{"id":"https://openalex.org/W4205847188","doi":"https://doi.org/10.1109/access.2022.3140781","title":"Deep Reinforcement Learning With Adversarial Training for Automated Excavation Using Depth Images","display_name":"Deep Reinforcement Learning With Adversarial Training for Automated Excavation Using Depth Images","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4205847188","doi":"https://doi.org/10.1109/access.2022.3140781"},"language":"en","primary_location":{"id":"doi:10.1109/access.2022.3140781","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3140781","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9668973/09672107.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/9668973/09672107.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028032706","display_name":"Takayuki Osa","orcid":"https://orcid.org/0000-0002-6895-9088"},"institutions":[{"id":"https://openalex.org/I207014233","display_name":"Kyushu Institute of Technology","ror":"https://ror.org/02278tr80","country_code":"JP","type":"education","lineage":["https://openalex.org/I207014233"]},{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Takayuki Osa","raw_affiliation_strings":["Department of Human Intelligence Systems, Kyushu Institute of Technology, Fukuoka, Japan","RIKEN Center for Advanced Intelligence Project, Tokyo, Japan","Research Center for Neuromorphic AI Hardware, Kyushu Institute of Technology, Fukuoka, Japan"],"raw_orcid":"https://orcid.org/0000-0002-6895-9088","affiliations":[{"raw_affiliation_string":"Department of Human Intelligence Systems, Kyushu Institute of Technology, Fukuoka, Japan","institution_ids":["https://openalex.org/I207014233"]},{"raw_affiliation_string":"RIKEN Center for Advanced Intelligence Project, Tokyo, Japan","institution_ids":["https://openalex.org/I4210126580"]},{"raw_affiliation_string":"Research Center for Neuromorphic AI Hardware, Kyushu Institute of Technology, Fukuoka, Japan","institution_ids":["https://openalex.org/I207014233"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025652230","display_name":"Masanori Aizawa","orcid":null},"institutions":[{"id":"https://openalex.org/I882656400","display_name":"Komatsu (Japan)","ror":"https://ror.org/03s23ay81","country_code":"JP","type":"company","lineage":["https://openalex.org/I882656400"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masanori Aizawa","raw_affiliation_strings":["Komatsu Ltd., Kanagawa, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Komatsu Ltd., Kanagawa, Japan","institution_ids":["https://openalex.org/I882656400"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5028032706"],"corresponding_institution_ids":["https://openalex.org/I207014233","https://openalex.org/I4210126580"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":2.6386,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.90934972,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"10","issue":null,"first_page":"4523","last_page":"4535"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9973999857902527,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9973999857902527,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9775000214576721,"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/T10409","display_name":"Fuel Cells and Related Materials","score":0.907800018787384,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7988495826721191},{"id":"https://openalex.org/keywords/excavation","display_name":"Excavation","score":0.7702562808990479},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7360998392105103},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6710125803947449},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.624083936214447},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5563993453979492},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.49962687492370605},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.499053955078125},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4772048890590668},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.4558500051498413},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4365920126438141},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.42211657762527466},{"id":"https://openalex.org/keywords/economic-shortage","display_name":"Economic shortage","score":0.4176112413406372},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14951926469802856}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7988495826721191},{"id":"https://openalex.org/C31858485","wikidata":"https://www.wikidata.org/wiki/Q959782","display_name":"Excavation","level":2,"score":0.7702562808990479},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7360998392105103},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6710125803947449},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.624083936214447},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5563993453979492},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.49962687492370605},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.499053955078125},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4772048890590668},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.4558500051498413},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4365920126438141},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.42211657762527466},{"id":"https://openalex.org/C194051981","wikidata":"https://www.wikidata.org/wiki/Q1337691","display_name":"Economic shortage","level":3,"score":0.4176112413406372},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14951926469802856},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C187320778","wikidata":"https://www.wikidata.org/wiki/Q1349130","display_name":"Geotechnical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C2778137410","wikidata":"https://www.wikidata.org/wiki/Q2732820","display_name":"Government (linguistics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2022.3140781","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3140781","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9668973/09672107.