{"id":"https://openalex.org/W4416728120","doi":"https://doi.org/10.1109/lra.2025.3632069","title":"GraspControl: Text-Sketch Instruction as an Interface for Controllable Grasp Synthesis","display_name":"GraspControl: Text-Sketch Instruction as an Interface for Controllable Grasp Synthesis","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W4416728120","doi":"https://doi.org/10.1109/lra.2025.3632069"},"language":null,"primary_location":{"id":"doi:10.1109/lra.2025.3632069","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3632069","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-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/A5088114151","display_name":"Xiaopeng Wen","orcid":"https://orcid.org/0000-0001-5360-4770"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaopeng Wen","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0001-5360-4770","affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078047250","display_name":"Songtao Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songtao Tian","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073840185","display_name":"Yi Sun","orcid":"https://orcid.org/0000-0001-6086-5741"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Sun","raw_affiliation_strings":["School of Information and Communication Engineering, Dalian University of Technology, Dalian, China"],"raw_orcid":"https://orcid.org/0000-0001-6086-5741","affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Dalian University of Technology, Dalian, China","institution_ids":["https://openalex.org/I27357992"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I27357992"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.327354,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":"1","first_page":"562","last_page":"569"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9776999950408936,"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":0.9776999950408936,"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":0.003700000001117587,"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":0.0032999999821186066,"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":0.972000002861023},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.6194000244140625},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5968000292778015},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5522000193595886},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.499099999666214},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4325000047683716},{"id":"https://openalex.org/keywords/grippers","display_name":"Grippers","score":0.42250001430511475}],"concepts":[{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.972000002861023},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7534999847412109},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.6194000244140625},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5968000292778015},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5741999745368958},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5522000193595886},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.499099999666214},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4722000062465668},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4325000047683716},{"id":"https://openalex.org/C2775960376","wikidata":"https://www.wikidata.org/wiki/Q1435859","display_name":"Grippers","level":2,"score":0.42250001430511475},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40869998931884766},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.3774000108242035},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.33000001311302185},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.32919999957084656},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2851000130176544},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27459999918937683},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.25369998812675476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2025.3632069","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3632069","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4243852216","display_name":null,"funder_award_id":"U1708263","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4540967683","display_name":null,"funder_award_id":"62373075","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1794703952","https://openalex.org/W2047346158","https://openalex.org/W2083624955","https://openalex.org/W2085261163","https://openalex.org/W2145023731","https://openalex.org/W2160821342","https://openalex.org/W2888535642","https://openalex.org/W2889969363","https://openalex.org/W2962737955","https://openalex.org/W2976611405","https://openalex.org/W2986303149","https://openalex.org/W3035198432","https://openalex.org/W3153149165","https://openalex.org/W3175450634","https://openalex.org/W3207187156","https://openalex.org/W4312515528","https://openalex.org/W4312933868","https://openalex.org/W4376122412","https://openalex.org/W4380450805","https://openalex.org/W4382366145","https://openalex.org/W4385270985","https://openalex.org/W4386076215","https://openalex.org/W4387092545","https://openalex.org/W4389666604","https://openalex.org/W4396821558","https://openalex.org/W4401414292","https://openalex.org/W4404056828","https://openalex.org/W4407637743"],"related_works":[],"abstract_inverted_index":{"Large":[0],"vision-language":[1],"models":[2,137],"have":[3],"been":[4],"shown":[5],"to":[6,18,47,114,155],"perform":[7],"complex":[8,209],"tasks.":[9],"However,":[10],"aligning":[11],"language":[12,41,60,93],"instructions":[13,42,61],"with":[14,62,72,169],"object":[15,96,113,136],"visual":[16,70,109,167],"information":[17,66,71],"enable":[19],"general":[20],"inference":[21],"for":[22,128],"robotic":[23,196],"grasping":[24,175],"poses":[25,142],"a":[26,36,56,83,144,151,170],"significant":[27],"challenge.":[28],"To":[29],"tackle":[30],"this":[31],"issue,":[32],"we":[33,54,81,149],"introduce":[34],"GraspControl,":[35],"method":[37,204],"that":[38,58,202],"leverages":[39],"grasp":[40,89,92,120,129,141,162,186],"and":[43,64,69,77,94,108,138,164,194],"sketches":[44,73,90,97,121],"of":[45,51,67,74,86,111,134,177,184],"objects":[46],"control":[48],"the":[49,75,103,106,112,132,157,174,178,182],"generation":[50],"grasps.":[52],"Initially,":[53],"construct":[55],"dataset":[57],"augments":[59],"position":[63],"orientation":[65],"grasps,":[68],"gripper":[76],"target":[78],"objects.":[79],"Subsequently,":[80],"develop":[82],"model":[84],"capable":[85],"generating":[87],"2D":[88,95,119],"given":[91],"as":[98,123],"input":[99,126],"prompts,":[100],"thereby":[101],"bridging":[102],"gap":[104],"between":[105,159],"linguistic":[107],"representations":[110],"be":[115],"grasped.":[116],"These":[117],"generated":[118],"serve":[122],"an":[124],"innovative":[125],"modality":[127],"synthesis,":[130],"directing":[131],"creation":[133],"3D":[135,140,145],"corresponding":[139],"through":[143,188],"reconstruction":[146],"module.":[147],"Furthermore,":[148],"incorporate":[150],"multi-modal":[152],"attention":[153],"loss":[154],"ensure":[156],"consistency":[158],"high-level":[160],"semantic":[161],"features":[163],"intricate":[165],"low-level":[166],"features,":[168],"particular":[171],"emphasis":[172],"on":[173],"area":[176],"object.":[179],"We":[180],"evaluate":[181],"capabilities":[183],"our":[185,203],"approach":[187],"extensive":[189],"experiments":[190],"in":[191,208],"both":[192],"simulated":[193],"real-world":[195],"scenarios.":[197],"The":[198],"experimental":[199],"results":[200],"confirm":[201],"can":[205],"execute":[206],"grasps":[207],"environments.":[210]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-11-12T00:00:00"}