{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T06:50:14Z","timestamp":1777445414205,"version":"3.51.4"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61906211"],"award-info":[{"award-number":["61906211"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61836003"],"award-info":[{"award-number":["61836003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Natural Science Foundation for Universities of Jiangsu Province","award":["20KJB520008"],"award-info":[{"award-number":["20KJB520008"]}]},{"name":"Natural Science Foundation for Universities of Jiangsu Province","award":["21KJB120009"],"award-info":[{"award-number":["21KJB120009"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Intell Robot Syst"],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1007\/s10846-023-01953-9","type":"journal-article","created":{"date-parts":[[2023,10,18]],"date-time":"2023-10-18T08:02:39Z","timestamp":1697616159000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Hierarchical Goal-Guided Learning for the Evasive Maneuver of Fixed-Wing UAVs based on Deep Reinforcement Learning"],"prefix":"10.1007","volume":"109","author":[{"given":"Yinlong","family":"Yuan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhu Liang","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yun","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengpeng","family":"Jiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Hua","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,10,18]]},"reference":[{"issue":"1","key":"1953_CR1","first-page":"2835","volume":"33","author":"Y Liu","year":"2019","unstructured":"Liu, Y., Luo, Z., Liu, Z., Shi, J., Cheng, G.: Cooperative routing problem for ground vehicle and unmanned aerial vehicle: The application on intelligence, surveillance and reconnaissance missions. IEEE Access 33(1), 2835\u20132850 (2019)","journal-title":"IEEE Access"},{"issue":"4","key":"1953_CR2","doi-asserted-by":"publisher","first-page":"383","DOI":"10.1007\/s10846-006-9089-6","volume":"47","author":"J Reimann","year":"2006","unstructured":"Reimann, J., Vachtsevanos, G.: Uavs in urban operations: target interception and containment. J. Intell. Robot. Syst. 47(4), 383\u2013396 (2006)","journal-title":"J. Intell. Robot. Syst."},{"issue":"1","key":"1953_CR3","doi-asserted-by":"publisher","first-page":"673","DOI":"10.1109\/TAES.2012.6129663","volume":"48","author":"M Suresh","year":"2012","unstructured":"Suresh, M., Ghose, D.: Uav grouping and coordination tactics for ground attack missions. IEEE Trans. Aerospace Electron. Syst. 48(1), 673\u2013692 (2012)","journal-title":"IEEE Trans. Aerospace Electron. Syst."},{"issue":"6","key":"1953_CR4","doi-asserted-by":"publisher","first-page":"287","DOI":"10.2514\/1.53860","volume":"10","author":"M Haque","year":"2013","unstructured":"Haque, M., Egerstedt, M., Rahmani, A.: Multilevel coalition formation strategy for suppression of enemy air defenses missions. J. Aerospace Inf. Syst. 10(6), 287\u2013296 (2013)","journal-title":"J. Aerospace Inf. Syst."},{"key":"1953_CR5","doi-asserted-by":"crossref","unstructured":"Guo, L., Li, X.-R., Huang, H., Jing, S., He, Y.-C., Wang, C.-Z.: Intelligent penetration of uav based on moth suppression algorithm. In: 2018 Chinese automation congress (2018)","DOI":"10.1109\/CAC.2018.8623737"},{"key":"1953_CR6","doi-asserted-by":"publisher","first-page":"122757","DOI":"10.1109\/ACCESS.2020.3007496","volume":"8","author":"Z Zhang","year":"2020","unstructured":"Zhang, Z., Wu, J., Dai, J., He, C.: A novel real-time penetration path planning algorithm for stealth uav in 3d complex dynamic environment. IEEE Access 8, 122757\u2013122771 (2020)","journal-title":"IEEE Access"},{"key":"1953_CR7","unstructured":"Li, F., Yu, L., Zhou, Z., Fu, Z., Zhang, T.: The nonlinear model predictive control avoidance strategy of the fighter maneuver in endgame. Guofang Keji Daxue Xuebao\/J. Natl. Univ. Def. Technol. 