":[13,173],"scenarios":[14],"like":[15],"uncommon":[16],"materials":[17],"and":[18,34,45,55,90,108,146,160,186],"shapes.":[19],"Humans,":[20],"however,":[21],"intuitively":[22],"adjust":[23],"grasps":[24],"their":[26,150],"physics-informed":[27],"interpretations":[28],"of":[29,77,105],"the":[30,75,84,102,114,158,162],"object,":[31],"using":[32,59],"visual":[33],"linguistic":[35],"cues.":[36],"This":[37],"work":[38],"introduces":[39],"PhyGrasp,":[40,132],"a":[41,60,135],"large":[42],"multimodal":[43],"model":[44],"dataset":[46,136],"that":[47,125,166],"enhance":[48],"robotic":[49],"manipulation":[50],"by":[51],"combining":[52],"natural":[53],"language":[54,68,116,152],"3D":[56,85],"point":[57],"clouds":[58],"bridge":[61],"module":[62],"to":[63,99],"integrate":[64],"these":[65,93],"inputs.":[66],"The":[67],"modality":[69,86],"exhibits":[70],"robust":[71],"reasoning":[72],"capabilities":[73],"concerning":[74],"impacts":[76],"diverse":[78],"physical":[79,103,144],"properties":[80,104,145],"on":[81,161,190],"while":[83],"comprehends":[87],"object":[88,106,140],"shapes":[89],"parts.":[91],"With":[92],"two":[94],"capabilities,":[95],"PhyGrasp":[96,167],"is":[97],"able":[98],"accurately":[100],"assess":[101],"parts":[107],"determine":[109],"optimal":[110],"grasping":[111,123],"poses.":[112],"Additionally,":[113],"model\u2019s":[115],"comprehension":[117],"enables":[118],"human":[119,128,147],"instruction":[120],"interpretation,":[121],"generating":[122],"poses":[124],"align":[126],"preferences.":[129],"To":[130],"train":[131],"we":[133],"construct":[134],"PhyPartNet":[137],"195K":[139],"instances":[141],"varying":[143],"preferences,":[148],"alongside":[149],"corresponding":[151],"descriptions.":[153],"Extensive":[154],"experiments":[155],"conducted":[156],"in":[157,172,179],"simulation":[159],"real":[163],"robots":[164],"demonstrate":[165],"achieves":[168],"state-of-the-art":[169],"performance,":[170],"particularly":[171],"cases,":[174],"e.g.,":[175],"about":[176],"10%":[177],"improvement":[178],"success":[180],"rate":[181],"over":[182],"GraspNet.":[183],"More":[184],"demos":[185],"information":[187],"are":[188],"available":[189],"https://sites.google.com/view/phygrasp.":[191]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-28T00:00:00"}