{"id":"https://openalex.org/W4407403532","doi":"https://doi.org/10.1109/lra.2025.3541334","title":"Observe Then Act: Asynchronous Active Vision-Action Model for Robotic Manipulation","display_name":"Observe Then Act: Asynchronous Active Vision-Action Model for Robotic Manipulation","publication_year":2025,"publication_date":"2025-02-12","ids":{"openalex":"https://openalex.org/W4407403532","doi":"https://doi.org/10.1109/lra.2025.3541334"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2025.3541334","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3541334","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":"https://openalex.org/A5112945982","display_name":"Guokang Wang","orcid":"https://orcid.org/0009-0006-2972-0863"},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Guokang Wang","raw_affiliation_strings":["School of Electrical and Information Engineering, Zhengzhou University, Zhengzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Zhengzhou University, Zhengzhou, China","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108080156","display_name":"Hang Li","orcid":"https://orcid.org/0009-0001-2667-8843"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Li","raw_affiliation_strings":["School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100699732","display_name":"Shuyuan Zhang","orcid":"https://orcid.org/0000-0002-9297-4333"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuyuan Zhang","raw_affiliation_strings":["School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101833400","display_name":"Di Guo","orcid":"https://orcid.org/0000-0002-9816-0103"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Di Guo","raw_affiliation_strings":["School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006721216","display_name":"Yanhong Liu","orcid":"https://orcid.org/0000-0002-7349-5871"},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanhong Liu","raw_affiliation_strings":["School of Electrical and Information Engineering, Zhengzhou University, Zhengzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Zhengzhou University, Zhengzhou, China","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041101317","display_name":"Huaping Liu","orcid":"https://orcid.org/0000-0002-4042-6044"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaping Liu","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5112945982"],"corresponding_institution_ids":["https://openalex.org/I38877650"],"apc_list":null,"apc_paid":null,"fwci":5.1809,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.95457896,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"10","issue":"4","first_page":"3422","last_page":"3429"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11687","display_name":"Teleoperation and Haptic Systems","score":0.8159000277519226,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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/T11687","display_name":"Teleoperation and Haptic Systems","score":0.8159000277519226,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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/T10653","display_name":"Robot Manipulation and Learning","score":0.7337999939918518,"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/asynchronous-communication","display_name":"Asynchronous communication","score":0.639236330986023},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6158421635627747},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5560420155525208},{"id":"https://openalex.org/keywords/active-vision","display_name":"Active vision","score":0.43195199966430664},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43187570571899414},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.42258214950561523},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4033563733100891},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07903146743774414},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07662683725357056}],"concepts":[{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.639236330986023},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6158421635627747},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5560420155525208},{"id":"https://openalex.org/C193611912","wikidata":"https://www.wikidata.org/wiki/Q4677596","display_name":"Active vision","level":2,"score":0.43195199966430664},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43187570571899414},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.42258214950561523},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4033563733100891},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07903146743774414},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07662683725357056},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2025.3541334","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3541334","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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2006683033","https://openalex.org/W2016711711","https://openalex.org/W2464708700","https://openalex.org/W2963926543","https://openalex.org/W2967729293","https://openalex.org/W3007769740","https://openalex.org/W3090901006","https://openalex.org/W3174849255","https://openalex.org/W3194662286","https://openalex.org/W4225947020","https://openalex.org/W4226036061","https://openalex.org/W4243970992","https://openalex.org/W4287181769","https://openalex.org/W4385430519","https://openalex.org/W4389667206","https://openalex.org/W4390874087","https://openalex.org/W4401413837","https://openalex.org/W4401414496","https://openalex.org/W4401664900","https://openalex.org/W4402715959","https://openalex.org/W4402716331","https://openalex.org/W4402772268","https://openalex.org/W4405786804","https://openalex.org/W6752007561","https://openalex.org/W6752380930","https://openalex.org/W6755305357","https://openalex.org/W6775293196","https://openalex.org/W6790830454","https://openalex.org/W6803600046","https://openalex.org/W6839404800","https://openalex.org/W6843759960","https://openalex.org/W6852775642","https://openalex.org/W6853439583","https://openalex.org/W6856544564","https://openalex.org/W6873303141"],"related_works":["https://openalex.org/W2912872656","https://openalex.org/W4246210236","https://openalex.org/W1571999748","https://openalex.org/W1982241259","https://openalex.org/W2169063751","https://openalex.org/W2098049229","https://openalex.org/W3023196456","https://openalex.org/W2123189663","https://openalex.org/W2100016924","https://openalex.org/W1891287906"],"abstract_inverted_index":{"In":[0,30],"real-world":[1],"scenarios,":[2],"many":[3],"robotic":[4,38],"manipulation":[5,39,104,136],"tasks":[6,115],"are":[7],"hindered":[8],"by":[9],"occlusions":[10],"and":[11,44,67,99,108],"limited":[12,41],"fields":[13],"of":[14,37],"view,":[15],"posing":[16],"significant":[17],"challenges":[18],"for":[19],"passive":[20],"observation-based":[21],"models":[22],"that":[23,121],"rely":[24],"on":[25,95,112],"fixed":[26],"or":[27],"wrist-mounted":[28],"cameras.":[29],"this":[31],"letter,":[32],"we":[33],"investigate":[34],"the":[35,82,92,96,102],"problem":[36],"under":[40],"visual":[42,133],"observation":[43],"propose":[45],"a":[46,56,62,71,86],"task-driven":[47],"asynchronous":[48],"active":[49],"vision-action":[50],"model.":[51],"Our":[52],"model":[53,111,123],"serially":[54],"connects":[55],"camera":[57,88],"Next-Best-View":[58],"(NBV)":[59],"policy":[60],"with":[61],"gripper":[63],"Next-Best-Pose":[64],"(NBP)":[65],"policy,":[66],"trains":[68],"them":[69],"in":[70,116,131,135],"sensor-motor":[72],"coordination":[73],"framework":[74],"using":[75],"few-shot":[76],"reinforcement":[77],"learning.":[78],"This":[79],"approach":[80],"enables":[81],"agent":[83],"to":[84,89],"reposition":[85],"third-person":[87],"actively":[90],"observe":[91],"environment":[93],"based":[94],"task":[97],"goal,":[98],"subsequently":[100],"determine":[101],"appropriate":[103],"actions.":[105],"We":[106],"trained":[107],"evaluated":[109],"our":[110,122],"8":[113],"viewpoint-constrained":[114],"RLBench.":[117],"The":[118],"results":[119],"demonstrate":[120],"consistently":[124],"outperforms":[125],"baseline":[126],"algorithms,":[127],"showcasing":[128],"its":[129],"effectiveness":[130],"handling":[132],"constraints":[134],"tasks.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4}],"updated_date":"2026-02-25T08:12:03.925757","created_date":"2025-10-10T00:00:00"}
