{"id":"https://openalex.org/W4286539216","doi":"https://doi.org/10.1109/lra.2022.3193019","title":"Self-Supervised Reinforcement Learning for Active Object Detection","display_name":"Self-Supervised Reinforcement Learning for Active Object Detection","publication_year":2022,"publication_date":"2022-07-21","ids":{"openalex":"https://openalex.org/W4286539216","doi":"https://doi.org/10.1109/lra.2022.3193019"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2022.3193019","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2022.3193019","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/A5030374805","display_name":"Fen Fang","orcid":"https://orcid.org/0000-0002-3834-4795"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Fen Fang","raw_affiliation_strings":["Institute for Infocomm Research, A*STAR, Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, A*STAR, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080546069","display_name":"Wenyu Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wenyu Liang","raw_affiliation_strings":["Institute for Infocomm Research, A*STAR, Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, A*STAR, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017822851","display_name":"Yan Wu","orcid":"https://orcid.org/0000-0002-4644-0664"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yan Wu","raw_affiliation_strings":["Institute for Infocomm Research, A*STAR, Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, A*STAR, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052143634","display_name":"Qianli Xu","orcid":"https://orcid.org/0000-0003-0105-5903"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Qianli Xu","raw_affiliation_strings":["Institute for Infocomm Research, A*STAR, Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, A*STAR, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077258552","display_name":"Joo\u2010Hwee Lim","orcid":"https://orcid.org/0000-0002-4103-3824"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Joo-Hwee Lim","raw_affiliation_strings":["Institute for Infocomm Research, A*STAR, Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, A*STAR, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5030374805"],"corresponding_institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3005327000"],"apc_list":null,"apc_paid":null,"fwci":2.3619,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.90082828,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"7","issue":"4","first_page":"10224","last_page":"10231"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9983999729156494,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8555262684822083},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7515749931335449},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7412577271461487},{"id":"https://openalex.org/keywords/viewpoints","display_name":"Viewpoints","score":0.6818174123764038},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6349647045135498},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5226675868034363},{"id":"https://openalex.org/keywords/inefficiency","display_name":"Inefficiency","score":0.47637125849723816},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.4624299108982086},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4583432674407959},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4540995657444},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.44645795226097107},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38772544264793396},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.38580596446990967}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8555262684822083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7515749931335449},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7412577271461487},{"id":"https://openalex.org/C2776035091","wikidata":"https://www.wikidata.org/wiki/Q7928819","display_name":"Viewpoints","level":2,"score":0.6818174123764038},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6349647045135498},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5226675868034363},{"id":"https://openalex.org/C2778869765","wikidata":"https://www.wikidata.org/wiki/Q6028363","display_name":"Inefficiency","level":2,"score":0.47637125849723816},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.4624299108982086},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4583432674407959},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4540995657444},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44645795226097107},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38772544264793396},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.38580596446990967},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2022.3193019","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2022.3193019","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":[{"id":"https://metadata.un.org/sdg/16","score":0.800000011920929,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G3616239415","display_name":null,"funder_award_id":"A18A2b0046","funder_id":"https://openalex.org/F4320320696","funder_display_name":"Agency