{"id":"https://openalex.org/W4415969292","doi":"https://doi.org/10.1109/iecon58223.2025.11221104","title":"Obstacle Avoidance Control Design Using Imitation and Reinforcement Learning for Two-Wheeled Robot with A Stereo Camera","display_name":"Obstacle Avoidance Control Design Using Imitation and Reinforcement Learning for Two-Wheeled Robot with A Stereo Camera","publication_year":2025,"publication_date":"2025-10-14","ids":{"openalex":"https://openalex.org/W4415969292","doi":"https://doi.org/10.1109/iecon58223.2025.11221104"},"language":null,"primary_location":{"id":"doi:10.1109/iecon58223.2025.11221104","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iecon58223.2025.11221104","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IECON 2025 \u2013 51st Annual Conference of the IEEE Industrial Electronics Society","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/A5013860606","display_name":"Koichi Hidaka","orcid":"https://orcid.org/0000-0001-9018-7822"},"institutions":[{"id":"https://openalex.org/I165522056","display_name":"Tokyo Denki University","ror":"https://ror.org/01pa62v70","country_code":"JP","type":"education","lineage":["https://openalex.org/I165522056"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Koichi Hidaka","raw_affiliation_strings":["Tokyo Denki University,Dept. Electrical and Electronics Engineering,Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"Tokyo Denki University,Dept. Electrical and Electronics Engineering,Tokyo,Japan","institution_ids":["https://openalex.org/I165522056"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5013860606"],"corresponding_institution_ids":["https://openalex.org/I165522056"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.39100342,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.3402000069618225,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.3402000069618225,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.16169999539852142,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.1460999995470047,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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":0.7559000253677368},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.6693999767303467},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6672999858856201},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5906000137329102},{"id":"https://openalex.org/keywords/obstacle","display_name":"Obstacle","score":0.541700005531311},{"id":"https://openalex.org/keywords/obstacle-avoidance","display_name":"Obstacle avoidance","score":0.4912000000476837},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.47870001196861267},{"id":"https://openalex.org/keywords/robot-control","display_name":"Robot control","score":0.46619999408721924},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.44830000400543213}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7559000253677368},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.6693999767303467},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6672999858856201},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6137999892234802},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6068000197410583},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5906000137329102},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.541700005531311},{"id":"https://openalex.org/C6683253","wikidata":"https://www.wikidata.org/wiki/Q7075535","display_name":"Obstacle avoidance","level":4,"score":0.4912000000476837},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47870001196861267},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.46619999408721924},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.44830000400543213},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.44179999828338623},{"id":"https://openalex.org/C40149104","wikidata":"https://www.wikidata.org/wiki/Q5620977","display_name":"Factory (object-oriented programming)","level":2,"score":0.41029998660087585},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.40299999713897705},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4000000059604645},{"id":"https://openalex.org/C162947575","wikidata":"https://www.wikidata.org/wiki/Q2005645","display_name":"Social robot","level":5,"score":0.3603000044822693},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33250001072883606},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.32109999656677246},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3138999938964844},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.30469998717308044},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2847999930381775},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2777999937534332},{"id":"https://openalex.org/C2778835581","wikidata":"https://www.wikidata.org/wiki/Q2916098","display_name":"Autonomous robot","level":4,"score":0.26649999618530273},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.26330000162124634},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C82327864","wikidata":"https://www.wikidata.org/wiki/Q835100","display_name":"Intelligent control","level":2,"score":0.25209999084472656},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iecon58223.2025.11221104","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iecon58223.2025.11221104","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IECON 2025 \u2013 51st Annual Conference of the IEEE Industrial Electronics