{"id":"https://openalex.org/W4401416843","doi":"https://doi.org/10.1109/icra57147.2024.10610690","title":"RGBManip: Monocular Image-based Robotic Manipulation through Active Object Pose Estimation","display_name":"RGBManip: Monocular Image-based Robotic Manipulation through Active Object Pose Estimation","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401416843","doi":"https://doi.org/10.1109/icra57147.2024.10610690"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10610690","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610690","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","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/A5056159007","display_name":"Boshi An","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Boshi An","raw_affiliation_strings":["Peking University and National Key Laboratory for Multimedia Information Processing,Hyperplane Lab, School of CS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University and National Key Laboratory for Multimedia Information Processing,Hyperplane Lab, School of CS","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080033977","display_name":"Yiran Geng","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiran Geng","raw_affiliation_strings":["Peking University and National Key Laboratory for Multimedia Information Processing,Hyperplane Lab, School of CS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University and National Key Laboratory for Multimedia Information Processing,Hyperplane Lab, School of CS","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102003705","display_name":"Kai Chen","orcid":"https://orcid.org/0000-0002-5028-2603"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kai Chen","raw_affiliation_strings":["The Chinese University of Hong Kong,Department of Computer Science and Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012981856","display_name":"Xiaoqi Li","orcid":"https://orcid.org/0000-0001-8855-7759"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoqi Li","raw_affiliation_strings":["Peking University and National Key Laboratory for Multimedia Information Processing,Hyperplane Lab, School of CS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University and National Key Laboratory for Multimedia Information Processing,Hyperplane Lab, School of CS","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090516040","display_name":"Qi Dou","orcid":"https://orcid.org/0000-0002-3416-9950"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Qi Dou","raw_affiliation_strings":["The Chinese University of Hong Kong,Department of Computer Science and Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100709866","display_name":"Hao Dong","orcid":"https://orcid.org/0000-0002-5101-7430"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Dong","raw_affiliation_strings":["Peking University and National Key Laboratory for Multimedia Information Processing,Hyperplane Lab, School of CS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University and National Key Laboratory for Multimedia Information Processing,Hyperplane Lab, School of CS","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7748","last_page":"7755"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9998999834060669,"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":0.9998999834060669,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T10868","display_name":"Soft Robotics and Applications","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.8273413181304932},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.8226385116577148},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.7799904346466064},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7274917364120483},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.5913630723953247},{"id":"https://openalex.org/keywords/3d-pose-estimation","display_name":"3D pose estimation","score":0.5871320962905884},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5173851251602173},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4500555992126465},{"id":"https://openalex.org/keywords/monocular-vision","display_name":"Monocular vision","score":0.4345815181732178}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.8273413181304932},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.8226385116577148},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.7799904346466064},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7274917364120483},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.5913630723953247},{"id":"https://openalex.org/C36613465","wikidata":"https://www.wikidata.org/wiki/Q4636322","display_name":"3D pose estimation","level":3,"score":0.5871320962905884},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5173851251602173},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4500555992126465},{"id":"https://openalex.org/C158829959","wikidata":"https://www.wikidata.org/wiki/Q1640606","display_name":"Monocular