{"id":"https://openalex.org/W7103898793","doi":"https://doi.org/10.1109/tase.2025.3628910","title":"A Two-Stage Reinforcement Learning Algorithm for AUV Path Planning Based on Trajectory Exploration and Sequence Modeling","display_name":"A Two-Stage Reinforcement Learning Algorithm for AUV Path Planning Based on Trajectory Exploration and Sequence Modeling","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W7103898793","doi":"https://doi.org/10.1109/tase.2025.3628910"},"language":null,"primary_location":{"id":"doi:10.1109/tase.2025.3628910","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2025.3628910","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":"Yue Liu","orcid":"https://orcid.org/0009-0006-7892-212X"},"institutions":[{"id":"https://openalex.org/I31847773","display_name":"Zhejiang Ocean University","ror":"https://ror.org/03mys6533","country_code":"CN","type":"education","lineage":["https://openalex.org/I31847773"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yue Liu","raw_affiliation_strings":["State Key Laboratory of Ocean Sensing and the Ocean College, Zhejiang University, Zhoushan, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Ocean Sensing and the Ocean College, Zhejiang University, Zhoushan, China","institution_ids":["https://openalex.org/I31847773"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Huan Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I31847773","display_name":"Zhejiang Ocean University","ror":"https://ror.org/03mys6533","country_code":"CN","type":"education","lineage":["https://openalex.org/I31847773"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huan Tang","raw_affiliation_strings":["State Key Laboratory of Ocean Sensing and the Ocean College, Zhejiang University, Zhoushan, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Ocean Sensing and the Ocean College, Zhejiang University, Zhoushan, China","institution_ids":["https://openalex.org/I31847773"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiacheng Li","orcid":"https://orcid.org/0000-0002-4193-3718"},"institutions":[{"id":"https://openalex.org/I31847773","display_name":"Zhejiang Ocean University","ror":"https://ror.org/03mys6533","country_code":"CN","type":"education","lineage":["https://openalex.org/I31847773"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiacheng Li","raw_affiliation_strings":["State Key Laboratory of Ocean Sensing and the Ocean College, Zhejiang University, Zhoushan, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Ocean Sensing and the Ocean College, Zhejiang University, Zhoushan, China","institution_ids":["https://openalex.org/I31847773"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yun Xu","orcid":"https://orcid.org/0009-0004-7686-3408"},"institutions":[{"id":"https://openalex.org/I31847773","display_name":"Zhejiang Ocean University","ror":"https://ror.org/03mys6533","country_code":"CN","type":"education","lineage":["https://openalex.org/I31847773"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Xu","raw_affiliation_strings":["State Key Laboratory of Ocean Sensing and the Ocean College, Zhejiang University, Zhoushan, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Ocean Sensing and the Ocean College, Zhejiang University, Zhoushan, China","institution_ids":["https://openalex.org/I31847773"]}]},{"author_position":"last","author":{"id":null,"display_name":"Dongfang Ma","orcid":"https://orcid.org/0000-0002-9334-1570"},"institutions":[{"id":"https://openalex.org/I31847773","display_name":"Zhejiang Ocean University","ror":"https://ror.org/03mys6533","country_code":"CN","type":"education","lineage":["https://openalex.org/I31847773"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongfang Ma","raw_affiliation_strings":["State Key Laboratory of Ocean Sensing and the Ocean College, Zhejiang University, Zhoushan, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Ocean Sensing and the Ocean College, Zhejiang University, Zhoushan, China","institution_ids":["https://openalex.org/I31847773"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I31847773"],"apc_list":null,"apc_paid":null,"fwci":1.2181,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.86070627,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"22","issue":null,"first_page":"23671","last_page":"23686"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.5171999931335449,"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"}},"topics":[{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.5171999931335449,"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/T11622","display_name":"Maritime Navigation and Safety","score":0.25870001316070557,"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/T11192","display_name":"Underwater Vehicles and Communication Systems","score":0.13910000026226044,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.774399995803833},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.666100025177002},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.571399986743927},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.5590999722480774},{"id":"https://openalex.org/keywords/underwater","display_name":"Underwater","score":0.5242999792098999},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.37560001015663147},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.3560999929904938},{"id":"https://openalex.org/keywords/remotely-operated-underwater-vehicle","display_name":"Remotely operated underwater vehicle","score":0.35269999504089355}],"concepts":[{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.774399995803833},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.666100025177002},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5873000025749207},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.571399986743927},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.5590999722480774},{"id":"https://openalex.org/C98083399","wikidata":"https://www.wikidata.org/wiki/Q3246517","display_name":"Underwater","level":2,"score":0.5242999792098999},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39250001311302185},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.38199999928474426},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.37560001015663147},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.3560999929904938},{"id":"https://openalex.org/C145424490","wikidata":"https://www.wikidata.org/wiki/Q618465","display_name":"Remotely