36(3), 83\u201390 (2014)"},{"issue":"2","key":"1953_CR8","doi-asserted-by":"publisher","first-page":"574","DOI":"10.2514\/1.49079","volume":"34","author":"F Imado","year":"2015","unstructured":"Imado, F., Kuroda, T.: Engagement tactics for two missiles against an optimally maneuvering aircraft. J. Guid. Control Dyn. 34(2), 574\u2013582 (2015)","journal-title":"J. Guid. Control Dyn."},{"key":"1953_CR9","unstructured":"Jie, C., Fang, Y., Tao, J.: Path planning under obstacle-avoidance constraints based on ant colony optimization algorithm. In: 2017 IEEE 17th International Conference on Communication Technology (ICCT) (2017)"},{"key":"1953_CR10","doi-asserted-by":"crossref","unstructured":"Ge, F., Li, K., Xu, W., Wang, Y.: Path planning of uav for oilfield inspection based on improved grey wolf optimization algorithm. In: 2019 Chinese Control And Decision Conference (CCDC) (2019)","DOI":"10.1109\/CCDC.2019.8833455"},{"key":"1953_CR11","doi-asserted-by":"publisher","first-page":"105981","DOI":"10.1016\/j.ast.2020.105981","volume":"104","author":"X Fu","year":"2020","unstructured":"Fu, X., Pan, J., Wang, H., Gao, X.: A formation maintenance and reconstruction method of uav swarm based on distributed control. Aerospace Sci. Technol. 104, 105981 (2020)","journal-title":"Aerospace Sci. Technol."},{"issue":"1","key":"1953_CR12","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1108\/00022661311294067","volume":"85","author":"S Chen","year":"2013","unstructured":"Chen, S., Liu, H., Chen, J., Shen, L.: Penetration trajectory planning based on radar tracking features for uav. Aircraft Eng. Aerospace Technol. 85(1), 62\u201371 (2013)","journal-title":"Aircraft Eng. Aerospace Technol."},{"issue":"7540","key":"1953_CR13","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., Rusu, A.A., Veness, J., Bellemare, M.G., Graves, A., Riedmiller, M., Fidjeland, A., Ostrovski, G., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","journal-title":"Nature"},{"key":"1953_CR14","unstructured":"Schulman, J., Levine, S., Abbeel, P., Jordan, M., Moritz, P.: Trust region policy optimization. In: International conference on machine learning, pp. 1889\u20131897 (2015). PMLR"},{"key":"1953_CR15","unstructured":"Lillicrap, T.P., Hunt, J.J., Pritzel, A., Heess, N., Erez, T., Tassa, Y., Silver, D., Wierstra, D.: Continuous control with deep reinforcement learning. arXiv:1509.02971 (2015)"},{"key":"1953_CR16","unstructured":"Florensa, C., Held, D., Wulfmeier, M., Abbeel, P.: Reverse curriculum generation for reinforcement learning. In: Proceedings of the 1st Annual conference on robot learning, pp. 482\u2013495 (2017)"},{"key":"1953_CR17","doi-asserted-by":"crossref","unstructured":"Puente-Castro, A., Rivero, D., Pazos, A., Fernandez-Blanco, E.: Uav swarm path planning with reinforcement learning for field prospecting. arXiv:2106.02322 (2021)","DOI":"10.1007\/s10489-022-03254-4"},{"key":"1953_CR18","unstructured":"Zuo, J., Yang, R., Zhang, Y., Zhonglin, L.I., Meng, W.U.: Intelligent decision-making in air combat maneuvering based on heuristic reinforcement learning. Hangkong Xuebao\/Acta Aeronautica et Astronautica Sinica 38(10) (2017)"},{"key":"1953_CR19","doi-asserted-by":"crossref","unstructured":"Bouhamed, O., Ghazzai, H., Besbes, H., Massoud, Y.: Autonomous uav navigation: A ddpg-based deep reinforcement learning approach. In: IEEE International symposium on circuits and systems (2020)","DOI":"10.1109\/ISCAS45731.2020.9181245"},{"key":"1953_CR20","doi-asserted-by":"crossref","unstructured":"Wang, D., Fan, T., Han, T., Pan, J.: A two-stage reinforcement learning approach for multi-uav collision avoidance under imperfect sensing. IEEE Robot. Autom. Lett. 5(2), 3098\u20133105 (2020)","DOI":"10.1109\/LRA.2020.2974648"},{"key":"1953_CR21","unstructured":"Zijian, H.U., Gao, X., Wan, K., Zhai, Y., Wang, Q.: Relevant experience learning: A deep reinforcement learning method for uav autonomous motion planning in complex unknown environments. Chinese Journal of Aeronautics (2021)"},{"key":"1953_CR22","doi-asserted-by":"crossref","unstructured":"Yang, Q., Zhu, Y., Zhang, J., Qiao, S., Liu, J.: