{"id":"https://openalex.org/W4306317644","doi":"https://doi.org/10.1145/3511808.3557078","title":"Hierarchical Reinforcement Learning using Gaussian Random Trajectory Generation in Autonomous Furniture Assembly","display_name":"Hierarchical Reinforcement Learning using Gaussian Random Trajectory Generation in Autonomous Furniture Assembly","publication_year":2022,"publication_date":"2022-10-16","ids":{"openalex":"https://openalex.org/W4306317644","doi":"https://doi.org/10.1145/3511808.3557078"},"language":"en","primary_location":{"id":"doi:10.1145/3511808.3557078","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3511808.3557078","pdf_url":null,"source":{"id":"https://openalex.org/S4363608762","display_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","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/A5081315657","display_name":"Won Joon Yun","orcid":"https://orcid.org/0000-0003-0405-8843"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Won Joon Yun","raw_affiliation_strings":["Korea University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Korea University, Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077402873","display_name":"Aziz Mohaisen","orcid":"https://orcid.org/0000-0003-3227-2505"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Mohaisen","raw_affiliation_strings":["University of Central Florida, Orlando, FL, USA"],"affiliations":[{"raw_affiliation_string":"University of Central Florida, Orlando, FL, USA","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039532704","display_name":"Soyi Jung","orcid":"https://orcid.org/0000-0001-8435-0646"},"institutions":[{"id":"https://openalex.org/I57664883","display_name":"Ajou University","ror":"https://ror.org/03tzb2h73","country_code":"KR","type":"education","lineage":["https://openalex.org/I57664883"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Soyi Jung","raw_affiliation_strings":["Ajou University, Suwon, South Korea"],"affiliations":[{"raw_affiliation_string":"Ajou University, Suwon, South Korea","institution_ids":["https://openalex.org/I57664883"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018364461","display_name":"Jong\u2010Kook Kim","orcid":"https://orcid.org/0000-0003-1828-7807"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jong-Kook Kim","raw_affiliation_strings":["Korea University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Korea University, Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049202871","display_name":"Joongheon Kim","orcid":"https://orcid.org/0000-0003-2126-768X"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joongheon Kim","raw_affiliation_strings":["Korea University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Korea University, Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5081315657"],"corresponding_institution_ids":["https://openalex.org/I197347611"],"apc_list":null,"apc_paid":null,"fwci":3.1901,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.94327604,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3624","last_page":"3633"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9993000030517578,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9951000213623047,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.992900013923645,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.8422400951385498},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8166311383247375},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6770468950271606},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6367605924606323},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.5472575426101685},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5204758644104004},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.5111203789710999},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.49423912167549133},{"id":"https://openalex.org/keywords/time-horizon","display_name":"Time horizon","score":0.4909684956073761},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4556950628757477},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4486548602581024},{"id":"https://openalex.org/keywords/plan","display_name":"Plan (archaeology)","score":0.44732236862182617},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.2735361158847809},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.19972580671310425},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15216901898384094}],"concepts":[{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.8422400951385498},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8166311383247375},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6770468950271606},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6367605924606323},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.5472575426101685},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5204758644104004},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.5111203789710999},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.49423912167549133},{"id":"https://openalex.org/C28761237","wikidata":"https://www.wikidata.org/wiki/Q7805321","display_name":"Time horizon","level":2,"score":0.4909684956073761},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4556950628757477},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4486548602581024},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.44732236862182617},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2735361158847809},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.19972580671310425},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15216901898384094},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3511808.3557078","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3511808.3557078","pdf_url":null,"source":{"id":"https://openalex.org/S4363608762","display_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1971086298","https://openalex.org/W2019965290","https://openalex.org/W2062644434","https://openalex.org/W2070469928","https://openalex.org/W2096733369","https://openalex.org/W2562548250","https://openalex.org/W2600687292","https://openalex.org/W2739330054","https://openalex.org/W2766447205","https://openalex.org/W2791797404","https://openalex.org/W2885163910","https://openalex.org/W2901112449","https://openalex.org/W2903253065","https://openalex.org/W2908261578","https://openalex.org/W2909711564","https://openalex.org/W2963713397","https://openalex.org/W2963940579","https://openalex.org/W2964010185","https://openalex.org/W2967998934","https://openalex.org/W2990747716","https://openalex.org/W3012640291","https://openalex.org/W3146198107","https://openalex.org/W4288282931"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W4323768008","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W2169866437","https://openalex.org/W1964286703"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,26,34,38,93],"Gaussian":[6],"Random":[7],"Trajectory":[8],"guided":[9],"Hierarchical":[10],"Reinforcement":[11],"Learning":[12],"(GRT-HL)":[13],"method":[14],"for":[15,70,134],"autonomous":[16],"furniture":[17,20,71,114],"assembly.":[18],"The":[19,63],"assembly":[21,115],"problem":[22,125],"is":[23],"formulated":[24],"as":[25],"comprehensive":[27],"human-like":[28],"long-horizon":[29,124],"manipulation":[30],"task":[31],"that":[32,119],"requires":[33],"long-term":[35],"planning":[36],"and":[37,52,95],"sophisticated":[39],"control.":[40],"Our":[41],"proposed":[42],"model,":[43],"GRT-HL,":[44],"draws":[45],"inspirations":[46],"from":[47,85],"the":[48,57,61,74,78,82,86,89,97,102,108,123,132],"semi-supervised":[49],"adversarial":[50],"autoencoders,":[51],"learns":[53],"latent":[54],"representations":[55],"of":[56,60,77,104],"position":[58],"trajectories":[59],"end-effector.":[62,98],"high-level":[64,87],"policy":[65,91],"generates":[66],"an":[67],"optimal":[68],"trajectory":[69,83,133],"assembly,":[72],"considering":[73],"structural":[75],"limitations":[76],"robotic":[79],"agents.":[80],"Given":[81],"drawn":[84],"policy,":[88],"low-level":[90],"makes":[92],"plan":[94],"controls":[96],"We":[99,117],"first":[100],"evaluate":[101],"performance":[103],"GRT-HL":[105,120],"compared":[106],"to":[107],"state-of-the-art":[109],"reinforcement":[110],"learning":[111],"methods":[112],"in":[113],"tasks.":[116],"demonstrate":[118],"successfully":[121],"solves":[122],"with":[126],"extremely":[127],"sparse":[128],"rewards":[129],"by":[130],"generating":[131],"planning.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}