{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,13]],"date-time":"2026-09-13T21:35:10Z","timestamp":1789335310399,"version":"build-2803163510"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"21","license":[{"start":{"date-parts":[[2023,8,17]],"date-time":"2023-08-17T00:00:00Z","timestamp":1692230400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,8,17]],"date-time":"2023-08-17T00:00:00Z","timestamp":1692230400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100017683","name":"Dalian Science and Technology Innovation Fund","doi-asserted-by":"publisher","award":["2022JJ12GX015"],"award-info":[{"award-number":["2022JJ12GX015"]}],"id":[{"id":"10.13039\/501100017683","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1007\/s00521-023-08908-z","type":"journal-article","created":{"date-parts":[[2023,8,17]],"date-time":"2023-08-17T06:02:11Z","timestamp":1692252131000},"page":"15963-15977","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["A novel deep reinforcement learning for POMDP-based autonomous ship collision decision-making"],"prefix":"10.1007","volume":"37","author":[{"given":"Xinyu","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4467-3237","authenticated-orcid":false,"given":"Kangjie","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengbo","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jihong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huaiyuan","family":"Qi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,8,17]]},"reference":[{"key":"8908_CR1","unstructured":"Park HS, Cha C, Jo M (2019) A study on the guidelines for IMO maritime autonomous surface ships (MASS).Proceedings of the korean institute of navigation and port research conference. Korean institute of navigation and port research, pp 137-138"},{"key":"8908_CR2","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1017\/S037346330001599X","volume":"8","author":"JM Ss","year":"1955","unstructured":"Ss JM (1955) Collision at sea. J Navigat 8:261\u2013280","journal-title":"J Navigat"},{"key":"8908_CR3","doi-asserted-by":"publisher","first-page":"7823","DOI":"10.1109\/ACCESS.2021.3049238","volume":"9","author":"H Namgung","year":"2021","unstructured":"Namgung H, Kim JS (2021) Collision risk inference system for maritime autonomous surface ships using COLREGs rules compliant collision avoidance. IEEE Access 9:7823\u20137835","journal-title":"IEEE Access"},{"issue":"2","key":"8908_CR4","first-page":"103","volume":"3","author":"Y He","year":"2021","unstructured":"He Y, Li Z, Mou J et al (2021) Collision-avoidance path planning for multi-ship encounters considering ship manoeuvrability and COLREGs. Trans safety Environ 3(2):103\u2013113","journal-title":"Trans safety Environ"},{"issue":"3","key":"8908_CR5","doi-asserted-by":"publisher","first-page":"710","DOI":"10.1017\/S0373463319000924","volume":"73","author":"Y Zhou","year":"2020","unstructured":"Zhou Y, Huang J, Wang W et al (2020) A study of the application barriers to the use of autonomous ships posed by the good seamanship requirement of COLREGs. J Navigat 73(3):710\u2013725","journal-title":"J Navigat"},{"key":"8908_CR6","doi-asserted-by":"publisher","first-page":"4911","DOI":"10.3390\/s21144911","volume":"21","author":"X Zhang","year":"2021","unstructured":"Zhang X, Wang C, Chui KT, Liu RW (2021) A real-time collision avoidance framework of mass based on b-spline and optimal decoupling control. Sensors 21:4911","journal-title":"Sensors"},{"key":"8908_CR7","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1201\/9781003320289-18","volume":"2","author":"H Zhang","year":"2022","unstructured":"Zhang H, Zhang JF, Shi T et al (2022) A dynamic rapid-exploring Random Tree algorithm for collision avoidance for multi-ship encounter situations under COLREGs. Trends Maritime Technol Eng 2:161\u2013170","journal-title":"Trends Maritime Technol Eng"},{"key":"8908_CR8","doi-asserted-by":"publisher","first-page":"102735","DOI":"10.1016\/j.apor.2021.102735","volume":"113","author":"M Abebe","year":"2021","unstructured":"Abebe M, Noh Y, Seo C et al (2021) Developing a ship collision risk index estimation model based on dempster-shafer theory. Appl Ocean Res 113:102735\u2013102745","journal-title":"Appl Ocean