{"id":"https://openalex.org/W7117328036","doi":"https://doi.org/10.1007/s44443-025-00371-1","title":"A dual-arm cooperative control method based on improved proximal policy optimization","display_name":"A dual-arm cooperative control method based on improved proximal policy optimization","publication_year":2025,"publication_date":"2025-12-26","ids":{"openalex":"https://openalex.org/W7117328036","doi":"https://doi.org/10.1007/s44443-025-00371-1"},"language":"en","primary_location":{"id":"doi:10.1007/s44443-025-00371-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44443-025-00371-1","pdf_url":null,"source":{"id":"https://openalex.org/S2764955546","display_name":"Journal of King Saud University - Computer and Information Sciences","issn_l":"1319-1578","issn":["1319-1578","2213-1248"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of King Saud University Computer and Information Sciences","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1007/s44443-025-00371-1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104280856","display_name":"Man Su","orcid":null},"institutions":[{"id":"https://openalex.org/I178232147","display_name":"Guizhou University","ror":"https://ror.org/02wmsc916","country_code":"CN","type":"education","lineage":["https://openalex.org/I178232147"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Man Su","raw_affiliation_strings":["Guizhou University, Guiyang, Guizhou, 550025, PR China"],"affiliations":[{"raw_affiliation_string":"Guizhou University, Guiyang, Guizhou, 550025, PR China","institution_ids":["https://openalex.org/I178232147"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121337875","display_name":"Qingni Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I178232147","display_name":"Guizhou University","ror":"https://ror.org/02wmsc916","country_code":"CN","type":"education","lineage":["https://openalex.org/I178232147"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingni Yuan","raw_affiliation_strings":["Guizhou University, Guiyang, Guizhou, 550025, PR China"],"affiliations":[{"raw_affiliation_string":"Guizhou University, Guiyang, Guizhou, 550025, PR China","institution_ids":["https://openalex.org/I178232147"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076889837","display_name":"Pengju Qu","orcid":"https://orcid.org/0000-0002-3180-1105"},"institutions":[{"id":"https://openalex.org/I178232147","display_name":"Guizhou University","ror":"https://ror.org/02wmsc916","country_code":"CN","type":"education","lineage":["https://openalex.org/I178232147"]},{"id":"https://openalex.org/I4210156872","display_name":"Guizhou Institute of Technology","ror":"https://ror.org/05x510r30","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210156872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengju Qu","raw_affiliation_strings":["Guizhou Institute of Technology, Guiyang, Guizhou, 550025, PR China","Guizhou University, Guiyang, Guizhou, 550025, PR China"],"affiliations":[{"raw_affiliation_string":"Guizhou Institute of Technology, Guiyang, Guizhou, 550025, PR China","institution_ids":["https://openalex.org/I4210156872"]},{"raw_affiliation_string":"Guizhou University, Guiyang, Guizhou, 550025, PR China","institution_ids":["https://openalex.org/I178232147"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121318552","display_name":"Chao Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I178232147","display_name":"Guizhou University","ror":"https://ror.org/02wmsc916","country_code":"CN","type":"education","lineage":["https://openalex.org/I178232147"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Wang","raw_affiliation_strings":["Guizhou University, Guiyang, Guizhou, 550025, PR China"],"affiliations":[{"raw_affiliation_string":"Guizhou University, Guiyang, Guizhou, 550025, PR China","institution_ids":["https://openalex.org/I178232147"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101769384","display_name":"Yu Zhou","orcid":"https://orcid.org/0000-0003-1525-7282"},"institutions":[{"id":"https://openalex.org/I178232147","display_name":"Guizhou University","ror":"https://ror.org/02wmsc916","country_code":"CN","type":"education","lineage":["https://openalex.org/I178232147"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinjiang Zhou","raw_affiliation_strings":["Guizhou University, Guiyang, Guizhou, 550025, PR China"],"affiliations":[{"raw_affiliation_string":"Guizhou University, Guiyang, Guizhou, 550025, PR