vision","level":2,"score":0.4345815181732178}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10610690","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10610690","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"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":42,"referenced_works":["https://openalex.org/W2539321","https://openalex.org/W569478347","https://openalex.org/W2412454633","https://openalex.org/W2736601468","https://openalex.org/W2885546722","https://openalex.org/W2949924544","https://openalex.org/W2961368225","https://openalex.org/W2962793285","https://openalex.org/W2963892972","https://openalex.org/W2985029272","https://openalex.org/W3035624836","https://openalex.org/W3089874271","https://openalex.org/W3100922749","https://openalex.org/W3107992529","https://openalex.org/W3120441392","https://openalex.org/W3193686508","https://openalex.org/W3199614037","https://openalex.org/W3202459445","https://openalex.org/W3204859697","https://openalex.org/W3208372443","https://openalex.org/W3216834690","https://openalex.org/W4200150166","https://openalex.org/W4206944021","https://openalex.org/W4220747123","https://openalex.org/W4283785166","https://openalex.org/W4287017924","https://openalex.org/W4313027996","https://openalex.org/W4320165654","https://openalex.org/W4383108731","https://openalex.org/W4383109008","https://openalex.org/W4383109669","https://openalex.org/W4386065846","https://openalex.org/W4390873470","https://openalex.org/W4390874575","https://openalex.org/W4394671432","https://openalex.org/W6687484953","https://openalex.org/W6741002519","https://openalex.org/W6783508354","https://openalex.org/W6799458897","https://openalex.org/W6800089562","https://openalex.org/W6802704039","https://openalex.org/W6849915793"],"related_works":["https://openalex.org/W4253893311","https://openalex.org/W3089306886","https://openalex.org/W2113785214","https://openalex.org/W2798721181","https://openalex.org/W3201205132","https://openalex.org/W3213997683","https://openalex.org/W4312694060","https://openalex.org/W4386075737","https://openalex.org/W4307623796","https://openalex.org/W4394784820"],"abstract_inverted_index":{"Robotic":[0],"manipulation":[1,100,135,167,182,195],"requires":[2],"accurate":[3],"perception":[4],"of":[5,41,65,141,210],"the":[6,63,66,71,110,117,123,128,134,139,166,181,207],"environment,":[7],"which":[8,145],"poses":[9],"a":[10,175,188],"significant":[11],"challenge":[12],"due":[13,61],"to":[14,62,125,179],"its":[15],"inherent":[16],"complexity":[17],"and":[18,27,58,84,156,194,203],"constantly":[19],"changing":[20],"nature.":[21],"In":[22],"this":[23,120,171],"context,":[24],"RGB":[25,74],"image":[26],"point-cloud":[28,49],"observations":[29,50],"are":[30],"two":[31],"commonly":[32],"used":[33],"modalities":[34,43],"in":[35,78,200],"visual-based":[36],"robotic":[37,89,99,224],"manipulation,":[38],"but":[39],"each":[40],"these":[42,93],"have":[44],"their":[45],"own":[46],"limitations.":[47],"Commercial":[48],"often":[51],"suffer":[52],"from":[53,130,154],"issues":[54],"like":[55],"sparse":[56],"sampling":[57],"noisy":[59],"output":[60],"limits":[64],"emission-reception":[67],"imaging":[68],"principle.":[69],"On":[70],"other":[72],"hand,":[73],"images,":[75],"while":[76],"rich":[77],"texture":[79],"information,":[80],"lack":[81],"essential":[82],"depth":[83],"3D":[85],"information":[86],"crucial":[87],"for":[88,149,228],"manipulation.":[90,150,225],"To":[91,169],"mitigate":[92],"challenges,":[94],"we":[95,173],"propose":[96],"an":[97,104],"image-only":[98],"framework":[101],"that":[102,215],"leverages":[103],"eye-on-hand":[105],"monocular":[106],"camera":[107,121],"installed":[108],"on":[109,222],"robot\u2019s":[111],"parallel":[112],"gripper.":[113],"By":[114],"moving":[115],"with":[116,184],"robot":[118],"gripper,":[119],"gains":[122],"ability":[124],"actively":[126],"perceive":[127],"object":[129,143],"multiple":[131],"perspectives":[132],"during":[133],"process.":[136],"This":[137],"enables":[138],"estimation":[140],"6D":[142,191],"poses,":[144],"can":[146],"be":[147],"utilized":[148],"While,":[151],"obtaining":[152],"images":[153],"more":[155,229],"diverse":[157],"viewpoints":[158],"typically":[159],"improves":[160],"pose":[161,192],"estimation,":[162],"it":[163],"also":[164],"increases":[165],"time.":[168],"address":[170],"trade-off,":[172],"employ":[174],"reinforcement":[176],"learning":[177],"policy":[178],"synchronize":[180],"strategy":[183],"active":[185],"perception,":[186],"achieving":[187],"balance":[189],"between":[190],"accuracy":[193],"efficiency.":[196],"Our":[197],"experimental":[198],"results":[199],"both":[201],"simulated":[202],"real-world":[204],"environments":[205],"showcase":[206],"state-of-the-art":[208],"effectiveness":[209],"our":[211,216],"approach.":[212],"We":[213],"believe":[214],"method":[217],"will":[218],"inspire":[219],"further":[220],"research":[221],"real-world-oriented":[223],"See":[226],"https://rgbmanip.github.io/":[227],"details.":[230]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}