{"id":"https://openalex.org/W7134952522","doi":"https://doi.org/10.1109/tase.2026.3672621","title":"Humanoid Five-Digit Robotic Grasping via Multi-Agent Reinforcement Learning With Potential-Guided Optimization and Weight Scheduling","display_name":"Humanoid Five-Digit Robotic Grasping via Multi-Agent Reinforcement Learning With Potential-Guided Optimization and Weight Scheduling","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7134952522","doi":"https://doi.org/10.1109/tase.2026.3672621"},"language":null,"primary_location":{"id":"doi:10.1109/tase.2026.3672621","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2026.3672621","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":"https://openalex.org/A5128745652","display_name":"Jiashuai Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiashuai Wang","raw_affiliation_strings":["Center for Intelligent Medical Engineering, School of Control Science and Engineering, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0001-8064-7741","affiliations":[{"raw_affiliation_string":"Center for Intelligent Medical Engineering, School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ke Li","orcid":"https://orcid.org/0000-0002-8660-0116"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Li","raw_affiliation_strings":["Center for Intelligent Medical Engineering, School of Control Science and Engineering, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0002-8660-0116","affiliations":[{"raw_affiliation_string":"Center for Intelligent Medical Engineering, School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100357657","display_name":"Xiaoyu Wang","orcid":"https://orcid.org/0000-0003-4664-2108"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyu Wang","raw_affiliation_strings":["Center for Intelligent Medical Engineering, School of Control Science and Engineering, Shandong University, Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Intelligent Medical Engineering, School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128695851","display_name":"Guanglin Li","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanglin Li","raw_affiliation_strings":["CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0001-9016-2617","affiliations":[{"raw_affiliation_string":"CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I4210145761","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077069697","display_name":"Zong\u2010Ming Li","orcid":"https://orcid.org/0000-0002-9636-7012"},"institutions":[{"id":"https://openalex.org/I138006243","display_name":"University of Arizona","ror":"https://ror.org/03m2x1q45","country_code":"US","type":"education","lineage":["https://openalex.org/I138006243"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zong-Ming Li","raw_affiliation_strings":["Department of Orthopaedic Surgery, The University of Arizona, Tucson, AZ, USA"],"raw_orcid":"https://orcid.org/0000-0002-9636-7012","affiliations":[{"raw_affiliation_string":"Department of Orthopaedic Surgery, The University of Arizona, Tucson, AZ, USA","institution_ids":["https://openalex.org/I138006243"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128791346","display_name":"Na Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Na Zhang","raw_affiliation_strings":["Center for Intelligent Medical Engineering, School of Control Science and Engineering, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0002-3512-5896","affiliations":[{"raw_affiliation_string":"Center for Intelligent Medical Engineering, School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mengqi Liu","orcid":"https://orcid.org/0009-0007-2490-0897"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengqi Liu","raw_affiliation_strings":["Center for Intelligent Medical Engineering, School of Control Science and Engineering, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0009-0007-2490-0897","affiliations":[{"raw_affiliation_string":"Center for Intelligent Medical Engineering, School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5128752462","display_name":"Na Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I4210161528","display_name":"Qilu Hospital of Shandong University","ror":"https://ror.org/056ef9489","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210161528"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Na Wei","raw_affiliation_strings":["Department of Geriatrics, Qilu Hospital, Shandong University, Jinan, China"],"raw_orcid":"https://orcid.org/0000-0003-0675-0040","affiliations":[{"raw_affiliation_string":"Department of Geriatrics, Qilu Hospital, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I4210161528"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"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":0.32268605,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"23","issue":null,"first_page":"6299","last_page":"6314"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.7657999992370605,"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":0.7657999992370605,"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":0.18119999766349792,"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/T10784","display_name":"Muscle activation and electromyography studies","score":0.029999999329447746,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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":0.6668999791145325},{"id":"https://openalex.org/keywords/grippers","display_name":"Grippers","score":0.6064000129699707},{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.46560001373291016},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.43790000677108765},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.4320000112056732},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.42309999465942383},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.4226999878883362},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.387800008058548},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.3619000017642975}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6668999791145325},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6614000201225281},{"id":"https://openalex.org/C2775960376","wikidata":"https://www.wikidata.org/wiki/Q1435859","display_name":"Grippers","level":2,"score":0.6064000129699707},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5425000190734863},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.46560001373291016},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.43790000677108765},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.4320000112056732},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.42309999465942383},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.4226999878883362},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.387800008058548},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3619000017642975},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.35100001096725464},{"id":"https://openalex.org/C164660894","wikidata":"https://www.wikidata.org/wiki/Q2037833","display_name":"Piecewise","level":2,"score":0.3167000114917755},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.31610000133514404},{"id":"https://openalex.org/C2776881184","wikidata":"https://www.wikidata.org/wiki/Q83360","display_name":"Thumb","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.30799999833106995},{"id":"https://openalex.org/C119701452","wikidata":"https://www.wikidata.org/wiki/Q5165881","display_name":"Control