{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T10:54:58Z","timestamp":1773658498122,"version":"3.50.1"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T00:00:00Z","timestamp":1769644800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T00:00:00Z","timestamp":1769644800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100003472","name":"Harbin Institute of Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003472","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int. J. Mach. Learn. & Cyber."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1007\/s13042-025-02865-w","type":"journal-article","created":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T14:40:06Z","timestamp":1769697606000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Mine SAR online planning based on grey system theory and proximal policy optimization"],"prefix":"10.1007","volume":"17","author":[{"given":"Shanfan","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingshuang","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,29]]},"reference":[{"key":"2865_CR1","unstructured":"Chikwanha A, Motepe S, Stopforth R (2012) Survey and requirements for search and rescue ground and air vehicles for mining applications. In: 2012 19th International Conference on Mechatronics and Machine Vision in Practice (M2VIP), pp. 105\u2013109"},{"key":"2865_CR2","doi-asserted-by":"publisher","unstructured":"Liu S, Li X (2023) A survey on man overboard accident search and rescue technology by unmanned aerial vehicle. pp 1062\u20131067. https:\/\/doi.org\/10.1109\/CCDC58219.2023.10326951","DOI":"10.1109\/CCDC58219.2023.10326951"},{"issue":"2","key":"2865_CR3","doi-asserted-by":"publisher","first-page":"735","DOI":"10.1109\/TASE.2021.3062810","volume":"19","author":"H Huang","year":"2022","unstructured":"Huang H, Savkin AV, Ni W (2022) Online UAV trajectory planning for covert video surveillance of mobile targets. IEEE Trans Autom Sci Eng 19(2):735\u2013746. https:\/\/doi.org\/10.1109\/TASE.2021.3062810","journal-title":"IEEE Trans Autom Sci Eng"},{"issue":"13","key":"2865_CR4","doi-asserted-by":"publisher","first-page":"10.3390\/rs15133","DOI":"10.3390\/rs15133266","volume":"15","author":"M Lyu","year":"2023","unstructured":"Lyu M, Zhao Y, Huang C, Huang H (2023) Unmanned aerial vehicles for search and rescue: a survey. Remote Sensing 15(13):10.3390\/rs15133266","journal-title":"Remote Sensing"},{"key":"2865_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.119243","volume":"215","author":"C Zhang","year":"2022","unstructured":"Zhang C, Zhou W, Qin W, Tang W (2022) A novel UAV path planning approach: Heuristic crossing search and rescue optimization algorithm. Expert Syst Appl 215:119243","journal-title":"Expert Syst Appl"},{"issue":"22","key":"2865_CR6","doi-asserted-by":"publisher","first-page":"10.3390\/electro","DOI":"10.3390\/electronics12224584","volume":"12","author":"H Zhang","year":"2023","unstructured":"Zhang H, Huang Y, Qin H, Geng Z (2023) USV search mission planning methodology for lost target rescue on sea. Electronics 12(22):10.3390\/electronics12224584","journal-title":"Electronics"},{"issue":"116403","key":"2865_CR7","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1016\/j.oceaneng.2023.116403","volume":"291","author":"J Wu","year":"2024","unstructured":"Wu J, Cheng L, Chu S, Song Y (2024) An autonomous coverage path planning algorithm for maritime search and rescue of persons-in-water based on deep reinforcement learning. Ocean Eng 291(116403):10. https:\/\/doi.org\/10.1016\/j.oceaneng.2023.116403","journal-title":"Ocean Eng"},{"key":"2865_CR8","doi-asserted-by":"crossref","unstructured":"Qin H, Zhou N, Han S, Xue Y (2024) An environment information-driven online bi-level path planning algorithm for underwater search and rescue auv. Ocean Eng 296","DOI":"10.1016\/j.oceaneng.2024.116949"},{"issue":"2","key":"2865_CR9","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1109\/JAS.2023.123945","volume":"11","author":"S Feng","year":"2024","unstructured":"Feng S, Zeng L, Liu J, Yang Y, Song W (2024) Multi-UAVS collaborative path planning in the cramped environment. IEEE\/CAA J Automatica Sinica 