{"id":"https://openalex.org/W4408352604","doi":"https://doi.org/10.1109/icassp49660.2025.10888293","title":"Active Visual Learning for Robots with Dueling Deep Q-Networks and Transformer Encoders","display_name":"Active Visual Learning for Robots with Dueling Deep Q-Networks and Transformer Encoders","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352604","doi":"https://doi.org/10.1109/icassp49660.2025.10888293"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888293","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888293","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5102967431","display_name":"Hongliang Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongliang Zeng","raw_affiliation_strings":["South China University of Technology,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology,Guangzhou,China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ping Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ping Zhang","raw_affiliation_strings":["South China University of Technology,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology,Guangzhou,China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100394185","display_name":"Fang Li","orcid":"https://orcid.org/0000-0002-4195-9475"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fang Li","raw_affiliation_strings":["South China University of Technology,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology,Guangzhou,China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010254162","display_name":"Q. B. Yi","orcid":"https://orcid.org/0009-0001-7168-3481"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinpeng Yi","raw_affiliation_strings":["South China University of Technology,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology,Guangzhou,China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050097054","display_name":"Jiahua Wang","orcid":"https://orcid.org/0000-0001-8427-1059"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahua Wang","raw_affiliation_strings":["South China University of Technology,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology,Guangzhou,China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037080088","display_name":"Tingyu Ye","orcid":"https://orcid.org/0000-0001-8804-8209"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tingyu Ye","raw_affiliation_strings":["South China University of Technology,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology,Guangzhou,China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":null,"apc_paid":null,"fwci":1.0114,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.75048263,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9157000184059143,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9157000184059143,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/encoder","display_name":"Encoder","score":0.746664822101593},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6696423292160034},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6444600224494934},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5225600600242615},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4870150685310364},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.2830479145050049},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17325827479362488},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09007930755615234},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.07897615432739258}],"concepts":[{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.746664822101593},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6696423292160034},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6444600224494934},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5225600600242615},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4870150685310364},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.2830479145050049},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17325827479362488},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09007930755615234},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07897615432739258}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888293","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888293","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":25,"referenced_works":["https://openalex.org/W2145339207","https://openalex.org/W2194775991","https://openalex.org/W2907503094","https://openalex.org/W2951360122","https://openalex.org/W2988715931","https://openalex.org/W2990045899","https://openalex.org/W3034428269","https://openalex.org/W3096754345","https://openalex.org/W3107575247","https://openalex.org/W3134025030","https://openalex.org/W3197097949","https://openalex.org/W3207737292","https://openalex.org/W3215207332","https://openalex.org/W4205513365","https://openalex.org/W4214526701","https://openalex.org/W4214624153","https://openalex.org/W4226036061","https://openalex.org/W4372349494","https://openalex.org/W4385245566","https://openalex.org/W4385453680","https://openalex.org/W4401023928","https://openalex.org/W4405365185","https://openalex.org/W6685444567","https://openalex.org/W6739778489","https://openalex.org/W6763422710"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Active":[0],"vision":[1,59],"learning":[2,29,75],"aims":[3],"to":[4,16,25,33,57,62,88,110,133],"develop":[5],"intelligent":[6],"systems":[7],"capable":[8],"of":[9,44,120,137,178],"actively":[10,34],"exploring":[11],"and":[12,81,104,152,165],"understanding":[13],"their":[14,36],"surroundings":[15],"optimize":[17],"detection":[18,65,150],"performance.":[19,179],"Although":[20],"current":[21],"research":[22],"has":[23],"begun":[24],"explore":[26],"how":[27],"reinforcement":[28,74],"can":[30],"drive":[31],"robots":[32],"perceive":[35],"environment,":[37],"it":[38],"often":[39],"overlooks":[40],"the":[41,95,121,131,135,160,166],"critical":[42],"role":[43],"integrating":[45],"historical":[46],"contextual":[47,113],"information.":[48],"To":[49],"address":[50],"this,":[51],"we":[52,145],"propose":[53],"an":[54],"innovative":[55],"approach":[56,158],"active":[58],"learning,":[60],"designed":[61,127],"enhance":[63],"target":[64],"performance":[66],"in":[67,149,176],"unknown":[68],"environments.":[69],"Specifically,":[70],"this":[71],"method":[72,171],"combines":[73],"with":[76],"deep":[77],"neural":[78],"network":[79],"techniques":[80],"cleverly":[82],"designs":[83],"a":[84,106,117],"sliding":[85],"window":[86],"mechanism":[87,129],"integrate":[89],"observations":[90],"over":[91],"multiple":[92],"steps":[93],"into":[94],"state":[96],"input.":[97],"We":[98,155],"employ":[99],"PointNet++":[100],"for":[101],"feature":[102],"extraction":[103],"utilize":[105],"Transformer":[107],"encoder":[108],"module":[109],"process":[111],"spatial":[112],"information,":[114],"thereby":[115],"constructing":[116],"comprehensive":[118],"representation":[119],"robot\u2019s":[122],"environment.":[123],"Additionally,":[124],"our":[125,157,170],"carefully":[126],"reward":[128,143],"encourages":[130],"robot":[132],"prioritize":[134],"exploration":[136],"diverse":[138],"object":[139],"categories.":[140],"With":[141],"these":[142],"strategies,":[144],"achieve":[146],"significant":[147],"improvements":[148],"accuracy":[151],"sampling":[153],"efficiency.":[154],"validated":[156],"on":[159],"real-world":[161],"3D":[162],"dataset":[163],"R3ED,":[164],"results":[167],"demonstrate":[168],"that":[169],"outperforms":[172],"other":[173],"baseline":[174],"methods":[175],"terms":[177]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}