{"id":"https://openalex.org/W7160616135","doi":"https://doi.org/10.1109/tase.2026.3691390","title":"Linear Attention-Driven DRL With Sparse Expert Fusion: A Dynamic Optimization Algorithm of Underwater Manipulator for Long Horizon Tasks","display_name":"Linear Attention-Driven DRL With Sparse Expert Fusion: A Dynamic Optimization Algorithm of Underwater Manipulator for Long Horizon Tasks","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7160616135","doi":"https://doi.org/10.1109/tase.2026.3691390"},"language":null,"primary_location":{"id":"doi:10.1109/tase.2026.3691390","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2026.3691390","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/A5065157502","display_name":"Y Li","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yufeng Li","raw_affiliation_strings":["School of Marine Science and Technology, Northwestern Polytechnical University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0003-0634-6734","affiliations":[{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135639782","display_name":"Jian Gao","orcid":"https://orcid.org/0000-0002-1181-4531"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Gao","raw_affiliation_strings":["School of Marine Science and Technology, Northwestern Polytechnical University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0002-1181-4531","affiliations":[{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062925729","display_name":"Y Z Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yimin Chen","raw_affiliation_strings":["School of Marine Science and Technology, Northwestern Polytechnical University, Xi’an, China"],"raw_orcid":"https://orcid.org/0000-0003-1562-1443","affiliations":[{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":5.0077,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.95672528,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"23","issue":null,"first_page":"9695","last_page":"9708"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11192","display_name":"Underwater Vehicles and Communication Systems","score":0.6313999891281128,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean 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/T11192","display_name":"Underwater Vehicles and Communication Systems","score":0.6313999891281128,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean 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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.05290000140666962,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.044599998742341995,"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/manipulator","display_name":"Manipulator (device)","score":0.5468999743461609},{"id":"https://openalex.org/keywords/optimization-algorithm","display_name":"Optimization algorithm","score":0.4927000105381012},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4580000042915344},{"id":"https://openalex.org/keywords/horizon","display_name":"Horizon","score":0.4269999861717224},{"id":"https://openalex.org/keywords/underwater","display_name":"Underwater","score":0.4171999990940094},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.3698999881744385},{"id":"https://openalex.org/keywords/linear-programming","display_name":"Linear programming","score":0.35019999742507935},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.3427000045776367}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6212000250816345},{"id":"https://openalex.org/C2781347998","wikidata":"https://www.wikidata.org/wiki/Q1587588","display_name":"Manipulator (device)","level":3,"score":0.5468999743461609},{"id":"https://openalex.org/C2987595161","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Optimization algorithm","level":2,"score":0.4927000105381012},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4580000042915344},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4311000108718872},{"id":"https://openalex.org/C159176650","wikidata":"https://www.wikidata.org/wiki/Q43261","display_name":"Horizon","level":2,"score":0.4269999861717224},{"id":"https://openalex.org/C98083399","wikidata":"https://www.wikidata.org/wiki/Q3246517","display_name":"Underwater","level":2,"score":0.4171999990940094},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.40540000796318054},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.3698999881744385},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.35019999742507935},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.3427000045776367},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.32339999079704285},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C2985527887","wikidata":"https://www.wikidata.org/wiki/Q1587588","display_name":"Robot manipulator","level":3,"score":0.3059000074863434},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.30169999599456787},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C79487989","wikidata":"https://www.wikidata.org/wiki/Q934680","display_name":"Vehicle dynamics","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C55660270","wikidata":"https://www.wikidata.org/wiki/Q5164377","display_name":"Constrained optimization","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tase.2026.3691390","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2026.3691390","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/G2622849348","display_name":null,"funder_award_id":"52571392","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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Deep":[0],"Reinforcement":[1],"Learning":[2],"(DRL),":[3],"leveraging":[4],"the":[5,141,171,177,180,195,212,236],"nonlinear":[6],"approximation":[7],"capabilities":[8],"of":[9,66,90,96,179,220],"deep":[10],"neural":[11],"networks,":[12],"maps":[13],"high-dimensional":[14,41,146],"perception":[15],"information":[16],"to":[17,26,50,57,130,143,162],"robotic":[18],"control":[19,29,95],"commands":[20],"and":[21,44,54,149,206,224,239],"has":[22],"been":[23],"widely":[24],"applied":[25],"various":[27,200],"continuous":[28],"tasks.":[30,154],"However,":[31],"for":[32,70,93,166],"long-horizon":[33,94,173,201],"tasks,":[34,202],"manipulators":[35,72],"often":[36],"face":[37],"challenges":[38],"such":[39],"as":[40],"exploration":[42],"spaces":[43],"sparse":[45],"rewards,":[46],"making":[47],"it":[48],"difficult":[49],"learn":[51,164],"effective":[52],"strategies":[53],"even":[55],"leading":[56],"potentially":[58],"dangerous":[59],"actions.":[60],"Additionally,":[61,227],"collecting":[62],"a":[63,82,87,100,112,123,156,231],"large":[64],"volume":[65],"high-quality":[67],"expert":[68,91,107],"demonstrations":[69],"underwater":[71,97,184,243],"is":[73,109,128,160,187,197],"challenging.":[74],"To":[75,175],"overcome":[76],"these":[77],"limitations,":[78],"this":[79,192],"study":[80],"proposes":[81],"DRL":[83,101],"algorithm":[84,214],"that":[85,117,211],"integrates":[86],"small":[88],"amount":[89],"experience":[92,108],"manipulators.":[98],"Firstly,":[99],"dynamic":[102,114],"optimization":[103],"strategy":[104],"based":[105],"on":[106,199],"designed,":[110],"featuring":[111],"dual-buffer":[113],"sampling":[115],"mechanism":[116,126],"enables":[118],"efficient":[119],"early-stage":[120],"learning.":[121],"Secondly,":[122],"linear":[124],"attention":[125],"network":[127],"developed":[129],"aggregate":[131],"global":[132],"task":[133,221],"features":[134,151],"while":[135],"maintaining":[136],"low":[137],"computational":[138],"complexity,":[139],"allowing":[140],"model":[142],"effectively":[144],"process":[145],"sensory":[147],"inputs":[148],"share":[150],"across":[152],"multiple":[153],"Furthermore,":[155],"staged":[157],"reward":[158],"function":[159],"designed":[161],"steadily":[163],"skills":[165],"each":[167],"phase,":[168],"ultimately":[169],"completing":[170],"entire":[172],"task.":[174],"validate":[176],"effectiveness":[178],"proposed":[181,213],"algorithm,":[182],"an":[183],"simulation":[185,193],"environment":[186,234],"constructed":[188],"in":[189,218,230,241],"Gazebo.":[190],"In":[191],"environment,":[194],"manipulator":[196],"trained":[198],"including":[203],"grasp-place,":[204],"grasp-stack,":[205],"grasp-insert.":[207],"Training":[208],"results":[209],"demonstrate":[210],"outperforms":[215],"existing":[216],"methods":[217],"terms":[219],"success":[222],"rate":[223],"policy":[225],"stability.":[226],"real-world":[228],"experiments":[229],"water":[232],"tank":[233],"verify":[235],"algorithm\u2019s":[237],"generalization":[238],"robustness":[240],"practical":[242],"operations.":[244]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2026-05-09T00:00:00"}