11(2):529\u2013538. https:\/\/doi.org\/10.1109\/JAS.2023.123945","journal-title":"IEEE\/CAA J Automatica Sinica"},{"key":"2865_CR10","unstructured":"Macdonald RA, Smith SL (2018) Active sensing for motion planning in uncertain environments via mutual information policies. Int J Robot Res 027836491877202"},{"key":"2865_CR11","unstructured":"Yulong L (2013) Analysis on current research status and key technologies of mine search and rescue robots. Mining Process Equip"},{"issue":"3","key":"2865_CR12","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1002\/rob.21501","volume":"31","author":"W Wang","year":"2014","unstructured":"Wang W, Dong W, Su Y, Wu D, Du Z (2014) Development of search-and-rescue robots for underground coal mine applications. J Field Robot 31(3):386\u2013407","journal-title":"J Field Robot"},{"issue":"1","key":"2865_CR13","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1007\/s11633-024-1512-6","volume":"22","author":"Y Chen","year":"2025","unstructured":"Chen Y, Xiao J (2025) Target search and navigation in heterogeneous robot systems with deep reinforcement learning. Mach Intellig Res 22(1):79\u201390","journal-title":"Mach Intellig Res"},{"key":"2865_CR14","unstructured":"Jonnarth A, Zhao J, Felsberg M (2023) End-to-end reinforcement learning for online coverage path planning in unknown environments. ArXiv arXiv:abs\/2306.16978"},{"key":"2865_CR15","unstructured":"Jonnarth A, Zhao J, Felsberg M (2023) Learning coverage paths in unknown environments with deep reinforcement learning"},{"issue":"1","key":"2865_CR16","doi-asserted-by":"publisher","first-page":"663","DOI":"10.1613\/jair.2567","volume":"32","author":"S Ross","year":"2008","unstructured":"Ross S, Pineau J, Paquet S, Chaib-Draa B (2008) Online planning algorithms for POMDPS. J Artif Intellig Res 32(1):663\u2013704","journal-title":"J Artif Intellig Res"},{"issue":"5","key":"2865_CR17","doi-asserted-by":"publisher","first-page":"288","DOI":"10.1016\/S0167-6911(82)80025-X","volume":"1","author":"D Ju-Long","year":"1982","unstructured":"Ju-Long D (1982) Control problems of grey systems. Syst Control Lett 1(5):288\u2013294","journal-title":"Syst Control Lett"},{"key":"2865_CR18","unstructured":"Bo F, Qian C (2025) An evaluation and similarity analysis of provincial green development levels in china using grey relational analysis. Contemp Soc Sci"},{"key":"2865_CR19","unstructured":"Ye J, Dang Y (2011) A novel grey fixed weight cluster model based on interval grey numbers. Theory Appl Grey Syst"},{"key":"2865_CR20","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-8727-2_10","volume-title":"Grey models for decision-making","author":"S Liu","year":"2025","unstructured":"Liu S (2025) Grey models for decision-making. Springer, Singapore"},{"key":"2865_CR21","doi-asserted-by":"crossref","unstructured":"Wang X, Xie N (2024) Discovering the mechanism of grey forecasting models from the perspective of dynamic system modelling. J Grey Syst 36(2)","DOI":"10.21203\/rs.3.rs-3098016\/v1"},{"key":"2865_CR22","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-6615-4_3","volume-title":"Grey buffer operators","author":"B Zeng","year":"2024","unstructured":"Zeng B, Shi Z (2024) Grey buffer operators. Springer, Singapore"},{"issue":"1","key":"2865_CR23","first-page":"93","volume":"25","author":"X Naiming","year":"2005","unstructured":"Naiming X, Sifeng L (2005) Discrete gm(1,1) and mechanism of grey forecasting model. Syst Eng Theory Pract 25(1):93\u201399","journal-title":"Syst Eng Theory Pract"},{"issue":"4","key":"2865_CR24","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.114898","volume":"176","author":"Z Hu","year":"2021","unstructured":"Hu Z, Gao C, Su Q (2021) A novel evolutionary algorithm based on even difference grey model. Expert Syst Appl 176(4):114898","journal-title":"Expert Syst Appl"},{"issue":"30745\u201330762","key":"2865_CR25","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1109\/ACCESS.2020.2973197","volume":"8","author":"C Dai","year":"2020","unstructured":"Dai C, Hu Z, Li Z, Xiong Z, Su Q (2020) An improved grey prediction evolution algorithm based on topological opposition-based learning. IEEE