Res"},{"issue":"2","key":"8908_CR9","doi-asserted-by":"publisher","first-page":"819","DOI":"10.1111\/poms.13581","volume":"31","author":"JRW Merrick","year":"2022","unstructured":"Merrick JRW, Dorsey CA, Wang B et al (2022) Measuring prediction accuracy in a maritime accident warning system. Product Operat Manag 31(2):819\u2013827","journal-title":"Product Operat Manag"},{"key":"8908_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.ress.2022.108934","volume":"230","author":"H Lan","year":"2023","unstructured":"Lan H, Ma X, Qiao W et al (2023) Determining the critical risk factors for predicting the severity of ship collision accidents using a data-driven approach. Reliabil Eng Syst Safety 230:108934","journal-title":"Reliabil Eng Syst Safety"},{"issue":"7","key":"8908_CR11","doi-asserted-by":"publisher","first-page":"901","DOI":"10.3390\/jmse10070901","volume":"10","author":"D Gao","year":"2022","unstructured":"Gao D, Zhou P, Shi W et al (2022) A dynamic obstacle avoidance method for unmanned surface vehicle under the international regulations for preventing collisions at sea. J Marine Sci Eng 10(7):901\u2013922","journal-title":"J Marine Sci Eng"},{"issue":"31","key":"8908_CR12","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1016\/j.ifacol.2022.10.411","volume":"55","author":"S Blindheim","year":"2022","unstructured":"Blindheim S, Johansen TA (2022) Particle swarm optimization for dynamic risk-aware path following for autonomous ships. IFAC-PapersOnLine 55(31):70\u201377","journal-title":"IFAC-PapersOnLine"},{"key":"8908_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.ocecoaman.2023.106482","volume":"235","author":"P Gao","year":"2023","unstructured":"Gao P, Zhou L, Zhao X et al (2023) Research on ship collision avoidance path planning based on modified potential field ant colony algorithm. Ocean Coastal Manag 235:106482","journal-title":"Ocean Coastal Manag"},{"issue":"8","key":"8908_CR14","doi-asserted-by":"publisher","first-page":"4073","DOI":"10.3390\/app12084073","volume":"12","author":"L Qian","year":"2022","unstructured":"Qian L, Zheng Y, Li L et al (2022) A new method of inland water ship trajectory prediction based on long short-term memory network optimized by genetic algorithm. Appl Sci 12(8):4073\u20134093","journal-title":"Appl Sci"},{"key":"8908_CR15","doi-asserted-by":"crossref","unstructured":"Kelleher J D (2019) Deep learning. MIT press","DOI":"10.7551\/mitpress\/11171.001.0001"},{"key":"8908_CR16","unstructured":"Sutton RS, Barto AG (2018) Reinforcement learning: An introduction. MIT press"},{"key":"8908_CR17","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-13-8285-7","volume-title":"Deep reinforcement learning","author":"M Sewak","year":"2019","unstructured":"Sewak M (2019) Deep reinforcement learning. Springer Singapore, Singapore"},{"key":"8908_CR18","first-page":"5261","volume":"3","author":"G Radanovic","year":"2019","unstructured":"Radanovic G, Devidze R, Parkes D et al (2019) Learning to collaborate in markov decision processes. Int Confer Mach Learn PMLR 3:5261\u20135270","journal-title":"Int Confer Mach Learn PMLR"},{"issue":"18","key":"8908_CR19","doi-asserted-by":"publisher","first-page":"4055","DOI":"10.3390\/s19184055","volume":"19","author":"X Zhang","year":"2019","unstructured":"Zhang X, Wang C, Liu Y et al (2019) Decision-making for the autonomous navigation of maritime autonomous surface ships based on scene division and deep reinforcement learning. Sensors 19(18):4055","journal-title":"Sensors"},{"key":"8908_CR20","doi-asserted-by":"publisher","first-page":"11262","DOI":"10.1109\/JSEN.2022.3222575","volume":"23","author":"J Xia","year":"2022","unstructured":"Xia J, Zhu X, Liu Z et al (2022) Research on collision avoidance algorithm of unmanned surface vehicle based on deep reinforcement learning. IEEE Sens J 23:11262\u201311273","journal-title":"IEEE Sens J"},{"issue":"7","key":"8908_CR21","doi-asserted-by":"publisher","first-page":"944","DOI":"10.3390\/jmse10070944","volume":"10","author":"W Wang","year":"2022","unstructured":"Wang W, Huang L, Liu K et al (2022) A COLREGs-compliant collision avoidance decision approach based on deep reinforcement learning. J Marine Sci Eng 10(7):944\u2013966","journal-title":"J Marine Sci Eng"},{"key":"8908_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2022.112378","volume":"64","author":"L