operated underwater vehicle","level":4,"score":0.35269999504089355},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3499999940395355},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34310001134872437},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3359000086784363},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.329800009727478},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3273000121116638},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C6683253","wikidata":"https://www.wikidata.org/wiki/Q7075535","display_name":"Obstacle avoidance","level":4,"score":0.28940001130104065},{"id":"https://openalex.org/C115286129","wikidata":"https://www.wikidata.org/wiki/Q123637","display_name":"Cybernetics","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.2786000072956085},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.260699987411499},{"id":"https://openalex.org/C176809094","wikidata":"https://www.wikidata.org/wiki/Q15401496","display_name":"Traverse","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.25540000200271606}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tase.2025.3628910","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2025.3628910","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":[{"display_name":"Affordable and clean energy","score":0.6992650628089905,"id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G1180317521","display_name":null,"funder_award_id":"52172334","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5111099937","display_name":null,"funder_award_id":"226-2023-00076","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G8223566187","display_name":null,"funder_award_id":"52131202","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"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1969483458","https://openalex.org/W1971086298","https://openalex.org/W2022467028","https://openalex.org/W2146500120","https://openalex.org/W2203166257","https://openalex.org/W3011646207","https://openalex.org/W3088197938","https://openalex.org/W3094883192","https://openalex.org/W3097665789","https://openalex.org/W3173581352","https://openalex.org/W3184852195","https://openalex.org/W3190079665","https://openalex.org/W3208245500","https://openalex.org/W4200635426","https://openalex.org/W4214496626","https://openalex.org/W4214735187","https://openalex.org/W4214897012","https://openalex.org/W4220843464","https://openalex.org/W4226153434","https://openalex.org/W4229082946","https://openalex.org/W4285818829","https://openalex.org/W4286370041","https://openalex.org/W4295278317","https://openalex.org/W4311513675","https://openalex.org/W4311774321","https://openalex.org/W4313191203","https://openalex.org/W4320015828","https://openalex.org/W4379382588","https://openalex.org/W4382239271","https://openalex.org/W4383742735","https://openalex.org/W4383891636","https://openalex.org/W4385251244","https://openalex.org/W4386023990","https://openalex.org/W4392349475","https://openalex.org/W4392824157","https://openalex.org/W4399310716","https://openalex.org/W4400228806","https://openalex.org/W4400726769","https://openalex.org/W4402793275","https://openalex.org/W4404840285","https://openalex.org/W4406983280","https://openalex.org/W4409327420","https://openalex.org/W4415797600"],"related_works":[],"abstract_inverted_index":{"Path":[0],"planning":[1,16],"is":[2,30,36,116,148],"essential":[3],"for":[4,89],"autonomous":[5],"underwater":[6,24,34],"vehicles":[7],"(AUVs)":[8],"to":[9,85,98,118,150,156,162,175],"perform":[10],"tasks.":[11],"Many":[12],"existing":[13,176],"single-objective":[14],"path":[15,168,182,194],"methods":[17],"rely":[18],"on":[19,56],"prior":[20,28,75],"knowledge":[21,29],"of":[22,128,154],"the":[23,33,63,80,93,107,136,152,157,181],"environment.":[25],"However,":[26],"extracting":[27],"challenging":[31],"because":[32],"environment":[35],"influenced":[37],"by":[38,187,196],"ocean":[39],"current,":[40],"complex":[41],"terrain,":[42],"and":[43,59,67,91,103,144,184,189],"other":[44],"factors.":[45],"This":[46,77],"paper":[47],"proposes":[48],"a":[49,100,110,139],"two-stage":[50],"reinforcement":[51],"learning":[52],"(RL)":[53],"algorithm":[54,78],"based":[55],"trajectory":[57,120],"exploration":[58,83,121],"sequence":[60],"modeling,":[61],"called":[62],"Soft":[64],"Actor":[65],"Critic":[66],"Online":[68],"Decision":[69],"Transformer":[70],"(SAC-ODT),":[71],"which":[72],"operates":[73],"without":[74],"knowledge.":[76],"utilizes":[79],"SAC":[81],"strategy":[82,95],"capability":[84,97],"generate":[86],"training":[87,127],"data":[88],"ODT":[90,94,130,155],"uses":[92],"optimization":[96],"plan":[99],"smooth,":[101],"energy-efficient,":[102],"safe":[104],"path.":[105],"In":[106],"first":[108],"stage,":[109,138],"Multi-Reward":[111],"Strategy":[112,146],"Embedding":[113],"(MRSE)":[114],"method":[115],"designed":[117],"facilitate":[119],"with":[122,131],"multiple":[123],"strategies,":[124],"enabling":[125,160],"further":[126],"an":[129],"comprehensive":[132],"decision-making":[133],"capability.":[134],"During":[135],"second":[137],"Condition":[140],"Prioritized":[141],"Buffer":[142],"Update":[143],"Sampling":[145],"(CP-BUSS)":[147],"proposed":[149],"enhance":[151],"sensitivity":[153],"reward":[158],"function,":[159],"adaptation":[161],"various":[163],"tasks":[164],"while":[165,192],"accelerating":[166],"high-quality":[167],"learning.":[169],"Experimental":[170],"results":[171],"demonstrate":[172],"that":[173],"compared":[174],"RL-based":[177],"benchmarks,":[178],"SAC-ODT":[179],"reduces":[180],"time":[183],"energy":[185],"consumption":[186],"2.7%":[188],"2.5%,":[190],"respectively,":[191],"improving":[193],"smoothness":[195],"91.96%.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-05T00:00:00"}