{"id":"https://openalex.org/W4389665522","doi":"https://doi.org/10.1109/iros55552.2023.10342009","title":"IOSG: Image-Driven Object Searching and Grasping","display_name":"IOSG: Image-Driven Object Searching and Grasping","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4389665522","doi":"https://doi.org/10.1109/iros55552.2023.10342009"},"language":"en","primary_location":{"id":"doi:10.1109/iros55552.2023.10342009","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10342009","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 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/A5088122096","display_name":"Houjian Yu","orcid":"https://orcid.org/0000-0001-8869-5078"},"institutions":[{"id":"https://openalex.org/I2800403580","display_name":"University of Minnesota System","ror":"https://ror.org/03grvy078","country_code":"US","type":"education","lineage":["https://openalex.org/I2800403580"]},{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Houjian Yu","raw_affiliation_strings":["Univ. of Minnesota,The Department of Electrical and Computer Engineering,Minneapolis,USA","The Department of Electrical and Computer Engineering, Univ. of Minnesota, Minneapolis, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. of Minnesota,The Department of Electrical and Computer Engineering,Minneapolis,USA","institution_ids":["https://openalex.org/I130238516","https://openalex.org/I2800403580"]},{"raw_affiliation_string":"The Department of Electrical and Computer Engineering, Univ. of Minnesota, Minneapolis, USA","institution_ids":["https://openalex.org/I130238516"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022469639","display_name":"Xibai Lou","orcid":"https://orcid.org/0009-0006-4242-847X"},"institutions":[{"id":"https://openalex.org/I2800403580","display_name":"University of Minnesota System","ror":"https://ror.org/03grvy078","country_code":"US","type":"education","lineage":["https://openalex.org/I2800403580"]},{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xibai Lou","raw_affiliation_strings":["Univ. of Minnesota,The Department of Electrical and Computer Engineering,Minneapolis,USA","The Department of Electrical and Computer Engineering, Univ. of Minnesota, Minneapolis, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. of Minnesota,The Department of Electrical and Computer Engineering,Minneapolis,USA","institution_ids":["https://openalex.org/I130238516","https://openalex.org/I2800403580"]},{"raw_affiliation_string":"The Department of Electrical and Computer Engineering, Univ. of Minnesota, Minneapolis, USA","institution_ids":["https://openalex.org/I130238516"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100397616","display_name":"Yang Yang","orcid":"https://orcid.org/0000-0002-5070-4511"},"institutions":[{"id":"https://openalex.org/I2800403580","display_name":"University of Minnesota System","ror":"https://ror.org/03grvy078","country_code":"US","type":"education","lineage":["https://openalex.org/I2800403580"]},{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang Yang","raw_affiliation_strings":["Univ. of Minnesota,The Department of Computer Science and Engineering,Minneapolis,USA","The Department of Computer Science and Engineering, Univ. of Minnesota, Minneapolis, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. of Minnesota,The Department of Computer Science and Engineering,Minneapolis,USA","institution_ids":["https://openalex.org/I130238516","https://openalex.org/I2800403580"]},{"raw_affiliation_string":"The Department of Computer Science and Engineering, Univ. of Minnesota, Minneapolis, USA","institution_ids":["https://openalex.org/I130238516"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057994317","display_name":"Changhyun Choi","orcid":"https://orcid.org/0000-0003-4715-3576"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]},{"id":"https://openalex.org/I2800403580","display_name":"University of Minnesota System","ror":"https://ror.org/03grvy078","country_code":"US","type":"education","lineage":["https://openalex.org/I2800403580"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Changhyun Choi","raw_affiliation_strings":["Univ. of Minnesota,The Department of Electrical and Computer Engineering,Minneapolis,USA","The Department of Electrical and Computer Engineering, Univ. of Minnesota, Minneapolis, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. of Minnesota,The Department of Electrical and Computer Engineering,Minneapolis,USA","institution_ids":["https://openalex.org/I130238516","https://openalex.org/I2800403580"]},{"raw_affiliation_string":"The Department of Electrical and Computer Engineering, Univ. of Minnesota, Minneapolis, USA","institution_ids":["https://openalex.org/I130238516"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5088122096"],"corresponding_institution_ids":["https://openalex.org/I130238516","https://openalex.org/I2800403580"],"apc_list":null,"apc_paid":null,"fwci":1.2892,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.82941138,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3145","last_page":"3152"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9991999864578247,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9987999796867371,"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":0.8367394208908081},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.810100793838501},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.7306462526321411},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6904033422470093},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6659778356552124},{"id":"https://openalex.org/keywords/clutter","display_name":"Clutter","score":0.650604248046875},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6292605400085449},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6263980865478516},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6044137477874756},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4891557991504669},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.45222076773643494},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4454529881477356},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.42479759454727173},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