China","institution_ids":["https://openalex.org/I178232147"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5104280856"],"corresponding_institution_ids":["https://openalex.org/I178232147"],"apc_list":{"value":1350,"currency":"USD","value_usd":1350},"apc_paid":{"value":1350,"currency":"USD","value_usd":1350},"fwci":1.1617,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85210327,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"38","issue":"2","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.5788999795913696,"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":0.5788999795913696,"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/T10982","display_name":"Motor Control and Adaptation","score":0.1639000028371811,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.13420000672340393,"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/convergence","display_name":"Convergence (economics)","score":0.6812999844551086},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5853000283241272},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5304999947547913},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.5236999988555908},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5171999931335449},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4788999855518341},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4652999937534332},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4268999993801117},{"id":"https://openalex.org/keywords/constrained-optimization","display_name":"Constrained optimization","score":0.4235999882221222}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.697700023651123},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6812999844551086},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6089000105857849},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5853000283241272},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5304999947547913},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.5236999988555908},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5171999931335449},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4788999855518341},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4652999937534332},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4268999993801117},{"id":"https://openalex.org/C55660270","wikidata":"https://www.wikidata.org/wiki/Q5164377","display_name":"Constrained optimization","level":2,"score":0.4235999882221222},{"id":"https://openalex.org/C89109886","wikidata":"https://www.wikidata.org/wiki/Q1535924","display_name":"Trust region","level":3,"score":0.4011000096797943},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.35920000076293945},{"id":"https://openalex.org/C2987595161","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Optimization algorithm","level":2,"score":0.3434000015258789},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.32580000162124634},{"id":"https://openalex.org/C164752517","wikidata":"https://www.wikidata.org/wiki/Q5570875","display_name":"Global optimization","level":2,"score":0.3091000020503998},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.30880001187324524},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.28029999136924744},{"id":"https://openalex.org/C92995354","wikidata":"https://www.wikidata.org/wiki/Q5165499","display_name":"Continuous optimization","level":4,"score":0.27869999408721924},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2775999903678894},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C2989514635","wikidata":"https://www.wikidata.org/wiki/Q5164377","display_name":"Constrained optimization problem","level":3,"score":0.2605000138282776},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C68781425","wikidata":"https://www.wikidata.org/wiki/Q2052203","display_name":"Multi-objective optimization","level":2,"score":0.2558000087738037},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.25459998846054077}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s44443-025-00371-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44443-025-00371-1","pdf_url":null,"source":{"id":"https://openalex.org/S2764955546","display_name":"Journal of King Saud University - Computer and Information Sciences","issn_l":"1319-1578","issn":["1319-1578","2213-1248"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of King Saud University Computer and Information Sciences","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:23ef1f5c25f14ffea62391dbb75e74f0","is_oa":true,"landing_page_url":"https://doaj.org/article/23ef1f5c25f14ffea62391dbb75e74f0","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of King Saud University: Computer and Information Sciences, Vol 38, Iss 2, Pp 1-21 