{"id":"https://openalex.org/W7126418888","doi":"https://doi.org/10.1007/s10846-026-02360-6","title":"Multi-Agent Continual Deep Reinforcement Learning with Artificial Potential Fields and Switching Control for a Cooperative Robotic Task","display_name":"Multi-Agent Continual Deep Reinforcement Learning with Artificial Potential Fields and Switching Control for a Cooperative Robotic Task","publication_year":2026,"publication_date":"2026-01-31","ids":{"openalex":"https://openalex.org/W7126418888","doi":"https://doi.org/10.1007/s10846-026-02360-6"},"language":"en","primary_location":{"id":"doi:10.1007/s10846-026-02360-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10846-026-02360-6","pdf_url":null,"source":{"id":"https://openalex.org/S91329792","display_name":"Journal of Intelligent & Robotic Systems","issn_l":"0921-0296","issn":["0921-0296","1573-0409"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent & Robotic Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1007/s10846-026-02360-6","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035254151","display_name":"Wenbo Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenbo Tan","raw_affiliation_strings":["School of Automation(Artificial Intelligence), Hangzhou Dianzi University, No. 1158, 2nd Avenue, Xiasha, Hangzhou, 310018, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation(Artificial Intelligence), Hangzhou Dianzi University, No. 1158, 2nd Avenue, Xiasha, Hangzhou, 310018, Zhejiang, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101867742","display_name":"Qiang Lv","orcid":"https://orcid.org/0000-0001-7349-2665"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Lv","raw_affiliation_strings":["School of Automation(Artificial Intelligence), Hangzhou Dianzi University, No. 1158, 2nd Avenue, Xiasha, Hangzhou, 310018, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation(Artificial Intelligence), Hangzhou Dianzi University, No. 1158, 2nd Avenue, Xiasha, Hangzhou, 310018, Zhejiang, China","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124671406","display_name":"Xiangqing Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210163399","display_name":"Shandong First Medical University","ror":"https://ror.org/05jb9pq57","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163399"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"XiangQing Li","raw_affiliation_strings":["College of Medical Information and Artificial Intelligence, Shandong First Medical University, No. 6699 Qingdao Road, Jinan, 250117, Shandong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Medical Information and Artificial Intelligence, Shandong First Medical University, No. 6699 Qingdao Road, Jinan, 250117, Shandong, China","institution_ids":["https://openalex.org/I4210163399"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124524564","display_name":"Na Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I4210163399","display_name":"Shandong First Medical University","ror":"https://ror.org/05jb9pq57","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163399"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Na Sun","raw_affiliation_strings":["College of Medical Information and Artificial Intelligence, Shandong First Medical University, No. 6699 Qingdao Road, Jinan, 250117, Shandong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Medical Information and Artificial Intelligence, Shandong First Medical University, No. 6699 Qingdao Road, Jinan, 250117, Shandong, China","institution_ids":["https://openalex.org/I4210163399"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061069541","display_name":"Na Huang","orcid":"https://orcid.org/0000-0001-7009-4418"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Na Huang","raw_affiliation_strings":["School of Automation(Artificial Intelligence), Hangzhou Dianzi University, No. 1158, 2nd Avenue, Xiasha, Hangzhou, 310018, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation(Artificial Intelligence), Hangzhou Dianzi University, No. 1158, 2nd Avenue, Xiasha, Hangzhou, 310018, Zhejiang, China","institution_ids":["https://openalex.org/I50760025"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5035254151"],"corresponding_institution_ids":["https://openalex.org/I50760025"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11829486,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"112","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8543999791145325,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8543999791145325,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.05249999836087227,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.0272000003606081,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7835999727249146},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5040000081062317},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4636000096797943},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.4512999951839447},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4207000136375427},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.40119999647140503},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.38280001282691956},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3734999895095825},{"id":"https://openalex.org/keywords/human-multitasking","display_name":"Human