{"id":"https://openalex.org/W7147430446","doi":"https://doi.org/10.1109/tase.2026.3678655","title":"Robotic Bin Packing via Hierarchical Reinforcement Learning","display_name":"Robotic Bin Packing via Hierarchical Reinforcement Learning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7147430446","doi":"https://doi.org/10.1109/tase.2026.3678655"},"language":null,"primary_location":{"id":"doi:10.1109/tase.2026.3678655","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2026.3678655","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"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 Transactions on Automation Science and Engineering","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":null,"display_name":"Baoying Wang","orcid":"https://orcid.org/0009-0008-8909-2031"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baoying Wang","raw_affiliation_strings":["State Key Laboratory of Fluid Power and Mechatronic Systems, the Grasp Laboratory, and the School of Mechanical Engineering, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0008-8909-2031","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Fluid Power and Mechatronic Systems, the Grasp Laboratory, and the School of Mechanical Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132545870","display_name":"Wei Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Yu","raw_affiliation_strings":["State Key Laboratory of Fluid Power and Mechatronic Systems, the Grasp Laboratory, and the School of Mechanical Engineering, Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Fluid Power and Mechatronic Systems, the Grasp Laboratory, and the School of Mechanical Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100430876","display_name":"Xi Zhang","orcid":"https://orcid.org/0000-0003-3415-5345"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xidan Zhang","raw_affiliation_strings":["State Key Laboratory of Fluid Power and Mechatronic Systems, the Grasp Laboratory, and the School of Mechanical Engineering, Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Fluid Power and Mechatronic Systems, the Grasp Laboratory, and the School of Mechanical Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102535013","display_name":"Ziyi Zheng","orcid":"https://orcid.org/0009-0008-9918-6728"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyi Zheng","raw_affiliation_strings":["State Key Laboratory of Fluid Power and Mechatronic Systems, the Grasp Laboratory, and the School of Mechanical Engineering, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0008-9918-6728","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Fluid Power and Mechatronic Systems, the Grasp Laboratory, and the School of Mechanical Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109153417","display_name":"Weijie Kong","orcid":"https://orcid.org/0000-0003-1700-4801"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weijie Kong","raw_affiliation_strings":["State Key Laboratory of Fluid Power and Mechatronic Systems, the Grasp Laboratory, and the School of Mechanical Engineering, Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Fluid Power and Mechatronic Systems, the Grasp Laboratory, and the School of Mechanical Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016175741","display_name":"Huixu Dong","orcid":"https://orcid.org/0000-0002-2582-6728"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huixu Dong","raw_affiliation_strings":["State Key Laboratory of Fluid Power and Mechatronic Systems, the Grasp Laboratory, and the School of Mechanical Engineering, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-2582-6728","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Fluid Power and Mechatronic Systems, the Grasp Laboratory, and the School of Mechanical Engineering, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.45397277,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"23","issue":null,"first_page":"8634","last_page":"8646"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12176","display_name":"Optimization and Packing Problems","score":0.9649999737739563,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/T12176","display_name":"Optimization and Packing Problems","score":0.9649999737739563,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/T11814","display_name":"Advanced Manufacturing and Logistics Optimization","score":0.004699999932199717,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/T11522","display_name":"VLSI and FPGA Design Techniques","score":0.0015999999595806003,"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/bin-packing-problem","display_name":"Bin packing problem","score":0.7958999872207642},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6385999917984009},{"id":"https://openalex.org/keywords/grippers","display_name":"Grippers","score":0.5839999914169312},{"id":"https://openalex.org/keywords/container","display_name":"Container (type theory)","score":0.5753999948501587},{"id":"https://openalex.org/keywords/packing-problems","display_name":"Packing problems","score":0.5314000248908997},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5285000205039978},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4941999912261963},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.48429998755455017},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.43630000948905945}],"concepts":[{"id":"https://openalex.org/C87219788","wikidata":"https://www.wikidata.org/wiki/Q814581","display_name":"Bin packing problem","level":3,"score":0.7958999872207642},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6692000031471252},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6385999917984009},{"id":"https://openalex.org/C2775960376","wikidata":"https://www.wikidata.org/wiki/Q1435859","display_name":"Grippers","level":2,"score":0.5839999914169312},{"id":"https://openalex.org/C2781018962","wikidata":"https://www.wikidata.org/wiki/Q5164884","display_name":"Container (type theory)","level":2,"score":0.5753999948501587},{"id":"https://openalex.org/C130253271","wikidata":"https://www.wikidata.org/wiki/Q3851477","display_name":"Packing