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s44443-025-00371-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s44443-025-00371-1","pdf_url":null,"source":{"id":"https://openalex.org/S2764955546","display_name":"Journal of King Saud University - Computer and Information Sciences","issn_l":"1319-1578","issn":["1319-1578","2213-1248"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of King Saud University Computer and Information Sciences","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7319245338439941,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G3321821406","display_name":null,"funder_award_id":"No.52165063","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5503630433","display_name":null,"funder_award_id":"No.52065010","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W2096630263","https://openalex.org/W2109910161","https://openalex.org/W3081506755","https://openalex.org/W3082889183","https://openalex.org/W3090434134","https://openalex.org/W3100789280","https://openalex.org/W3124201714","https://openalex.org/W3128060803","https://openalex.org/W3128256958","https://openalex.org/W3130418699","https://openalex.org/W3134939669","https://openalex.org/W3135203571","https://openalex.org/W3145758608","https://openalex.org/W3168892396","https://openalex.org/W3169694071","https://openalex.org/W3212826513","https://openalex.org/W4213425745","https://openalex.org/W4214881458","https://openalex.org/W4285222939","https://openalex.org/W4293731347","https://openalex.org/W4311390918","https://openalex.org/W4312753513","https://openalex.org/W4313581354","https://openalex.org/W4320487039","https://openalex.org/W4367663367","https://openalex.org/W4378176035","https://openalex.org/W4384519313","https://openalex.org/W4386950658","https://openalex.org/W4390782280","https://openalex.org/W4390956470","https://openalex.org/W4390968395","https://openalex.org/W4392089697","https://openalex.org/W4394842097","https://openalex.org/W4394858569","https://openalex.org/W4400905328","https://openalex.org/W4401109918","https://openalex.org/W4401657419","https://openalex.org/W4402761317","https://openalex.org/W4406581146","https://openalex.org/W4406588824","https://openalex.org/W4407636090","https://openalex.org/W4407690624","https://openalex.org/W4407992447","https://openalex.org/W4415795381"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"To":[1],"address":[2],"the":[3,12,18,63,70,115,122,132,135,139,162],"challenges":[4],"of":[5,14,20,69,117,134],"high-dimensional":[6],"control":[7,48],"in":[8,35,169,176,180],"dual-arm":[9,46,71,181],"collaborative":[10,47,182],"tasks,":[11,186],"complexity":[13],"multi-stage":[15],"decision-making,":[16],"and":[17,38,66,76,106,138,172,184],"limitations":[19],"traditional":[21,160],"Proximal":[22,54,89,118],"Policy":[23,55,90,119,127],"Optimization":[24,56,91,120,128],"(PPO)":[25],"algorithms":[26],"due":[27],"to":[28,130,159],"their":[29],"single":[30],"constraint":[31],"mechanism,":[32],"which":[33,96],"results":[34,155],"policy":[36,140],"bias":[37],"insufficient":[39],"convergence":[40,170],"efficiency,":[41],"this":[42],"paper":[43],"proposes":[44],"a":[45,77,85,98,166,173],"method":[49,164],"based":[50],"on":[51,59],"an":[52,108],"improved":[53],"algorithm.":[57],"Based":[58],"deep":[60],"reinforcement":[61],"learning,":[62],"state":[64],"space":[65,68],"action":[67],"system":[72],"are":[73],"first":[74],"defined,":[75],"perception-decision-update":[78],"closed-loop":[79],"interaction":[80],"mechanism":[81],"is":[82,94],"constructed.":[83],"Subsequently,":[84],"Hierarchical":[86],"Constrained":[87],"Hybrid":[88],"algorithm":[92,123],"(HCH-PPO)":[93],"proposed,":[95],"designs":[97],"dual-timescale":[99],"hierarchical":[100,144],"policy,":[101],"establishes":[102],"dynamic":[103],"hybrid":[104],"constraints,":[105],"incorporates":[107],"adaptive":[109],"parameter":[110],"adjustment":[111],"mechanism.":[112],"While":[113],"maintaining":[114],"efficiency":[116],"(PPO),":[121],"introduces":[124],"Trust":[125],"Region":[126],"(TRPO)":[129],"enhance":[131],"stability":[133],"optimization":[136,145],"process":[137],"exploration":[141],"capability.":[142],"This":[143],"framework":[146],"effectively":[147],"enables":[148],"efficient":[149],"state-to-action":[150],"mapping":[151],"learning.":[152],"Finally,":[153],"experimental":[154],"demonstrate":[156],"that,":[157],"compared":[158],"PPO,":[161],"proposed":[163],"achieves":[165],"56.82%":[167],"improvement":[168],"speed":[171],"12%":[174],"increase":[175],"task":[177],"success":[178],"rate":[179],"grasping":[183],"placing":[185],"indicating":[187],"significant":[188],"performance":[189],"enhancement.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-12-26T00:00:00"}