Access 8(30745\u201330762):10. https:\/\/doi.org\/10.1109\/ACCESS.2020.2973197","journal-title":"IEEE Access"},{"key":"2865_CR26","doi-asserted-by":"publisher","unstructured":"Yang Z (2013) The multi-objective decision-making model based on grey correlation degree. pp 26\u201328. https:\/\/doi.org\/10.1109\/GSIS.2013.6714733","DOI":"10.1109\/GSIS.2013.6714733"},{"issue":"8","key":"2865_CR27","first-page":"1159","volume":"25","author":"S Liu","year":"2010","unstructured":"Liu S, Yuan W, Sheng K (2010) Multi-attribute intelligent grey target decision model. Control Decis 25(8):1159\u20131163","journal-title":"Control Decis"},{"key":"2865_CR28","unstructured":"Liu S, Tao L, Xie N, Yang Y (2015) On the new model system and framework of grey system theory"},{"key":"2865_CR29","doi-asserted-by":"publisher","unstructured":"Yang Z (2013) The multi-objective decision-making model based on grey correlation degree. pp 26\u201328. https:\/\/doi.org\/10.1109\/GSIS.2013.6714733","DOI":"10.1109\/GSIS.2013.6714733"},{"key":"2865_CR30","doi-asserted-by":"crossref","unstructured":"Bai X, Xu Y, Liu S (2021) Research on the regional leading industry selection of \u201ckashgar urban agglomerations\u201d based on multi-attribute weighted intelligent grey target decision-making evaluation model Grey systems theory and application 3:11","DOI":"10.1108\/GS-11-2019-0050"},{"issue":"000","key":"2865_CR31","first-page":"16","volume":"251","author":"H Gu","year":"2024","unstructured":"Gu H, Chen Y, Wu L (2024) A new grey adaptive integrated model for forecasting renewable electricity production. Expert Syst Appl 251(000):16","journal-title":"Expert Syst Appl"},{"issue":"PartB","key":"2865_CR32","first-page":"15","volume":"136","author":"L Liu","year":"2024","unstructured":"Liu L, Liu S, Yang Y, Guo X, Sun J (2024) A generalized grey model with symbolic regression algorithm and its application in predicting aircraft remaining useful life. Eng Appl Artif Intell 136(PartB):15","journal-title":"Eng Appl Artif Intell"},{"issue":"103124","key":"2865_CR33","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1016\/j.aei.2025.103124","volume":"65","author":"G Shang","year":"2025","unstructured":"Shang G, Xu L, Li Z, Xiao L, Zhou Z, He H (2025) Prediction of seam tracking errors in the intelligent welding system: A rapid prediction method based on real-time monitoring data. Adv Eng Inform 65(103124):10. https:\/\/doi.org\/10.1016\/j.aei.2025.103124","journal-title":"Adv Eng Inform"},{"key":"2865_CR34","unstructured":"Schulman J, Wolski F, Dhariwal P, Radford A, Klimov O (2017) Proximal policy optimization algorithms"},{"key":"2865_CR35","unstructured":"Engstrom L, Ilyas A, Santurkar S, Tsipras D, Madry A (2020) Implementation matters in deep policy gradients: a case study on PPO and TRPO"},{"key":"2865_CR36","unstructured":"Tucker G (2018) The mirage of action-dependent baselines in reinforcement learning"},{"key":"2865_CR37","unstructured":"Zhang J, Zhang Z, Han S, L S (2020) Proximal policy optimization via enhanced exploration efficiency"},{"key":"2865_CR38","volume-title":"Yingzhang","author":"RY LongfeiYue","year":"2022","unstructured":"LongfeiYue RY (2022) Yingzhang. Deep reinforcement learning for uav intelligent mission planning. Complex, LixinYu"},{"key":"2865_CR39","first-page":"287","volume":"1 Pt.1)","author":"Z Cui","year":"2023","unstructured":"Cui Z, Guan W, Luo W, Zhang X (2023) Intelligent navigation method for multiple marine autonomous surface ships based on improved PPO algorithm. Ocean Eng 1 Pt.1):287","journal-title":"Ocean Eng"},{"issue":"Sep. 15","key":"2865_CR40","first-page":"1","volume":"284","author":"C Wu","year":"2023","unstructured":"Wu C, Yu W, Li GLW (2023) Deep reinforcement learning with dynamic window approach based collision avoidance path planning for maritime autonomous surface ships. Ocean Eng 284(Sep. 15):1\u20131116","journal-title":"Ocean Eng"},{"key":"2865_CR41","doi-asserted-by":"crossref","unstructured":"Guan W, Han H, Cui Z (2024) Autonomous navigation of marine surface vessel in extreme encounter situation. J Marine Sci Technol 