problems","level":2,"score":0.5314000248908997},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5285000205039978},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4941999912261963},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.48429998755455017},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.43630000948905945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43290001153945923},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4153999984264374},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.36640000343322754},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3555999994277954},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.35269999504089355},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.34139999747276306},{"id":"https://openalex.org/C156273044","wikidata":"https://www.wikidata.org/wiki/Q4913766","display_name":"Bin","level":2,"score":0.3228999972343445},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C134516590","wikidata":"https://www.wikidata.org/wiki/Q475603","display_name":"Set packing","level":3,"score":0.3050999939441681},{"id":"https://openalex.org/C115908005","wikidata":"https://www.wikidata.org/wiki/Q2668364","display_name":"Combinatorial explosion","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C2983137510","wikidata":"https://www.wikidata.org/wiki/Q1413942","display_name":"Material handling","level":2,"score":0.28929999470710754},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.27970001101493835},{"id":"https://openalex.org/C163797641","wikidata":"https://www.wikidata.org/wiki/Q2067937","display_name":"Tree structure","level":3,"score":0.2718999981880188},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.2630999982357025},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C52692508","wikidata":"https://www.wikidata.org/wiki/Q1333872","display_name":"Combinatorial optimization","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C60891933","wikidata":"https://www.wikidata.org/wiki/Q796575","display_name":"Ant colony","level":3,"score":0.25679999589920044},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.25369998812675476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tase.2026.3678655","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2026.3678655","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"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 Transactions on Automation Science and Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.4735978841781616,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1920942232","https://openalex.org/W2035260387","https://openalex.org/W2101057470","https://openalex.org/W2105482032","https://openalex.org/W2112796928","https://openalex.org/W2131774270","https://openalex.org/W2134288639","https://openalex.org/W2145339207","https://openalex.org/W2161926431","https://openalex.org/W2503984601","https://openalex.org/W2950604921","https://openalex.org/W2952394201","https://openalex.org/W2967842325","https://openalex.org/W3082452785","https://openalex.org/W3099587965","https://openalex.org/W3175494061","https://openalex.org/W3188558100","https://openalex.org/W3213354518","https://openalex.org/W4200291756","https://openalex.org/W4220778817","https://openalex.org/W4226102240","https://openalex.org/W4310297571","https://openalex.org/W4316660701","https://openalex.org/W4379513523","https://openalex.org/W4380930001","https://openalex.org/W4385245566","https://openalex.org/W4389335084","https://openalex.org/W4393972752","https://openalex.org/W4401415884","https://openalex.org/W4402830235","https://openalex.org/W4406856814","https://openalex.org/W4412079973","https://openalex.org/W4413468652","https://openalex.org/W4416756184","https://openalex.org/W6922480057","https://openalex.org/W7076051656"],"related_works":[],"abstract_inverted_index":{"The":[0,26],"3D":[1],"bin":[2,41],"packing":[3,27,47,96,103,187],"problem":[4,116],"has":[5],"aroused":[6],"enthusiastic":[7],"research":[8,80],"interest":[9],"in":[10,40,197],"recent":[11],"years":[12],"due":[13],"to":[14,73,99,170],"its":[15],"wide":[16],"range":[17],"of":[18,69,157,193],"real-world":[19,185],"applications,":[20],"such":[21],"as":[22,43],"logistics":[23],"and":[24,29,33,49,128,142,181],"warehousing.":[25],"sequence":[28,126],"placement":[30,60,134],"pose":[31],"(position":[32],"orientation)":[34],"are":[35],"the":[36,101,115,144,155,158,171,190,194],"primary":[37],"optimization":[38],"objectives":[39],"packing,":[42],"they":[44],"dramatically":[45],"impact":[46],"results":[48],"transportation":[50],"costs.":[51],"Existing":[52],"methods":[53,173],"either":[54],"focus":[55],"exclusively":[56],"on":[57],"sequential":[58],"or":[59,62],"decisions,":[61],"navigate":[63],"a":[64,84,95,108,121,129,139,147],"vast":[65],"combined":[66],"action":[67],"space":[68,167],"both,":[70],"generally":[71],"struggling":[72],"reach":[74],"global":[75],"optimum.":[76],"To":[77],"bridge":[78],"this":[79],"gap,":[81],"we":[82,93,106,137],"propose":[83],"novel":[85],"approach":[86],"that":[87],"jointly":[88],"optimizes":[89],"both":[90],"objectives.":[91],"First,":[92],"introduce":[94],"configuration":[97],"tree":[98],"represent":[100],"dynamic":[102],"process.":[104],"Second,":[105],"develop":[107],"hierarchical":[109],"reinforcement":[110],"learning":[111],"framework":[112,145],"which":[113,161],"decomposes":[114],"into":[117],"two":[118],"tractable":[119],"subtasks:":[120],"high-level":[122],"manager":[123],"network":[124,132],"for":[125,133],"generation":[127],"low-level":[130],"worker":[131],"determination.":[135],"Third,":[136],"formulate":[138],"stepwise":[140],"reward":[141],"train":[143],"using":[146],"Dueling":[148],"Deep":[149],"Q-Network.":[150],"Finally,":[151],"extensive":[152],"experiments":[153,188],"demonstrate":[154],"superiority":[156],"proposed":[159,195],"method,":[160],"achieves":[162],"over":[163],"10%":[164],"higher":[165],"container":[166,180],"utilization":[168],"compared":[169],"advanced":[172],"while":[174],"maintaining":[175],"robust":[176],"generalization":[177],"across":[178],"varied":[179],"box":[182],"dimensions.":[183],"Furthermore,":[184],"robotic":[186],"validate":[189],"practical":[191],"applicability":[192],"method":[196],"industrial":[198],"scenarios.":[199]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-02T00:00:00"}