for Science, Technology and Research"}],"funders":[{"id":"https://openalex.org/F4320320696","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W343636949","https://openalex.org/W639708223","https://openalex.org/W2075682391","https://openalex.org/W2144691386","https://openalex.org/W2194775991","https://openalex.org/W2558661413","https://openalex.org/W2580726517","https://openalex.org/W2593769898","https://openalex.org/W2768890541","https://openalex.org/W2769883686","https://openalex.org/W2783311157","https://openalex.org/W2803694688","https://openalex.org/W2907503094","https://openalex.org/W2964112854","https://openalex.org/W2990500698","https://openalex.org/W2990873191","https://openalex.org/W3034781633","https://openalex.org/W3091317905","https://openalex.org/W3175558129","https://openalex.org/W3176365423","https://openalex.org/W3195977921","https://openalex.org/W3205934217","https://openalex.org/W4251266081","https://openalex.org/W6630207832","https://openalex.org/W6637373629","https://openalex.org/W6687681856","https://openalex.org/W6729556111","https://openalex.org/W6771876938","https://openalex.org/W6774303775","https://openalex.org/W6775634482","https://openalex.org/W6775647304","https://openalex.org/W6776867236","https://openalex.org/W6840645976"],"related_works":["https://openalex.org/W2385368906","https://openalex.org/W2902924992","https://openalex.org/W2626642044","https://openalex.org/W2619807045","https://openalex.org/W2388758053","https://openalex.org/W93537448","https://openalex.org/W2949734191","https://openalex.org/W2017333877","https://openalex.org/W2048332520","https://openalex.org/W4233821346"],"abstract_inverted_index":{"Active":[0],"object":[1],"detection":[2,168],"(AOD)":[3],"offers":[4],"significant":[5],"advantage":[6],"in":[7,34,214],"expanding":[8],"the":[9,100,112,129,221,224],"perceptual":[10],"capacity":[11],"of":[12,32,66,70,78,96,121,223],"a":[13,20,35,87,104,135,180,185,215],"robotics":[14],"system.":[15],"AOD":[16,49],"is":[17,144],"formulated":[18],"as":[19],"sequential":[21],"action":[22,67,74,108],"decision":[23],"process":[24],"to":[25,29,46,64,98,110,210],"determine":[26],"optimal":[27],"viewpoints":[28,97,190],"identify":[30],"objects":[31,213],"interest":[33],"visual":[36],"scene.":[37],"While":[38],"reinforcement":[39],"learning":[40,123],"(RL)":[41],"has":[42,218],"been":[43],"successfully":[44],"used":[45],"solve":[47],"many":[48],"problems,":[50],"conventional":[51],"RL":[52,90,159],"methods":[53],"suffer":[54],"from":[55,128],"(i)":[56],"sample":[57],"inefficiency,":[58],"and":[59,73,103,118,134,146,153,157,170,200],"(ii)":[60],"unstable":[61],"outcome":[62],"due":[63],"inter-dependencies":[65],"type":[68],"(direction":[69],"view":[71,79],"change)":[72],"range":[75,109,136],"(step":[76],"size":[77],"change).":[80],"To":[81],"address":[82],"these":[83],"issues,":[84],"we":[85],"propose":[86],"novel":[88],"self-supervised":[89,94,105,122],"method,":[91],"which":[92],"employs":[93],"representations":[95],"initialize":[99],"policy":[101,130],"network,":[102],"loss":[106,124],"on":[107,148,174,179,205],"enhance":[111],"network":[113,131],"parameter":[114],"optimization.":[115],"The":[116,141,161],"output":[117],"target":[119],"pairs":[120],"are":[125,191],"automatically":[126],"generated":[127],"online":[132],"prediction":[133],"shrinkage":[137],"algorithm":[138],"(RSA),":[139],"respectively.":[140],"proposed":[142,225],"method":[143,166,196],"evaluated":[145],"benchmarked":[147],"two":[149],"public":[150],"datasets":[151],"(T-LESS":[152],"AVD)":[154],"using":[155],"on-policy":[156],"off-policy":[158],"algorithms.":[160],"results":[162],"show":[163],"that":[164],"our":[165,195],"enhances":[167],"accuracy":[169],"achieves":[171,197],"faster":[172],"convergence":[173],"both":[175],"datasets.":[176],"By":[177],"evaluating":[178],"more":[181,192,198],"complex":[182],"environment":[183],"with":[184],"larger":[186],"state":[187],"space":[188],"(where":[189],"densely":[193],"sampled),":[194],"robust":[199],"stable":[201],"performance.":[202],"Our":[203],"experiment":[204],"real":[206],"robot":[207],"application":[208],"scenario":[209],"disambiguate":[211],"similar":[212],"cluttered":[216],"scene":[217],"also":[219],"demonstrated":[220],"effectiveness":[222],"method.":[226]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}