multitasking","score":0.36809998750686646}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7835999727249146},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.744700014591217},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6187000274658203},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5040000081062317},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4636000096797943},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.4512999951839447},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4207000136375427},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.40119999647140503},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.38280001282691956},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3734999895095825},{"id":"https://openalex.org/C107418235","wikidata":"https://www.wikidata.org/wiki/Q1520565","display_name":"Human multitasking","level":2,"score":0.36809998750686646},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.36160001158714294},{"id":"https://openalex.org/C2780323453","wikidata":"https://www.wikidata.org/wiki/Q7113957","display_name":"Overshoot (microwave communication)","level":2,"score":0.3544999957084656},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.3531999886035919},{"id":"https://openalex.org/C172707124","wikidata":"https://www.wikidata.org/wiki/Q423488","display_name":"Actuator","level":2,"score":0.35089999437332153},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.3508000075817108},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.33820000290870667},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.337799996137619},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.33489999175071716},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.31060001254081726},{"id":"https://openalex.org/C526921623","wikidata":"https://www.wikidata.org/wiki/Q190117","display_name":"Automotive industry","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.2874999940395355},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C17816587","wikidata":"https://www.wikidata.org/wiki/Q1501872","display_name":"Inverse kinematics","level":3,"score":0.2696000039577484},{"id":"https://openalex.org/C2775960376","wikidata":"https://www.wikidata.org/wiki/Q1435859","display_name":"Grippers","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.2547000050544739},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10846-026-02360-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10846-026-02360-6","pdf_url":null,"source":{"id":"https://openalex.org/S91329792","display_name":"Journal of Intelligent & Robotic Systems","issn_l":"0921-0296","issn":["0921-0296","1573-0409"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent & Robotic Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10846-026-02360-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10846-026-02360-6","pdf_url":null,"source":{"id":"https://openalex.org/S91329792","display_name":"Journal of Intelligent & Robotic Systems","issn_l":"0921-0296","issn":["0921-0296","1573-0409"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent & Robotic Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4444859027862549,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W2058334894","https://openalex.org/W2103120971","https://openalex.org/W2112474089","https://openalex.org/W2113260111","https://openalex.org/W2116966230","https://openalex.org/W2560647685","https://openalex.org/W2736601468","https://openalex.org/W2785926206","https://openalex.org/W2904246096","https://openalex.org/W2921955147","https://openalex.org/W2963403593","https://openalex.org/W2968526727","https://openalex.org/W3088304681","https://openalex.org/W3117215073","https://openalex.org/W3179821297","https://openalex.org/W3204523122","https://openalex.org/W3205960420","https://openalex.org/W4210444794","https://openalex.org/W4220683105","https://openalex.org/W4252939763","https://openalex.org/W4280536386","https://openalex.org/W4286893914","https://openalex.org/W4299802797","https://openalex.org/W4307234290","https://openalex.org/W4362519817","https://openalex.org/W4377862404","https://openalex.org/W4383604734","https://openalex.org/W4386148416","https://openalex.org/W4387087834","https://openalex.org/W4389306512","https://openalex.org/W4389363807","