{"id":"https://openalex.org/W4405786716","doi":"https://doi.org/10.1109/iros58592.2024.10801718","title":"RT-Grasp: Reasoning Tuning Robotic Grasping via Multi-modal Large Language Model","display_name":"RT-Grasp: Reasoning Tuning Robotic Grasping via Multi-modal Large Language Model","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405786716","doi":"https://doi.org/10.1109/iros58592.2024.10801718"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10801718","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801718","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/A5008185461","display_name":"Jinxuan Xu","orcid":"https://orcid.org/0000-0002-8182-9413"},"institutions":[{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Jinxuan Xu","raw_affiliation_strings":["Rutgers University,Department of Electrical and Computer Engineering"],"affiliations":[{"raw_affiliation_string":"Rutgers University,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I4210096112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050808028","display_name":"Shiyu Jin","orcid":"https://orcid.org/0000-0002-6475-5942"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shiyu Jin","raw_affiliation_strings":["Robotics and Autonomous Driving Lab (RAL),Baidu Research,USA"],"affiliations":[{"raw_affiliation_string":"Robotics and Autonomous Driving Lab (RAL),Baidu Research,USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106404175","display_name":"Yutian Lei","orcid":"https://orcid.org/0009-0006-5793-2513"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yutian Lei","raw_affiliation_strings":["Robotics and Autonomous Driving Lab (RAL),Baidu Research,USA"],"affiliations":[{"raw_affiliation_string":"Robotics and Autonomous Driving Lab (RAL),Baidu Research,USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100667143","display_name":"Yuqian Zhang","orcid":"https://orcid.org/0000-0002-6917-9868"},"institutions":[{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Yuqian Zhang","raw_affiliation_strings":["Rutgers University,Department of Electrical and Computer Engineering"],"affiliations":[{"raw_affiliation_string":"Rutgers University,Department of Electrical and Computer Engineering","institution_ids":["https://openalex.org/I4210096112"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101843626","display_name":"Liangjun Zhang","orcid":"https://orcid.org/0000-0001-5737-2540"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liangjun Zhang","raw_affiliation_strings":["Robotics and Autonomous Driving Lab (RAL),Baidu Research,USA"],"affiliations":[{"raw_affiliation_string":"Robotics and Autonomous Driving Lab (RAL),Baidu Research,USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5008185461"],"corresponding_institution_ids":["https://openalex.org/I4210096112"],"apc_list":null,"apc_paid":null,"fwci":2.9338,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.92414107,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7323","last_page":"7330"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9943000078201294,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9943000078201294,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9908000230789185,"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":0.9857000112533569,"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":0.8997085690498352},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7601625919342041},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6691201329231262},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3815023899078369},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1733773946762085},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.04623067378997803}],"concepts":[{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.8997085690498352},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7601625919342041},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6691201329231262},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3815023899078369},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1733773946762085},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.04623067378997803},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros58592.2024.10801718","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801718","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1999156278","https://openalex.org/W2076363786","https://openalex.org/W2089630413","https://openalex.org/W2109163007","https://openalex.org/W2123435073","https://openalex.org/W2201912979","https://openalex.org/W2600030077","https://openalex.org/W2910747522","https://openalex.org/W2953669419","https://openalex.org/W2962716343","https://openalex.org/W2962875890","https://openalex.org/W2963033241","https://openalex.org/W2963326767","https://openalex.org/W3130885760","https://openalex.org/W3204858942","https://openalex.org/W3205420310","https://openalex.org/W4285102225","https://openalex.org/W4292978855","https://openalex.org/W4360615633","https://openalex.org/W4383108457","https://openalex.org/W4383108836","https://openalex.org/W4388660746","https://openalex.org/W6755207826","https://openalex.org/W6784155536","https://openalex.org/W6791353385","https://openalex.org/W6796581206","https://openalex.org/W6801810553","https://openalex.org/W6810640255","https://openalex.org/W6810738896","https://openalex.org/W6838959477","https://openalex.org/W6839928859","https://openalex.org/W6847224448","https://openalex.org/W6850503672","https://openalex.org/W6850625674","https://openalex.org/W6851592950","https://openalex.org/W6853053110","https://openalex.org/W6853054754","https://openalex.org/W6854108904","https://openalex.org/W6854555012","https://openalex.org/W6854738657","https://openalex.org/W6854929498"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2163296013","https://openalex.org/W2743859443","https://openalex.org/W2326995835","https://openalex.org/W165915117","https://openalex.org/W2059402478","https://openalex.org/W2123347777","https://openalex.org/W2963326767"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,20,58,154,180],"Large":[3],"Language":[4],"Models":[5],"(LLMs)":[6],"have":[7],"showcased":[8],"their":[9,22,34,160],"remarkable":[10],"reasoning":[11,50,75,88],"capabilities,":[12,99],"making":[13],"them":[14],"influential":[15],"across":[16],"various":[17],"fields.":[18],"However,":[19],"robotics,":[21],"use":[23],"has":[24],"primarily":[25],"been":[26],"limited":[27],"to":[28,33,100,126,132],"manipulation":[29],"planning":[30,169],"tasks":[31,153],"due":[32],"inherent":[35],"textual":[36],"output.":[37],"This":[38,92,156],"paper":[39],"addresses":[40],"this":[41,192],"limitation":[42],"by":[43],"investigating":[44],"the":[45,49,82,118,128,145,165,176],"potential":[46,177],"of":[47,52,90,130,147,178,191],"adopting":[48],"ability":[51],"LLMs":[53,131,149,179],"for":[54,62,150],"generating":[55],"numerical":[56,103,151],"predictions":[57],"robotics":[59],"tasks,":[60],"specifically":[61],"robotic":[63,133],"grasping.":[64,134],"We":[65],"propose":[66],"Reasoning":[67,119],"Tuning,":[68],"a":[69,74],"novel":[70],"method":[71],"that":[72,108],"integrates":[73],"phase":[76],"before":[77],"prediction":[78,152],"during":[79],"training,":[80],"leveraging":[81],"extensive":[83],"prior":[84],"knowledge":[85],"and":[86,111,141,170,189],"advanced":[87],"abilities":[89],"LLMs.":[91],"approach":[93],"enables":[94],"LLMs,":[95],"notably":[96],"with":[97],"multi-modal":[98,148],"generate":[101],"accurate":[102],"outputs":[104],"like":[105],"grasp":[106],"poses":[107],"are":[109,194],"context-aware":[110],"adaptable":[112],"through":[113],"conversations.":[114],"Additionally,":[115],"we":[116],"present":[117],"Tuning":[120],"VLM":[121],"Grasp":[122],"dataset,":[123],"carefully":[124],"curated":[125],"facilitate":[127],"adaptation":[129],"Extensive":[135],"validation":[136],"on":[137,196],"both":[138],"grasping":[139],"datasets":[140],"real-world":[142],"experiments":[143],"underscores":[144],"adaptability":[146],"robotics.":[155,181],"not":[157],"only":[158],"expands":[159],"applicability":[161],"but":[162],"also":[163],"bridges":[164],"gap":[166],"between":[167],"text-based":[168],"direct":[171],"robot":[172],"control,":[173],"thereby":[174],"maximizing":[175],"Our":[182],"dataset":[183],"will":[184],"be":[185],"released.":[186],"More":[187],"details":[188],"videos":[190],"work":[193],"available":[195],"our":[197],"project":[198],"page:":[199],"https://sites.google.com/view/rt-grasp.":[200]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7}],"updated_date":"2026-03-06T13:50:29.536080","created_date":"2025-10-10T00:00:00"}