{"id":"https://openalex.org/W4414538317","doi":"https://doi.org/10.1109/lra.2025.3615036","title":"Depth-PC: Sim-to-Real Transfer for Zero-Shot Visual Servoing via Cross-Modal Fusion","display_name":"Depth-PC: Sim-to-Real Transfer for Zero-Shot Visual Servoing via Cross-Modal Fusion","publication_year":2025,"publication_date":"2025-09-26","ids":{"openalex":"https://openalex.org/W4414538317","doi":"https://doi.org/10.1109/lra.2025.3615036"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2025.3615036","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3615036","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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":null,"display_name":"Haoyu Zhang","orcid":"https://orcid.org/0009-0005-2591-8285"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haoyu Zhang","raw_affiliation_strings":["Research Institute of Intelligent Control and Systems, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0009-0005-2591-8285","affiliations":[{"raw_affiliation_string":"Research Institute of Intelligent Control and Systems, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115602248","display_name":"Yang Liu","orcid":"https://orcid.org/0000-0002-7240-1546"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Liu","raw_affiliation_strings":["Research Institute of Intelligent Control and Systems, Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Institute of Intelligent Control and Systems, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yimu Jiang","orcid":"https://orcid.org/0009-0009-9504-5001"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yimu Jiang","raw_affiliation_strings":["Research Institute of Intelligent Control and Systems, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0009-0009-9504-5001","affiliations":[{"raw_affiliation_string":"Research Institute of Intelligent Control and Systems, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024993361","display_name":"Weiyang Lin","orcid":"https://orcid.org/0000-0002-0493-1289"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiyang Lin","raw_affiliation_strings":["Research Institute of Intelligent Control and Systems, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0002-0493-1289","affiliations":[{"raw_affiliation_string":"Research Institute of Intelligent Control and Systems, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":null,"display_name":"Chao Ye","orcid":"https://orcid.org/0000-0003-2263-8286"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Ye","raw_affiliation_strings":["Research Institute of Intelligent Control and Systems, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0003-2263-8286","affiliations":[{"raw_affiliation_string":"Research Institute of Intelligent Control and Systems, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24469279,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"10","issue":"11","first_page":"11976","last_page":"11983"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.9973999857902527,"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":0.9973999857902527,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9962000250816345,"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/T13114","display_name":"Image Processing Techniques and Applications","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/visual-servoing","display_name":"Visual servoing","score":0.921999990940094},{"id":"https://openalex.org/keywords/servo","display_name":"Servo","score":0.6352999806404114},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6319000124931335},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5856000185012817},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5331000089645386},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45329999923706055},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4392000138759613},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.38370001316070557}],"concepts":[{"id":"https://openalex.org/C10912380","wikidata":"https://www.wikidata.org/wiki/Q527952","display_name":"Visual servoing","level":3,"score":0.921999990940094},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6974999904632568},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6644999980926514},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6618000268936157},{"id":"https://openalex.org/C107354338","wikidata":"https://www.wikidata.org/wiki/Q1937153","display_name":"Servo","level":2,"score":0.6352999806404114},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6319000124931335},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5856000185012817},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5331000089645386},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45329999923706055},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4392000138759613},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.38370001316070557},{"id":"https://openalex.org/C32731416","wikidata":"https://www.wikidata.org/wiki/Q7455930","display_name":"Servo