{"id":"https://openalex.org/W4408222769","doi":"https://doi.org/10.1109/robio64047.2024.10907650","title":"Visual Robotic Manipulation with Depth-Aware Pretraining","display_name":"Visual Robotic Manipulation with Depth-Aware Pretraining","publication_year":2024,"publication_date":"2024-12-10","ids":{"openalex":"https://openalex.org/W4408222769","doi":"https://doi.org/10.1109/robio64047.2024.10907650"},"language":"en","primary_location":{"id":"doi:10.1109/robio64047.2024.10907650","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio64047.2024.10907650","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 Biomimetics (ROBIO)","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/A5004994159","display_name":"Jinming Li","orcid":"https://orcid.org/0000-0001-8906-9191"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinming Li","raw_affiliation_strings":["School of Science, Shanghai University,Department of Mathematics,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Science, Shanghai University,Department of Mathematics,China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101782600","display_name":"Wanying Wang","orcid":"https://orcid.org/0000-0003-0765-8430"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanying Wang","raw_affiliation_strings":["School of Science, Shanghai University,Department of Mathematics,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Science, Shanghai University,Department of Mathematics,China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033203506","display_name":"Yaxin Peng","orcid":"https://orcid.org/0000-0002-2983-555X"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaxin Peng","raw_affiliation_strings":["School of Science, Shanghai University,Department of Mathematics,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Science, Shanghai University,Department of Mathematics,China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008090356","display_name":"Chaomin Shen","orcid":"https://orcid.org/0000-0001-9389-6472"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaomin Shen","raw_affiliation_strings":["School of Computer Science, East China Normal University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, East China Normal University,China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100611386","display_name":"Yichen Zhu","orcid":"https://orcid.org/0000-0003-3614-1537"},"institutions":[{"id":"https://openalex.org/I4210093653","display_name":"Midea Group (China)","ror":"https://ror.org/006fm2278","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210093653"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yichen Zhu","raw_affiliation_strings":["Midea Group,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Midea Group,China","institution_ids":["https://openalex.org/I4210093653"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102897990","display_name":"Zhiyuan Xu","orcid":"https://orcid.org/0000-0001-8955-8358"},"institutions":[{"id":"https://openalex.org/I4210093653","display_name":"Midea Group (China)","ror":"https://ror.org/006fm2278","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210093653"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyuan Xu","raw_affiliation_strings":["Midea Group,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Midea Group,China","institution_ids":["https://openalex.org/I4210093653"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"843","last_page":"850"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.98580002784729,"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":0.98580002784729,"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/T11159","display_name":"Manufacturing Process and Optimization","score":0.9836999773979187,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/T10571","display_name":"Robotic Mechanisms and Dynamics","score":0.9768999814987183,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6804841160774231},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5381897687911987},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.520825982093811},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4367946982383728},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3464406728744507}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6804841160774231},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5381897687911987},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.520825982093811},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4367946982383728},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3464406728744507}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/robio64047.2024.10907650","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robio64047.2024.10907650","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 Biomimetics (ROBIO)","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":59,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2201912979","https://openalex.org/W2594519801","https://openalex.org/W2962858109","https://openalex.org/W2991276239","https://openalex.org/W3035524453","https://openalex.org/W3159481202","https://openalex.org/W3171007011","https://openalex.org/W3172615411","https://openalex.org/W3204665606","https://openalex.org/W3204703845","https://openalex.org/W3216273127","https://openalex.org/W4214638047","https://openalex.org/W4312287667","https://openalex.org/W4313156423","https://openalex.org/W4319300750","https://openalex.org/W4322096648","https://openalex.org/W4385430451","https://openalex.org/W4385430678","https://openalex.org/W4385430679","https://openalex.org/W4386071817","https://openalex.org/W4386804659","https://openalex.org/W4401023654","https://openalex.org/W4401414095","https://openalex.org/W4401414111","https://openalex.org/W4402783855","https://openalex.org/W4403793633","https://openalex.org/W4403878024","https://openalex.org/W6739901393","https://openalex.org/W6744513255","https://openalex.org/W6744563498","https://openalex.org/W6753243525","https://openalex.org/W6763422710","https://openalex.org/W6777843581","https://openalex.org/W6785731366","https://openalex.org/W6793853427","https://openalex.org/W6798184267","https://openalex.org/W6800774826","https://openalex.org/W6802366246","https://openalex.org/W6810536332","https://openalex.org/W6810655313","https://openalex.org/W6838557027","https://openalex.org/W6843759960","https://openalex.org/W6845226490","https://openalex.org/W6846242362","https://openalex.org/W6847122809","https://openalex.org/W6847203660","https://openalex.org/W6849204483","https://openalex.org/W6849915793","https://openalex.org/W6851800889","https://openalex.org/W6852027560","https://openalex.org/W6853532984","https://openalex.org/W6855158220","https://openalex.org/W6855642159","https://openalex.org/W6862417900","https://openalex.org/W6870075455","https://openalex.org/W6872635902","https://openalex.org/W6873657567"],"related_works":["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","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Recent":[0],"work":[1],"on":[2,24,154,164],"visual":[3,21,158],"representation":[4],"learning":[5,107],"has":[6],"shown":[7],"to":[8,36,44,66,83,128],"be":[9],"efficient":[10],"for":[11,58,76,160],"robotic":[12],"manipulation":[13,68,105,139],"tasks.":[14],"However,":[15],"most":[16],"existing":[17],"works":[18],"pretrained":[19],"the":[20,31,54,133,138],"backbone":[22,60,82],"solely":[23],"2D":[25,47],"images":[26],"or":[27],"egocentric":[28],"videos,":[29],"ignoring":[30],"fact":[32],"that":[33,136,148],"robots":[34],"learn":[35,45,84],"act":[37],"in":[38,118,146],"3D":[39,64,85,100,119],"space,":[40],"which":[41],"is":[42,102],"hard":[43],"from":[46,88],"observation.":[48],"In":[49],"this":[50],"paper,":[51],"we":[52,123],"examine":[53],"effectiveness":[55,117],"of":[56],"pretraining":[57],"vision":[59],"with":[61],"public-available":[62],"large-scale":[63],"data":[65],"improve":[67],"policy":[69,106,134],"learning.":[70],"Our":[71],"method,":[72],"namely":[73],"Depth-aware":[74],"Pretraining":[75],"Robotics":[77],"(DPR),":[78],"enables":[79],"an":[80],"RGB-only":[81],"scene":[86],"representations":[87],"self-supervised":[89],"contrastive":[90],"learning,":[91],"where":[92],"depth":[93],"information":[94,101],"serves":[95],"as":[96],"auxiliary":[97],"knowledge.":[98],"No":[99],"necessary":[103],"during":[104],"and":[108,116,142,157,167],"inference,":[109],"making":[110],"our":[111,149],"model":[112,140],"enjoy":[113],"both":[114,165],"efficiency":[115],"space":[120],"manipulation.":[121],"Furthermore,":[122],"introduce":[124],"a":[125],"new":[126],"way":[127],"inject":[129],"robots'":[130],"proprioception":[131],"into":[132],"networks":[135],"makes":[137],"robust":[141],"generalizable.":[143],"We":[144],"demonstrate":[145],"experiments":[147],"proposed":[150],"framework":[151],"improves":[152],"performance":[153],"unseen":[155],"objects":[156],"environments":[159],"various":[161],"robotics":[162],"tasks":[163],"simulated":[166],"real":[168],"robots.":[169]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}