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:1b5d8f508a684939bcef6cb4b997b178","is_oa":true,"landing_page_url":"https://doaj.org/article/1b5d8f508a684939bcef6cb4b997b178","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 10, Pp 4523-4535 (2022)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2022.3140781","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3140781","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9668973/09672107.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1575162418","display_name":null,"funder_award_id":"JP19K20370","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320324693","display_name":"Kyushu Institute of Technology","ror":"https://ror.org/02278tr80"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4205847188.pdf","grobid_xml":"https://content.openalex.org/works/W4205847188.grobid-xml"},"referenced_works_count":63,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W51508254","https://openalex.org/W83284419","https://openalex.org/W1570975970","https://openalex.org/W1601795611","https://openalex.org/W1673923490","https://openalex.org/W1846039755","https://openalex.org/W1945616565","https://openalex.org/W2000290430","https://openalex.org/W2056204581","https://openalex.org/W2058815839","https://openalex.org/W2066329101","https://openalex.org/W2111406701","https://openalex.org/W2128099450","https://openalex.org/W2130726249","https://openalex.org/W2132083787","https://openalex.org/W2145339207","https://openalex.org/W2155007355","https://openalex.org/W2162112538","https://openalex.org/W2292751606","https://openalex.org/W2597234992","https://openalex.org/W2601943843","https://openalex.org/W2602963933","https://openalex.org/W2605102758","https://openalex.org/W2781726626","https://openalex.org/W2787938642","https://openalex.org/W2897462754","https://openalex.org/W2941205169","https://openalex.org/W2949103145","https://openalex.org/W2963864421","https://openalex.org/W2964159205","https://openalex.org/W2968983352","https://openalex.org/W2989847975","https://openalex.org/W2990747716","https://openalex.org/W2996343955","https://openalex.org/W2997947190","https://openalex.org/W3004473134","https://openalex.org/W3015872276","https://openalex.org/W3034118413","https://openalex.org/W3101780148","https://openalex.org/W3103768745","https://openalex.org/W3107041087","https://openalex.org/W3118210634","https://openalex.org/W3137337287","https://openalex.org/W3179565202","https://openalex.org/W4297781264","https://openalex.org/W4302570325","https://openalex.org/W6602057636","https://openalex.org/W6637162671","https://openalex.org/W6640425456","https://openalex.org/W6682849425","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6733049761","https://openalex.org/W6735677848","https://openalex.org/W6747473740","https://openalex.org/W6748839928","https://openalex.org/W6762427411","https://openalex.org/W6774011044","https://openalex.org/W6785130903","https://openalex.org/W6785691520","https://openalex.org/W6791779665","https://openalex.org/W6798184745"],"related_works":["https://openalex.org/W2294590153","https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W4376605461","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W3087814763","https://openalex.org/W2892507673","https://openalex.org/W2361647908","https://openalex.org/W2937181779"],"abstract_inverted_index":{"Excavation,":[0],"which":[1,73],"is":[2,32,74,124,169],"one":[3],"of":[4,26,30,45,54,60,77,113,147,161,166],"the":[5,24,43,52,58,86,139,144,159,164],"most":[6],"frequently":[7],"performed":[8],"tasks":[9],"during":[10],"construction":[11],"often":[12,156],"poses":[13],"danger":[14],"to":[15,110],"human":[16],"operators.":[17],"To":[18],"reduce":[19,111],"potential":[20],"risks":[21],"and":[22,135,163],"address":[23],"problem":[25,133],"workforce":[27],"shortage,":[28],"automation":[29],"excavation":[31,55,87,162],"essential.":[33],"Although":[34],"previous":[35],"studies":[36],"have":[37,62],"yielded":[38],"promising":[39],"results":[40,120,150],"based":[41],"on":[42],"use":[44],"reinforcement":[46],"learning":[47,85],"(RL)":[48],"for":[49,80,84,171],"automated":[50],"excavation,":[51],"properties":[53],"task":[56,88],"in":[57,97,115,131],"context":[59],"RL":[61],"not":[63],"been":[64],"sufficiently":[65],"investigated.":[66],"In":[67],"this":[68],"study,":[69],"we":[70,100,136],"investigate":[71],"Qt-Opt,":[72],"a":[75,102,116],"variant":[76],"Q-learning":[78,117],"algorithms":[79],"continuous":[81],"action":[82],"space,":[83],"using":[89],"depth":[90],"images.":[91],"Inspired":[92],"by":[93],"virtual":[94,107],"adversarial":[95,108],"training":[96],"supervised":[98],"learning,":[99],"propose":[101],"regularization":[103],"method":[104,141],"that":[105,122,138,152],"uses":[106],"samples":[109],"overestimation":[112],"Q-values":[114],"algorithm.":[118],"Our":[119,149],"reveal":[121],"Qt-Opt":[123],"more":[125],"sample-efficient":[126],"than":[127],"state-of-the-art":[128],"actor-critic":[129],"methods":[130],"our":[132],"setting,":[134],"verify":[137],"proposed":[140],"further":[142],"improves":[143],"sample":[145],"efficiency":[146],"Qt-Opt.":[148],"demonstrate":[151],"multiple":[153],"optimal":[154],"actions":[155],"exist":[157],"within":[158],"process":[160],"choice":[165],"policy":[167],"representation":[168],"crucial":[170],"satisfactory":[172],"performance.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}