{"id":"https://openalex.org/W4405784930","doi":"https://doi.org/10.1109/iros58592.2024.10802688","title":"Imagine2Servo: Intelligent Visual Servoing with Diffusion-Driven Goal Generation for Robotic Tasks","display_name":"Imagine2Servo: Intelligent Visual Servoing with Diffusion-Driven Goal Generation for Robotic Tasks","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405784930","doi":"https://doi.org/10.1109/iros58592.2024.10802688"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10802688","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802688","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":"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/A5055361653","display_name":"Pranjali Pathre","orcid":null},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Pranjali Pathre","raw_affiliation_strings":["IIIT Hyderabad,Robotics Research Center,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIT Hyderabad,Robotics Research Center,India","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110350786","display_name":"Gunjan Gupta","orcid":null},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Gunjan Gupta","raw_affiliation_strings":["IIIT Hyderabad,Robotics Research Center,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIT Hyderabad,Robotics Research Center,India","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114184242","display_name":"Muzaffar Qureshi","orcid":"https://orcid.org/0000-0002-7569-3601"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M. Nomaan Qureshi","raw_affiliation_strings":["Carnegie Mellon University,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5096002334","display_name":"Mandyam Brunda","orcid":null},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mandyam Brunda","raw_affiliation_strings":["IIIT Hyderabad,Robotics Research Center,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIT Hyderabad,Robotics Research Center,India","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021658362","display_name":"Samarth Brahmbhatt","orcid":"https://orcid.org/0000-0002-3732-8865"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samarth Brahmbhatt","raw_affiliation_strings":["Intel Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Labs","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030758633","display_name":"K. Madhava Krishna","orcid":null},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"K. Madhava Krishna","raw_affiliation_strings":["IIIT Hyderabad,Robotics Research Center,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIT Hyderabad,Robotics Research Center,India","institution_ids":["https://openalex.org/I65181880"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3147,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.86444774,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"13466","last_page":"13472"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9983999729156494,"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"}},"topics":[{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9983999729156494,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.991100013256073,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9684000015258789,"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/visual-servoing","display_name":"Visual servoing","score":0.937703549861908},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7615923285484314},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4955328702926636},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4670003652572632},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.39974185824394226},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.35458630323410034}],"concepts":[{"id":"https://openalex.org/C10912380","wikidata":"https://www.wikidata.org/wiki/Q527952","display_name":"Visual servoing","level":3,"score":0.937703549861908},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7615923285484314},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4955328702926636},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4670003652572632},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39974185824394226},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.35458630323410034}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros58592.2024.10802688","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802688","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2167501464","https://openalex.org/W2528489519","https://openalex.org/W2961368225","https://openalex.org/W3007769740","https://openalex.org/W3009928773","https://openalex.org/W3044296014","https://openalex.org/W3091689308","https://openalex.org/W3109908659","https://openalex.org/W3203916424","https://openalex.org/W4200411144","https://openalex.org/W4312497550","https://openalex.org/W4312933868","https://openalex.org/W4313168473","https://openalex.org/W4385403811","https://openalex.org/W4386057725","https://openalex.org/W4386076215","https://openalex.org/W4390099961","https://openalex.org/W4401416102","https://openalex.org/W4402354045","https://openalex.org/W4402753888"],"related_works":["https://openalex.org/W2107326529","https://openalex.org/W4293869118","https://openalex.org/W2118183560","https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674"],"abstract_inverted_index":{"Visual":[0],"servoing,":[1],"the":[2,18,34,43,54,88,118,155,164,169,183],"method":[3],"of":[4,20,45,90,147,157,168,176,185],"controlling":[5],"robot":[6],"motion":[7],"through":[8],"feedback":[9,57,136],"from":[10,58],"visual":[11,76,91,158,186],"sensors,":[12],"has":[13],"seen":[14],"significant":[15],"advancements":[16],"with":[17,126],"integration":[19],"optical":[21],"flow-based":[22],"methods.":[23],"However,":[24],"its":[25],"application":[26,146],"remains":[27],"limited":[28],"by":[29,79],"inherent":[30],"challenges,":[31],"such":[32],"as":[33],"necessity":[35],"for":[36,87,137],"a":[37,59,110,144,174,179],"target":[38,51,130],"image":[39,71,131,148],"at":[40,120],"test":[41],"time,":[42],"requirement":[44],"substantial":[46],"overlap":[47,132],"between":[48],"initial":[49,128],"and":[50,53,102,129,133,166],"images,":[52],"reliance":[55],"on":[56],"single":[60],"camera.":[61],"This":[62,84],"paper":[63],"introduces":[64],"Imagine2Servo\u2020,":[65],"an":[66],"innovative":[67],"approach":[68],"leveraging":[69],"diffusion-based":[70],"editing":[72],"techniques":[73],"to":[74,150],"enhance":[75],"servoing":[77,92,123,159],"algorithms":[78],"generating":[80],"intermediate":[81],"goal":[82,106],"images.":[83,107],"methodology":[85],"allows":[86],"extension":[89],"applications":[93],"beyond":[94],"traditional":[95],"constraints,":[96],"enabling":[97],"tasks":[98],"like":[99],"long-range":[100],"navigation":[101],"manipulation":[103],"without":[104],"predefined":[105],"We":[108],"propose":[109],"pipeline":[111],"that":[112],"synthesizes":[113],"subgoal":[114],"images":[115],"grounded":[116],"in":[117,124,172,182],"task":[119,139],"hand,":[121],"facilitating":[122],"scenarios":[125],"minimal":[127],"integrating":[134],"multi-camera":[135],"comprehensive":[138],"execution.":[140],"Our":[141],"contributions":[142],"demonstrate":[143],"novel":[145],"generation":[149],"robotic":[151],"control,":[152],"significantly":[153],"broadening":[154],"capabilities":[156],"systems.":[160],"Real-world":[161],"experiments":[162],"validate":[163],"effectiveness":[165],"versatility":[167],"Imagine2Servo":[170],"framework":[171],"accomplishing":[173],"variety":[175],"tasks,":[177],"marking":[178],"notable":[180],"advancement":[181],"field":[184],"servoing.":[187]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