control","level":3,"score":0.35690000653266907},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.3228999972343445},{"id":"https://openalex.org/C49503481","wikidata":"https://www.wikidata.org/wiki/Q640815","display_name":"Servomechanism","level":2,"score":0.32179999351501465},{"id":"https://openalex.org/C2780023022","wikidata":"https://www.wikidata.org/wiki/Q1338171","display_name":"Compensation (psychology)","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.30559998750686646},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.2973000109195709},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.28450000286102295},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.2671000063419342},{"id":"https://openalex.org/C2776126113","wikidata":"https://www.wikidata.org/wiki/Q1128980","display_name":"Industrial robot","level":3,"score":0.2615000009536743},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.26019999384880066}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2025.3615036","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3615036","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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/G139608838","display_name":null,"funder_award_id":"62503134","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":37,"referenced_works":["https://openalex.org/W569732077","https://openalex.org/W2031329434","https://openalex.org/W2048710758","https://openalex.org/W2082991751","https://openalex.org/W2084447079","https://openalex.org/W2116341502","https://openalex.org/W2117228865","https://openalex.org/W2124386111","https://openalex.org/W2141584146","https://openalex.org/W2145640590","https://openalex.org/W2165232124","https://openalex.org/W2167501464","https://openalex.org/W2417087373","https://openalex.org/W2560609797","https://openalex.org/W2769459570","https://openalex.org/W2788822937","https://openalex.org/W2948713068","https://openalex.org/W2963188159","https://openalex.org/W2979750740","https://openalex.org/W3003339604","https://openalex.org/W3004030350","https://openalex.org/W3034275286","https://openalex.org/W3045988483","https://openalex.org/W3090423738","https://openalex.org/W3091689308","https://openalex.org/W3107372911","https://openalex.org/W3109908659","https://openalex.org/W3131598771","https://openalex.org/W3136515919","https://openalex.org/W3171969922","https://openalex.org/W4200150166","https://openalex.org/W4214755140","https://openalex.org/W4224598146","https://openalex.org/W4238767840","https://openalex.org/W4281557677","https://openalex.org/W4401416312","https://openalex.org/W4401416910"],"related_works":[],"abstract_inverted_index":{"Visual":[0],"servoing":[1,61],"techniques":[2],"guide":[3],"robotic":[4,136],"motion":[5],"using":[6],"visual":[7,60],"information":[8,83],"to":[9,29,111,129,146],"accomplish":[10],"manipulation":[11],"tasks,":[12,103],"requiring":[13],"high":[14],"precision":[15],"and":[16,26,44,81,88,117,126],"robustness":[17],"against":[18],"noise.":[19],"Traditional":[20],"methods":[21],"often":[22],"require":[23],"prior":[24],"knowledge":[25],"are":[27],"susceptible":[28],"external":[30],"disturbances.":[31],"Learning-driven":[32],"alternatives,":[33],"while":[34,139],"promising,":[35],"frequently":[36],"struggle":[37],"with":[38,150],"the":[39,133,147,158,165],"scarcity":[40],"of":[41,84,160,167],"training":[42,67],"data":[43],"fall":[45],"short":[46],"in":[47,101],"generalization.":[48],"To":[49,78],"address":[50],"these":[51],"challenges,":[52],"we":[53,94,154],"propose":[54],"<italic":[55,85,89],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[56,86,90,175],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Depth-PC</i>,":[57],"a":[58,99,106],"novel":[59],"framework":[62],"that":[63],"leverages":[64],"decoupled":[65],"simulation-based":[66],"from":[68],"real-world":[69,118],"inference,":[70],"achieving":[71],"zero-shot":[72,141],"Sim2Real":[73,142],"transfer":[74],"for":[75,135],"servo":[76,102,137,168],"tasks.":[77,169],"exploit":[79],"spatial":[80],"geometric":[82],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">depth</i>":[87],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">point":[91],"cloud</i>":[92],"features,":[93],"introduce":[95],"cross-modal":[96],"feature":[97,162],"fusion,":[98],"first":[100],"followed":[104],"by":[105],"dedicated":[107],"Graph":[108],"Neural":[109],"Network":[110],"establish":[112],"keypoint":[113],"correspondences.":[114],"Through":[115],"simulation":[116],"experiments,":[119],"our":[120,151],"approach":[121],"demonstrates":[122],"superior":[123],"convergence":[124],"basin":[125],"accuracy":[127],"compared":[128],"SOTA":[130],"methods,":[131],"fulfilling":[132],"requirements":[134],"tasks":[138],"enabling":[140],"transfer.":[143],"In":[144],"addition":[145],"enhancements":[148],"achieved":[149],"proposed":[152],"framework,":[153],"have":[155],"also":[156],"demonstrated":[157],"effectiveness":[159],"cross-modality":[161],"fusion":[163],"within":[164],"realm":[166],"Code":[170],"is":[171],"available":[172],"at":[173],"<uri":[174],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/3nnui/Depth-PC</uri>.":[176]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}