Jiang","year":"2022","unstructured":"Jiang L, An L, Zhang X, Wang C, Wang X (2022) A human-like collision avoidance method for autonomous ship with attention-based deep reinforcement learning. Ocean Eng 64:112378","journal-title":"Ocean Eng"},{"key":"8908_CR23","doi-asserted-by":"publisher","first-page":"639","DOI":"10.3390\/jmse10050639","volume":"10","author":"Q Chen","year":"2022","unstructured":"Chen Q, Xiao C, Wen Y, Tao M, Zhan W (2022) Ship intention prediction at intersections based on vision and bayesian framework. J Marine Sci Eng 10:639","journal-title":"J Marine Sci Eng"},{"key":"8908_CR24","doi-asserted-by":"crossref","unstructured":"Zou Y, Zhao L, Qin S, et al. (2020) Ship target detection and identification based on SSDMobilenetV2. 2020 IEEE 5th Information Technology and Mechatronics Engineering Conference (ITOEC). IEEE, pp 1676-1680","DOI":"10.1109\/ITOEC49072.2020.9141734"},{"issue":"7","key":"8908_CR25","doi-asserted-by":"publisher","first-page":"1327","DOI":"10.3390\/rs13071327","volume":"13","author":"L Tian","year":"2021","unstructured":"Tian L, Cao Y, He B et al (2021) Image enhancement driven by object characteristics and dense feature reuse network for ship target detection in remote sensing imagery. Remote Sens 13(7):1327","journal-title":"Remote Sens"},{"key":"8908_CR26","first-page":"1","volume":"60","author":"G Xiong","year":"2021","unstructured":"Xiong G, Wang F, Yu W et al (2021) Spatial singularity-exponent-domain multiresolution imaging-based SAR ship target detection method. IEEE Trans Geosci Remote Sens 60:1\u201312","journal-title":"IEEE Trans Geosci Remote Sens"},{"issue":"8","key":"8908_CR27","doi-asserted-by":"publisher","first-page":"908","DOI":"10.3390\/jmse9080908","volume":"9","author":"J Zhou","year":"2021","unstructured":"Zhou J, Jiang P, Zou A et al (2021) Ship target detection algorithm based on improved YOLOV5. J Marine Sci Eng 9(8):908","journal-title":"J Marine Sci Eng"},{"key":"8908_CR28","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2020.107001","volume":"199","author":"J Woo","year":"2022","unstructured":"Woo J, Kim N (2022) Collision avoidance for an unmanned surface vehicle using deep reinforcement learning. Ocean Eng 199:107001","journal-title":"Ocean Eng"},{"key":"8908_CR29","first-page":"253","volume":"5","author":"H Kurniawati","year":"2022","unstructured":"Kurniawati H (2022) Partially observable markov decision processes and robotics. Ann Rev Cont Robot Autonom Syst 5:253\u2013277","journal-title":"Ann Rev Cont Robot Autonom Syst"},{"key":"8908_CR30","unstructured":"Li L, Zhao W, Wang C, Luan Z (2022) POMDP motion planning algorithm based on multi-modal driving intention. IEEE Transactions on Intelligent Vehicles, pp 1-10"},{"key":"8908_CR31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10846-021-01489-w","volume":"103","author":"S Ahmad","year":"2021","unstructured":"Ahmad S, Sunberg ZN, Humbert JS (2021) End-to-end probabilistic depth perception and 3D obstacle avoidance using POMDP. J Intell Robot Syst 103:1\u201318","journal-title":"J Intell Robot Syst"},{"key":"8908_CR32","doi-asserted-by":"crossref","unstructured":"Li Q, Li H, Wang J, Feng C (2022) Robot navigation in crowds environment base deep reinforcement learning with POMDP. International Conference on Multimedia Technology and Enhanced Learning, Springer, pp 675-660","DOI":"10.1007\/978-3-031-18123-8_53"},{"key":"8908_CR33","doi-asserted-by":"publisher","first-page":"10731","DOI":"10.1016\/j.ast.2021.107314","volume":"121","author":"W Jiang","year":"2022","unstructured":"Jiang W, Lyu Y, Li Y, Guo Y, Zhang W (2022) UAV path planning and collision avoidance in 3D environments based on POMDP and improved grey wolf optimizer. Aerosp Sci Technol 121:10731","journal-title":"Aerosp Sci Technol"},{"issue":"3","key":"8908_CR34","doi-asserted-by":"publisher","first-page":"1905","DOI":"10.1007\/s10462-022-10213-5","volume":"56","author":"S Cong","year":"2023","unstructured":"Cong S, Zhou Y (2023) A review of convolutional neural network architectures and their optimizations. Artif Intell Rev 56(3):1905\u20131969","journal-title":"Artif Intell Rev"},{"key":"8908_CR35","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2022.110794","volume":"48","author":"W