3328269124031067},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08165013790130615}],"concepts":[{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.8367394208908081},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.810100793838501},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.7306462526321411},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6904033422470093},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6659778356552124},{"id":"https://openalex.org/C132094186","wikidata":"https://www.wikidata.org/wiki/Q641585","display_name":"Clutter","level":3,"score":0.650604248046875},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6292605400085449},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6263980865478516},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6044137477874756},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4891557991504669},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.45222076773643494},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4454529881477356},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.42479759454727173},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3328269124031067},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08165013790130615},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros55552.2023.10342009","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10342009","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4595098722","display_name":null,"funder_award_id":"2143730","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1665214252","https://openalex.org/W2019681680","https://openalex.org/W2082511574","https://openalex.org/W2145339207","https://openalex.org/W2158698691","https://openalex.org/W2194775991","https://openalex.org/W2598634450","https://openalex.org/W2601450892","https://openalex.org/W2605102758","https://openalex.org/W2918333121","https://openalex.org/W2962793652","https://openalex.org/W2963341924","https://openalex.org/W2964105864","https://openalex.org/W3004047800","https://openalex.org/W3004091482","https://openalex.org/W3089580269","https://openalex.org/W3090822776","https://openalex.org/W3098945452","https://openalex.org/W3099587965","https://openalex.org/W3132114951","https://openalex.org/W3174849255","https://openalex.org/W3176770340","https://openalex.org/W3205613184","https://openalex.org/W3205684050","https://openalex.org/W3205918749","https://openalex.org/W3207181464","https://openalex.org/W3210327237","https://openalex.org/W4225947020","https://openalex.org/W4294891514","https://openalex.org/W4312284415","https://openalex.org/W4312615341","https://openalex.org/W6631190155","https://openalex.org/W6637242042","https://openalex.org/W6638667902","https://openalex.org/W6717697761","https://openalex.org/W6735236233","https://openalex.org/W6735531217","https://openalex.org/W6755020528","https://openalex.org/W6783596713","https://openalex.org/W6785308759"],"related_works":["https://openalex.org/W2163296013","https://openalex.org/W2743859443","https://openalex.org/W2326995835","https://openalex.org/W165915117","https://openalex.org/W2059402478","https://openalex.org/W2106002764","https://openalex.org/W3109712509","https://openalex.org/W1579998189","https://openalex.org/W2172615727","https://openalex.org/W4387272257"],"abstract_inverted_index":{"When":[0],"robots":[1],"retrieve":[2,105,183],"specific":[3],"objects":[4,16],"from":[5,186],"cluttered":[6],"scenes,":[7],"such":[8,55],"as":[9],"home":[10],"and":[11,34,65,82,100,104,143,148,180,199,210,217,223],"warehouse":[12],"environments,":[13],"the":[14,51,63,92,120,123,131,135,139,157,170,175,184,187,232],"target":[15,32,52,71,98,158,171,185],"are":[17,25],"often":[18],"partially":[19],"occluded":[20,165],"or":[21,46,164],"completely":[22],"hidden.":[23],"Robots":[24],"thus":[26],"required":[27],"to":[28,49,61,68,102,118,182,201,237],"search,":[29],"identify":[30],"a":[31,87,96,109,115,128,202,208,228],"object,":[33],"successfully":[35],"grasp":[36,149],"it.":[37,106],"Preceding":[38],"works":[39],"have":[40],"relied":[41],"on":[42,215,227],"pre-trained":[43],"object":[44,99,159,172],"recognition":[45],"segmentation":[47],"models":[48,64],"find":[50,69,103],"object.":[53],"However,":[54],"methods":[56],"require":[57],"laborious":[58],"manual":[59],"annotations":[60],"train":[62],"even":[66],"fail":[67],"novel":[70,97,124],"objects.":[72,168],"In":[73],"this":[74],"paper,":[75],"we":[76],"propose":[77],"an":[78],"Image-driven":[79],"Object":[80],"Searching":[81],"Grasping":[83],"(IOSG)":[84],"approach":[85],"where":[86],"robot":[88,230],"is":[89,153,162,173,192],"provided":[90],"with":[91,194],"reference":[93],"image":[94],"of":[95,122],"tasked":[101],"We":[107],"design":[108],"Target":[110],"Similarity":[111],"Network":[112],"that":[113],"generates":[114],"probability":[116],"map":[117],"infer":[119],"location":[121],"target.":[125],"IOSG":[126],"learns":[127],"hierarchical":[129],"policy;":[130],"high-level":[132],"policy":[133],"predicts":[134],"subtask":[136],"type,":[137],"whereas":[138],"low-level":[140],"policies,":[141],"explorer":[142,152],"coordinator,":[144],"generate":[145],"effective":[146],"push":[147],"actions.":[150],"The":[151,189],"responsible":[154],"for":[155,231,241],"searching":[156],"when":[160],"it":[161],"hidden":[163],"by":[166],"other":[167],"Once":[169],"found,":[174],"coordinator":[176],"conducts":[177],"target-oriented":[178],"pushing":[179],"grasping":[181],"clutter.":[188],"proposed":[190],"pipeline":[191],"trained":[193],"full":[195],"self-supervision":[196],"in":[197,220],"simulation":[198,221],"applied":[200],"real":[203,229],"environment.":[204],"Our":[205],"model":[206],"achieves":[207],"96.0%":[209],"94.5%":[211],"task":[212],"success":[213,225],"rate":[214,226],"coordination":[216],"exploration":[218],"tasks":[219],"respectively,":[222],"85.0%":[224],"search-and-grasp":[233],"task.":[234],"Please":[235],"refer":[236],"our":[238],"project":[239],"page":[240],"more":[242],"information:":[243],"https://z.umn.edu/iosg.":[244]},"counts_by_year":[{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":2}],"updated_date":"2026-05-03T08:25:01.440150","created_date":"2025-10-10T00:00:00"}