reconfiguration","level":2,"score":0.30720001459121704},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.2996000051498413},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.28790000081062317},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.26919999718666077},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.26600000262260437},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.25929999351501465},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.2533999979496002},{"id":"https://openalex.org/C74222875","wikidata":"https://www.wikidata.org/wiki/Q16000312","display_name":"Robot kinematics","level":4,"score":0.2526000142097473},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tase.2026.3672621","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2026.3672621","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":[],"awards":[{"id":"https://openalex.org/G1986256372","display_name":null,"funder_award_id":"62073195","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5732895204","display_name":null,"funder_award_id":"62573268","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6951794512","display_name":null,"funder_award_id":"2020YFC2007904","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8950243412","display_name":null,"funder_award_id":"2020B0909020004","funder_id":"https://openalex.org/F4320336742","funder_display_name":"Key Research and Development Program of Liaoning Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320336742","display_name":"Key Research and Development Program of Liaoning Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Dexterous":[0],"multi-finger":[1],"robotic":[2,251],"grasping":[3,124,183,192,220,260,320],"faces":[4],"two":[5,63],"primary":[6],"limitations:":[7],"(1)":[8,67],"traditional":[9],"demonstration-based":[10],"learning":[11,34],"requires":[12],"a":[13,68,96,132,139,153,164,182,189,201,209,230,237,276],"separate":[14],"trajectory":[15,87],"to":[16,36,50,85,143,162,170,217,270,305],"be":[17],"trained":[18,281],"for":[19,126,335],"each":[20],"object":[21,128,195],"type,":[22],"resulting":[23],"in":[24,108,227,268,282,300,315,325],"limited":[25,133],"generalization":[26,314],"across":[27,193],"different":[28],"objects;":[29],"and":[30,44,53,89,94,112,208,222,261,265,285,303,313,317,322,344],"(2)":[31,95],"single-agent":[32],"reinforcement":[33],"struggles":[35],"coordinate":[37],"the":[38,42,110,121,178,198,205,213,219,225,250,310,326],"asynchronous":[39],"motions":[40],"of":[41,123,135,186,224],"thumb":[43,111],"fingers":[45,113],"with":[46,81,157,242],"heterogeneous":[47],"joints,":[48],"leading":[49],"inefficient":[51],"exploration":[52],"slow":[54],"convergence.":[55,151],"To":[56],"overcome":[57],"these":[58],"limitations,":[59],"this":[60,147,254,292],"study":[61],"proposed":[62,179,330],"core":[64],"innovations,":[65],"including":[66,339],"dynamic":[69,78],"modulation":[70,92],"kernel":[71],"movement":[72,79,83],"primitive":[73],"(DM-KMP)":[74],"algorithm,":[75],"which":[76,109],"combines":[77],"primitives":[80,84],"kernel-based":[82],"preserve":[86],"topology":[88],"local":[90],"probabilistic":[91],"characteristics;":[93],"novel":[97,255],"potential-guided":[98],"weight":[99,158],"scheduling":[100,159],"multi-agent":[101],"deep":[102],"deterministic":[103],"policy":[104,278],"gradient":[105],"method":[106,148,256,293,331],"(PWS-MADDPG),":[107],"are":[114],"modeled":[115],"as":[116],"independent":[117],"agents.":[118],"This":[119],"enables":[120],"generation":[122],"trajectories":[125],"diverse":[127],"categories":[129],"using":[130,236,253],"only":[131],"number":[134],"demonstrations.":[136],"By":[137],"leveraging":[138],"potential":[140,334],"field":[141],"model":[142,150],"optimize":[144],"action":[145],"selection,":[146],"accelerates":[149],"Moreover,":[152],"multi-modal":[154],"reward":[155],"function":[156],"was":[160,234],"designed":[161,235],"facilitate":[163],"seamless":[165],"transition":[166],"from":[167],"individual":[168],"optimization":[169],"coordinated":[171],"team":[172],"behavior.":[173],"Experiment":[174],"results":[175,247],"demonstrated":[176],"that":[177,249,279,291],"PWS-MADDPG":[180],"achieved":[181],"success":[184],"rate":[185],"85.48%":[187],"on":[188,275],"dexterous":[190],"hand":[191,252],"11":[194],"categories,":[196],"outperforming":[197],"existing":[199],"approaches\u2014with":[200],"40.31%":[202],"improvement":[203,211],"over":[204,212],"DDPG":[206],"algorithm":[207],"20.05%":[210],"MADDPG":[214],"algorithm.":[215],"Furthermore,":[216],"verify":[218],"stability":[221],"adaptability":[223],"system":[226],"real-world":[228,286,327],"scenarios,":[229],"grip-force":[231],"validation":[232],"experiment":[233],"custom":[238],"cylindrical":[239],"apparatus":[240],"embedded":[241],"five":[243],"six-axis":[244],"sensors.":[245],"These":[246,288],"demonstrate":[248],"can":[257],"maintain":[258],"stable":[259],"adaptively":[262],"regulate":[263],"grip":[264],"load":[266],"forces":[267],"response":[269],"incremental":[271],"external":[272],"loads,":[273],"based":[274],"control":[277],"is":[280],"both":[283,309],"simulation":[284],"environments.":[287],"findings":[289],"suggest":[290],"has":[294],"strong":[295,333],"Sim-to-Real":[296],"transferability,":[297],"biological":[298],"plausibility":[299],"force":[301],"adjustment,":[302],"robustness":[304,321],"environmental":[306],"disturbances,":[307],"enhancing":[308],"training":[311],"efficiency":[312],"simulation,":[316],"demonstrating":[318],"high":[319],"successful":[323],"rates":[324],"tasks.":[328],"The":[329],"holds":[332],"high-precision,":[336],"safety-critical":[337],"applications,":[338],"intelligent":[340],"manufacturing,":[341],"prosthetic":[342],"control,":[343],"living":[345],"assistance.":[346]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-12T00:00:00"}