Wenming","year":"2022","unstructured":"Wenming W, Jialu D, Yihan T (2022) A dynamic collision avoidance solution scheme of unmanned surface vessels based on proactive velocity obstacle and set-based guidance. Ocean Eng 48:110794","journal-title":"Ocean Eng"},{"key":"8908_CR36","first-page":"2466","volume":"34","author":"C Packer","year":"2021","unstructured":"Packer C, Abbeel P, Gonzalez JE (2021) Hindsight Task relabelling: experience replay for sparse reward meta-RL. Adv Neural Inform Process Syst 34:2466\u20132477","journal-title":"Adv Neural Inform Process Syst"},{"issue":"4","key":"8908_CR37","first-page":"851","volume":"37","author":"S Wang","year":"2020","unstructured":"Wang S, Du C, Zheng Y (2020) Path planning algorithm for flapping wing aircraft based on reinforcement learning. Control Decis 37(4):851\u2013860","journal-title":"Control Decis"},{"key":"8908_CR38","first-page":"113","volume":"3","author":"Y Wang","year":"2020","unstructured":"Wang Y, He H, Tan X (2020) Truly proximal policy optimization. Uncert Artific Intell PMLR 3:113\u2013122","journal-title":"Uncert Artific Intell PMLR"},{"key":"8908_CR39","doi-asserted-by":"publisher","first-page":"113","DOI":"10.32604\/jai.2020.010137","volume":"115","author":"Y Wang","year":"2020","unstructured":"Wang Y, He H, Tan X (2020) Truly proximal policy optimization. Uncerty Artifi Intell 115:113\u2013122","journal-title":"Uncerty Artifi Intell"},{"key":"8908_CR40","first-page":"20913","volume":"33","author":"T Zahavy","year":"2020","unstructured":"Zahavy T, Xu Z, Veeriah V et al (2020) A self-tuning actor-critic algorithm. Adv. Neural Inform Process Syst 33:20913\u201320924","journal-title":"Adv. Neural Inform Process Syst"},{"issue":"7540","key":"8908_CR41","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih V, Kavukcuoglu K, Silver D et al (2015) Human-level control through deep reinforcement learning. Nature 518(7540):529\u2013533","journal-title":"Nature"},{"issue":"4","key":"8908_CR42","doi-asserted-by":"publisher","first-page":"779","DOI":"10.3390\/jmse11040779","volume":"11","author":"J Liu","year":"2023","unstructured":"Liu J, Shi G, Zhu K et al (2023) Research on MASS collision avoidance in complex waters based on deep reinforcement learning. J Mar Sci Eng 11(4):779","journal-title":"J Mar Sci Eng"},{"key":"8908_CR43","first-page":"1","volume":"71","author":"W Xiao","year":"2022","unstructured":"Xiao W, Yuan L, He L et al (2022) Multigoal visual navigation with collision avoidance via deep reinforcement learning. IEEE Trans Instrument Meas 71:1\u20139","journal-title":"IEEE Trans Instrument Meas"},{"issue":"4","key":"8908_CR44","doi-asserted-by":"publisher","first-page":"3486","DOI":"10.1109\/TGRS.2020.3010441","volume":"59","author":"F Ozcelik","year":"2020","unstructured":"Ozcelik F, Alganci U, Sertel E et al (2020) Rethinking CNN-based pansharpening: guided colorization of panchromatic images via GANs. IEEE Trans Geosci Remote Sens 59(4):3486\u20133501","journal-title":"IEEE Trans Geosci Remote Sens"},{"issue":"11","key":"8908_CR45","doi-asserted-by":"publisher","first-page":"150","DOI":"10.4236\/jcc.2021.911010","volume":"9","author":"D Hirahara","year":"2021","unstructured":"Hirahara D, Takaya E, Kadowaki M et al (2021) Effect of the pixel interpolation method for downsampling medical images on deep learning accuracy. J Comput Commun 9(11):150\u2013156","journal-title":"J Comput Commun"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-023-08908-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-023-08908-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-023-08908-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,5]],"date-time":"2025-09-05T17:51:32Z","timestamp":1757094692000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-023-08908-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,17]]},"references-count":45,"journal-issue":{"issue":"21","published-print":{"date-parts":[[2025,7]]}},"alternative-id":["8908"],"URL":"https:\/\/doi.org\/10.1007\/s00521-023-08908-z","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,17]]},"assertion":[{"value":"31 December 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 July 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 August 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}}]}}