29(1)","DOI":"10.1007\/s00773-023-00979-w"},{"key":"2865_CR42","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2021.107605","volume":"4","author":"S Wen","year":"2021","unstructured":"Wen S, Wen Z, Zhang D, Zhang H, Wang T (2021) A multi-robot path-planning algorithm for autonomous navigation using meta-reinforcement learning based on transfer learning. Appl Soft Comput 4:107605","journal-title":"Appl Soft Comput"},{"issue":"000","key":"2865_CR43","first-page":"15","volume":"2023","author":"X Huang","year":"2023","unstructured":"Huang X, Wang W, Ji Z, Cheng B (2023) Representation enhancement-based proximal policy optimization for UAV path planning and obstacle avoidance. Int J Aerospace Eng 2023(000):15","journal-title":"Int J Aerospace Eng"},{"key":"2865_CR44","doi-asserted-by":"crossref","unstructured":"Zhang Y, Qiu L, Xu Y, Wang X, Wang S, Paul A, Wu Z (2023) Multi-path routing algorithm based on deep reinforcement learning for SDN. Appl Sci 13(22):2076-3417","DOI":"10.3390\/app132212520"},{"issue":"2","key":"2865_CR45","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1109\/MWC.001.2200315","volume":"30","author":"Z Lv","year":"2023","unstructured":"Lv Z, Cheng C, Lv H (2023) Multi-robot distributed communication in heterogeneous robotic systems on 5G networking. IEEE Wirel Commun 30(2):98\u2013104. https:\/\/doi.org\/10.1109\/MWC.001.2200315","journal-title":"IEEE Wirel Commun"},{"issue":"10","key":"2865_CR46","doi-asserted-by":"publisher","first-page":"13575","DOI":"10.1109\/TVT.2023.3277712","volume":"72","author":"K Liu","year":"2023","unstructured":"Liu K, Quan W, Cheng N, Wu W, Xu Z, Guo L, Gao D, Zhang H (2023) Reliable PPO-based concurrent multipath transfer for time-sensitive applications. IEEE Trans Veh Technol 72(10):13575\u201313590. https:\/\/doi.org\/10.1109\/TVT.2023.3277712","journal-title":"IEEE Trans Veh Technol"},{"issue":"3","key":"2865_CR47","doi-asserted-by":"publisher","first-page":"2378","DOI":"10.1109\/LRA.2019.2903261","volume":"4","author":"G Sartoretti","year":"2019","unstructured":"Sartoretti G, Kerr J, Shi Y, Wagner G, Kumar TKS, Koenig S, Choset H (2019) Primal: pathfinding via reinforcement and imitation multi-agent learning. IEEE Robot Autom Lett 4(3):2378\u20132385","journal-title":"IEEE Robot Autom Lett"},{"issue":"19","key":"2865_CR48","doi-asserted-by":"publisher","first-page":"10.3390\/app1419","DOI":"10.3390\/app14199127","volume":"14","author":"S Zhang","year":"2024","unstructured":"Zhang S, Zeng Q (2024) Online unmanned ground vehicle path planning based on multi-attribute intelligent reinforcement learning for mine search and rescue. Appl Sci 14(19):10.3390\/app14199127","journal-title":"Appl Sci"},{"issue":"5","key":"2865_CR49","doi-asserted-by":"publisher","first-page":"1141","DOI":"10.1109\/TSMCA.2012.2227719","volume":"43","author":"A Konar","year":"2013","unstructured":"Konar A, Goswami Chakraborty I, Singh SJ, Jain LC, Nagar AK (2013) A deterministic improved Q-learning for path planning of a mobile robot. IEEE Trans Syst Man Cybernet Syst 43(5):1141\u20131153. https:\/\/doi.org\/10.1109\/TSMCA.2012.2227719","journal-title":"IEEE Trans Syst Man Cybernet Syst"}],"container-title":["International Journal of Machine Learning and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-025-02865-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13042-025-02865-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-025-02865-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T09:56:10Z","timestamp":1773654970000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13042-025-02865-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,29]]},"references-count":49,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["2865"],"URL":"https:\/\/doi.org\/10.1007\/s13042-025-02865-w","relation":{},"ISSN":["1868-8071","1868-808X"],"issn-type":[{"value":"1868-8071","type":"print"},{"value":"1868-808X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,29]]},"assertion":[{"value":"5 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 November 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 January 2026","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":"Conflict of interest"}}],"article-number":"41"}}