https://openalex.org/W4390968395","https://openalex.org/W4391919254","https://openalex.org/W4392063227","https://openalex.org/W4392173735","https://openalex.org/W4392672418","https://openalex.org/W4393131855","https://openalex.org/W4394745351","https://openalex.org/W4395448724","https://openalex.org/W4396600726","https://openalex.org/W4399014819","https://openalex.org/W4400438493","https://openalex.org/W4401071725","https://openalex.org/W4401793915","https://openalex.org/W4402354150","https://openalex.org/W4402891929","https://openalex.org/W4403598347","https://openalex.org/W4406072527","https://openalex.org/W4410717250","https://openalex.org/W4412391533","https://openalex.org/W6921608480"],"related_works":[],"abstract_inverted_index":{"Autonomy":[0],"and":[1,47,75,110,139,174,203,210,220,285,296,305],"intelligence":[2],"are":[3,51],"the":[4,132,136,145,158,185,196,266,276,282],"key":[5],"directions":[6],"of":[7],"modern":[8],"manufacturing,":[9],"with":[10,69,207,260],"Deep":[11],"Reinforcement":[12],"Learning":[13],"(DRL)":[14],"providing":[15],"important":[16],"technical":[17],"support":[18],"for":[19,33,86,190,239],"robots":[20],"to":[21,117,142,165,225,271,280,303],"acquire":[22],"skills":[23],"autonomously.":[24],"Multi-agent":[25],"reinforcement":[26],"learning":[27,201],"(MARL)":[28],"offers":[29],"a":[30,59,76,103,106,127,179,261],"principled":[31],"framework":[32,61,268],"coordinated":[34],"decision-making":[35],"in":[36],"collaborative":[37],"robotics,":[38],"yet":[39],"it":[40],"often":[41],"suffers":[42],"from":[43],"poor":[44],"sample":[45],"efficiency":[46],"brittleness":[48],"when":[49,144],"demonstrations":[50],"limited.":[52],"To":[53],"address":[54],"these":[55],"issues,":[56],"we":[57,125,176],"propose":[58],"unified":[60],"that":[62,130,252,265,290],"couples":[63],"Multi-Agent":[64],"Artificial":[65],"Potential":[66],"Fields":[67],"(MAPF)":[68],"Behavior":[70],"Cloning":[71],"(BC),":[72],"continual":[73,114,294],"adaptation,":[74,295],"safety-oriented":[77],"switching":[78,128,221,243,297],"controller.":[79],"Specifically,":[80],"MAPF":[81,143,292],"generates":[82],"structured":[83],"expert":[84],"rollouts":[85],"joint-space":[87],"bimanual":[88,163],"control":[89,298],"under":[90,168,257,275],"explicit":[91],"joint":[92],"constraints,":[93],"yielding":[94],"an":[95,112,300],"effectively":[96],"unlimited":[97],"demonstration":[98],"stream.":[99],"We":[100,156,249],"then":[101],"train":[102],"policy":[104,134,284],"via":[105],"critic-gated":[107],"BC":[108,119],"loss":[109],"integrate":[111],"online":[113],"refreshing":[115],"mechanism":[116],"mitigate":[118],"overfitting":[120],"during":[121],"long-horizon":[122],"training.":[123],"Finally,":[124],"deploy":[126],"controller":[129],"uses":[131],"learned":[133,283],"as":[135],"default":[137],"solver":[138],"falls":[140],"back":[141],"time":[146],"budget":[147],"is":[148,269,299],"exceeded,":[149],"improving":[150],"reliability":[151],"while":[152,228],"retaining":[153],"low":[154],"runtime.":[155],"evaluate":[157],"approach":[159],"on":[160],"two":[161],"RoboSuite":[162],"tasks":[164],"test":[166],"generalization":[167],"goal":[169],"variations.":[170],"Under":[171],"identical":[172],"observations":[173],"rewards,":[175],"additionally":[177],"include":[178],"strong":[180],"SAC-based":[181],"CTDE/off-policy":[182],"backbone":[183],"within":[184],"same":[186],"MABCRL":[187,198],"pipeline":[188],"(MA(SAC)BCRL)":[189],"comprehensive":[191],"comparison.":[192],"Across":[193],"both":[194,281],"tasks,":[195],"proposed":[197],"training":[199],"improves":[200],"stability":[202],"final":[204],"performance":[205,253],"compared":[206],"plain":[208],"MARL":[209],"naive":[211],"BC.":[212],"On":[213,241],"ENV1,":[214],"MA(DDPG)BCRL":[215],"achieves":[216],"$$\\varvec{0.87\\pm":[217],"0.02}$$":[218],"success,":[219],"further":[222,250],"boosts":[223],"success":[224],"$$\\varvec{0.99\\pm":[226,246],"0.004}$$":[227],"maintaining":[229],"fast":[230],"execution":[231],"(about":[232],"$$\\varvec{9}$$\u2013$$\\varvec{11}$$":[233],"s/episode":[234,238],"versus":[235],"$$\\varvec{\\sim":[236],"34}$$":[237],"MAPF).":[240],"ENV2,":[242],"similarly":[244],"reaches":[245],"0.005}$$":[247],"success.":[248],"show":[251],"remains":[254],"essentially":[255],"unchanged":[256],"object-state":[258,273],"occlusion":[259],"hold":[262],"scheme,":[263],"suggesting":[264],"overall":[267],"robust":[270],"transient":[272],"missingness":[274],"observation":[277],"degradation":[278],"applied":[279],"MAPF.":[286],"These":[287],"results":[288],"suggest":[289],"combining":[291],"demonstrations,":[293],"effective":[301],"route":[302],"reliable":[304],"efficient":[306],"cooperative":[307],"robotic":[308],"manipulation.":[309]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2026-02-02T00:00:00"}