Society","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":30,"referenced_works":["https://openalex.org/W192919555","https://openalex.org/W1997027186","https://openalex.org/W2021061679","https://openalex.org/W2026176629","https://openalex.org/W2064675550","https://openalex.org/W2105934661","https://openalex.org/W2111112078","https://openalex.org/W2117211893","https://openalex.org/W2158400962","https://openalex.org/W2169528473","https://openalex.org/W2565402511","https://openalex.org/W2604216058","https://openalex.org/W2737529802","https://openalex.org/W2801667201","https://openalex.org/W2883180136","https://openalex.org/W2908515539","https://openalex.org/W2942307437","https://openalex.org/W2963037989","https://openalex.org/W2963150697","https://openalex.org/W2963353290","https://openalex.org/W2963809389","https://openalex.org/W3047375952","https://openalex.org/W3095329531","https://openalex.org/W3123846747","https://openalex.org/W3134645133","https://openalex.org/W3144958384","https://openalex.org/W3153654831","https://openalex.org/W3201311488","https://openalex.org/W4293363567","https://openalex.org/W4312769831"],"related_works":[],"abstract_inverted_index":{"Autonomous":[0,103],"Mobile":[1],"Robots":[2],"(AMRs)":[3],"have":[4,109,125,169,217],"been":[5,110,126,170],"utilized":[6],"in":[7,15,41,91,147,197,252,379],"production":[8,28],"plants":[9],"and":[10,37,44,47,52,69,77,84,105,114,174,200,214,222,245,272,305,310,360,384,438,452,457,465],"factories":[11,25],"for":[12,22,117,130,143],"logistics":[13],"purposes":[14],"recent":[16],"years":[17],"[1].":[18],"AMRs":[19,61],"are":[20,88,366,450,469],"essential":[21],"constructing":[23],"smart":[24],"that":[26,234,265,294,332,386],"enhance":[27],"efficiency":[29],"by":[30,415],"enabling":[31],"the":[32,60,74,92,99,140,156,160,185,190,203,215,250,273,301,308,311,340,351,354,357,361,364,369,375,396,398,401,404,417,422,445,453,458,461,466,473,476],"robot":[33,107,302,309,358],"to":[34,39,48,98,152,195,219,373,471],"respond":[35],"quickly":[36],"flexibly":[38],"changes":[40],"transportation":[42],"points":[43],"factory":[45],"layouts,":[46],"cooperate":[49],"with":[50,58,210,278,322,426],"people":[51,83],"other":[53,85,141,204],"robots":[54,145],"[2].":[55],"While":[56],"collaborating":[57],"humans,":[59],"must":[62],"avoid":[63,79],"stationary":[64],"objects,":[65,81],"such":[66],"as":[67,128],"billboards":[68],"trash":[70],"cans,":[71],"before":[72],"reaching":[73],"target":[75,100,418],"location,":[76],"also":[78],"moving":[80,463],"including":[82],"robots,":[86],"which":[87],"not":[89,314,334],"included":[90],"prior":[93],"environmental":[94],"information,":[95],"while":[96],"driving":[97],"location":[101],"[3]\u2013[6].":[102],"vehicle":[104],"mobile":[106,144],"controls":[108],"proposed":[111,127,274,317,411,477],"[7]\u2013[10].":[112],"Social-Scene-LSTM":[113],"State":[115],"Refinement":[116],"LSTM,":[118],"based":[119,289,344,406],"on":[120,290,300,345,407],"hierarchical":[121],"Long":[122,435],"Short-Term":[123,436],"Memory,":[124],"methods":[129,168,216],"predicting":[131],"pedestrian":[132],"movement":[133,267,414],"using":[134,184,239,283],"learning":[135,173,178,187,244,292,338],"[11],":[136],"[12],":[137],"[13].":[138],"On":[139,202],"hand,":[142,205],"used":[146,209,372],"transportation,":[148],"it":[149,390],"is":[150,276,303,313],"necessary":[151],"move":[153],"efficiently":[154],"along":[155],"optimal":[157],"route":[158],"toward":[159],"goal":[161],"without":[162],"stopping.":[163],"For":[164],"these":[165],"purposes,":[166],"many":[167,211],"proposed,":[171],"i.e.,":[172],"non-learning":[175,206],"approaches.":[176],"The":[177,286,316,410],"process":[179],"involves":[180],"designing":[181],"a":[182,227,236,240,261,296,346,427,439],"controller":[183,191],"available":[186],"data.":[188],"Thus,":[189],"can":[192,207],"be":[193,208,220,392],"made":[194],"operate":[196],"unknown":[198],"environments":[199],"situations.":[201],"control":[212],"methods,":[213],"proven":[218],"stable":[221],"robust.":[223],"This":[224,258],"paper":[225],"proposes":[226,260],"future":[228],"action":[229,282,343],"estimation":[230],"of":[231,242,356,363,382,389,403,433,455,475],"an":[232,279,328,434],"obstacle":[233,280,287,329,365,405],"learns":[235],"state-value":[237],"function":[238],"combination":[241],"imitation":[243],"reinforcement":[246,284,291,408],"learning,":[247,271],"thereby":[248],"addressing":[249],"difficulty":[251],"environment":[253],"modeling":[254],"under":[255],"complex":[256],"environments.":[257],"study":[259],"state":[262,355,362],"prediction":[263,430],"method":[264,275,318,399,412],"utilizes":[266,319],"behavior":[268],"acquired":[269],"through":[270],"demonstrated":[277],"avoidance":[281,288,330,448],"learning.":[285,409],"assumes":[293],"only":[295],"stereo":[297,370],"camera":[298,371],"mounted":[299],"used,":[304],"communication":[306],"between":[307,460],"obstacles":[312,376,385],"established.":[315],"Collision":[320],"Avoidance":[321],"Deep":[323],"Reinforcement":[324,337],"Learning":[325],"(CADRL)":[326],"[14],":[327],"algorithm":[331],"does":[333],"involve":[335],"communication.":[336],"determines":[339],"robot\u2019s":[341],"subsequent":[342],"value":[347],"function.":[348],"To":[349,394,443],"obtain":[350],"value,":[352],"both":[353],"itself":[359],"required.":[367],"However,":[368],"observe":[374],"has":[377],"limitations":[378],"its":[380],"field":[381],"view,":[383],"fall":[387],"outside":[388],"cannot":[391],"recognized.":[393],"solve":[395],"problem,":[397],"predicts":[400,413],"trajectory":[402,425,429],"combining":[416],"speed":[419],"estimated":[420],"from":[421],"obstacle\u2019s":[423],"running":[424],"learned":[428],"model":[431],"consisting":[432],"Memory":[437],"fully":[440],"connected":[441],"layer.":[442],"demonstrate":[444],"validity,":[446],"collision":[447],"simulations":[449],"performed,":[451],"number":[454],"collisions":[456],"error":[459],"actual":[462],"position":[464,468],"predicted":[467],"compared":[470],"illustrate":[472],"effectiveness":[474],"method.":[478]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-06T00:00:00"}