{"id":"https://openalex.org/W3109297494","doi":"https://doi.org/10.1109/icca51439.2020.9264562","title":"Motion Planning Using Reinforcement Learning Method for Underactuated Ship Berthing","display_name":"Motion Planning Using Reinforcement Learning Method for Underactuated Ship Berthing","publication_year":2020,"publication_date":"2020-10-09","ids":{"openalex":"https://openalex.org/W3109297494","doi":"https://doi.org/10.1109/icca51439.2020.9264562","mag":"3109297494"},"language":"en","primary_location":{"id":"doi:10.1109/icca51439.2020.9264562","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icca51439.2020.9264562","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 16th International Conference on Control & Automation (ICCA)","raw_type":"proceedings-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/A5100340490","display_name":"Haoran Zhang","orcid":"https://orcid.org/0000-0002-6883-1375"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haoran Zhang","raw_affiliation_strings":["School of Electronic and Information Engineering, Beijing Jiaotong University,Beijing,China,100044","School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, Beijing Jiaotong University,Beijing,China,100044","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113862617","display_name":"Chenkun Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenkun Yin","raw_affiliation_strings":["School of Electronic and Information Engineering, Beijing Jiaotong University,Beijing,China,100044","School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, Beijing Jiaotong University,Beijing,China,100044","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101621515","display_name":"Yanxin Zhang","orcid":"https://orcid.org/0000-0002-1767-7371"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanxin Zhang","raw_affiliation_strings":["School of Electronic and Information Engineering, Beijing Jiaotong University,Beijing,China,100044","School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, Beijing Jiaotong University,Beijing,China,100044","institution_ids":["https://openalex.org/I21193070"]},{"raw_affiliation_string":"School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100340490"],"corresponding_institution_ids":["https://openalex.org/I21193070"],"apc_list":null,"apc_paid":null,"fwci":0.4625,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.67942865,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"354","last_page":"359"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9980000257492065,"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/T12288","display_name":"Optimization and Search Problems","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8599834442138672},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7159260511398315},{"id":"https://openalex.org/keywords/underactuation","display_name":"Underactuation","score":0.6767100095748901},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.6759977340698242},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6669237613677979},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.617838978767395},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.4968867599964142},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.46705543994903564},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4257630705833435},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4101235270500183},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.36282169818878174},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3060249090194702},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.20862874388694763},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14577904343605042},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10139283537864685},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09975829720497131}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8599834442138672},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7159260511398315},{"id":"https://openalex.org/C88337583","wikidata":"https://www.wikidata.org/wiki/Q7883433","display_name":"Underactuation","level":3,"score":0.6767100095748901},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.6759977340698242},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6669237613677979},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.617838978767395},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4968867599964142},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.46705543994903564},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4257630705833435},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4101235270500183},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.36282169818878174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3060249090194702},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.20862874388694763},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14577904343605042},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10139283537864685},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09975829720497131},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icca51439.2020.9264562","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icca51439.2020.9264562","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 16th International Conference on Control & Automation (ICCA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"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":34,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1590684588","https://openalex.org/W1651569867","https://openalex.org/W1681187736","https://openalex.org/W2028240448","https://openalex.org/W2097163193","https://openalex.org/W2103398491","https://openalex.org/W2112908524","https://openalex.org/W2118525123","https://openalex.org/W2120944681","https://openalex.org/W2121863487","https://openalex.org/W2126909264","https://openalex.org/W2138668952","https://openalex.org/W2144540407","https://openalex.org/W2145339207","https://openalex.org/W2153344813","https://openalex.org/W2164429173","https://openalex.org/W2165150801","https://openalex.org/W2173248099","https://openalex.org/W2345644119","https://openalex.org/W2753865800","https://openalex.org/W2767518680","https://openalex.org/W2781726626","https://openalex.org/W2787938642","https://openalex.org/W2897661175","https://openalex.org/W2919417890","https://openalex.org/W2962902376","https://openalex.org/W2963864421","https://openalex.org/W4302570325","https://openalex.org/W6636911616","https://openalex.org/W6657403861","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6747473740"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W1985560493","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W4284974072","https://openalex.org/W2341346307","https://openalex.org/W4225269853"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,25,30,46],"novel":[4],"motion":[5,19,95],"planning":[6,20,96],"method":[7],"for":[8,36,62,112],"underactuated":[9],"ship":[10,64],"berthing":[11,18,39,67],"using":[12],"reinforcement":[13],"learning":[14],"(RL)":[15],"technique.":[16],"The":[17,41,57],"problem":[21,42],"is":[22,34,43,103],"formulated":[23],"as":[24],"Markov":[26],"Decision":[27],"Process,":[28],"where":[29],"specified":[31],"reward":[32],"function":[33],"designed":[35],"the":[37,63,70,79,90,99,113],"accurate":[38],"task.":[40,115],"addressed":[44],"by":[45,85,105],"state-of-art":[47],"RL":[48,93],"algorithm,":[49],"Twin":[50],"Delayed":[51],"Deep":[52,108],"Deterministic":[53,109],"Policy":[54,110],"Gradient":[55,111],"(TD3).":[56],"generated":[58],"trajectories":[59],"are":[60,73],"feasible":[61],"to":[65],"accomplish":[66],"task,":[68],"since":[69],"system":[71],"constraints":[72],"fully":[74],"taken":[75],"into":[76],"consideration":[77],"when":[78],"trained":[80],"agent":[81],"interacts":[82],"with":[83,107],"environment":[84],"RL.":[86],"Simulation":[87],"results":[88],"verify":[89],"effectiveness":[91],"of":[92,101],"based":[94],"method,":[97],"and":[98],"advantage":[100],"TD3":[102],"shown":[104],"comparison":[106],"same":[114]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-02-01T03:34:12.195049","created_date":"2025-10-10T00:00:00"}