Uav air combat autonomous maneuver decision based on ddpg algorithm. In: 2019 IEEE 15th International Conference on Control and Automation (ICCA) (2019)","DOI":"10.1109\/ICCA.2019.8899703"},{"key":"1953_CR23","unstructured":"Popov, I., Heess, N., Lillicrap, T., Hafner, R., Riedmiller, M.: Data-efficient deep reinforcement learning for dexterous manipulation. arXiv:1704.03073 (2017)"},{"key":"1953_CR24","unstructured":"Ng, A.Y., Harada, D., Russell, S.: Policy invariance under reward transformations: Theory and application to reward shaping, pp. 278\u2013287 (1999)"},{"key":"1953_CR25","unstructured":"Andrychowicz, M., Wolski, F., Ray, A., Schneider, J., Fong, R., Welinder, P., Mcgrew, B., Tobin, J., Abbeel, P., Zaremba, W.: Hindsight experience replay. In: Advances in neural information processing systems, pp. 1815\u20131824 (2017)"},{"issue":"3\u20134","key":"1953_CR26","first-page":"279","volume":"8","author":"W Cjch","year":"1992","unstructured":"Cjch, W., Dayan, P.: Q-learning. Machine Learning 8(3\u20134), 279\u2013292 (1992)","journal-title":"Machine Learning"},{"key":"1953_CR27","unstructured":"Sutton, R.S.: Generalization in reinforcement learning: successful examples using sparse coarse coding. In: annual conference on neural information processing systems, pp. 1038\u20131044. Curran associates, (1996)"},{"key":"1953_CR28","unstructured":"De, A.K., Hernandez-Garcia, J.F., Holland, G.Z., Sutton, R.S.: Multi-step reinforcement learning: a unifying algorithm. arXiv:1703.01327v1 (2017)"},{"key":"1953_CR29","unstructured":"Li, Y.: Deep reinforcement learning: an overview. arXiv:1701.07274 (2017)"},{"key":"1953_CR30","unstructured":"Lin, L.-J.: Reinforcement learning for robots using neural networks. Technical report, Carnegie-Mellon Univ Pittsburgh PA School of Computer Science (1993)"},{"key":"1953_CR31","unstructured":"Wang, J.X., Kurthnelson, Z., Tirumala, D., Soyer, H., Leibo, J.Z., Munos, R., Blundell, C., Kumaran, D., Botvinick, M.: Learning to reinforcement learn. arXiv:1611.05763v1 (2017)"},{"key":"1953_CR32","unstructured":"Zhu, Y., Fang, Z., Zheng, Y., Wei, W.: Homotopy based reinforcement learning with maximum entropy for autonomous air combat. arXiv:2112.01328 (2021)"}],"container-title":["Journal of Intelligent & Robotic Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10846-023-01953-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10846-023-01953-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10846-023-01953-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T05:16:25Z","timestamp":1698297385000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10846-023-01953-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10]]},"references-count":32,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2023,10]]}},"alternative-id":["1953"],"URL":"https:\/\/doi.org\/10.1007\/s10846-023-01953-9","relation":{},"ISSN":["0921-0296","1573-0409"],"issn-type":[{"value":"0921-0296","type":"print"},{"value":"1573-0409","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10]]},"assertion":[{"value":"1 August 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 August 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 October 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":"No conflict of interest exists in the submission of this manuscript.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}},{"value":"This article does not contain any studies with human participants or animals performed by any of the authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"All authors have participated in conception and design, or analysis and interpretation of the data; drafting the article or revising it critically for important intellectual content, and approval of the final version.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to Participate"}},{"value":"The authors declare no interest conflict regarding the publication of this paper.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for Publication"}}],"article-number":"43"}}