{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T00:19:57Z","timestamp":1774570797681,"version":"3.50.1"},"reference-count":69,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2025,2,10]],"date-time":"2025-02-10T00:00:00Z","timestamp":1739145600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,2,10]],"date-time":"2025-02-10T00:00:00Z","timestamp":1739145600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci. China Inf. Sci."],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1007\/s11432-023-4217-8","type":"journal-article","created":{"date-parts":[[2025,2,13]],"date-time":"2025-02-13T08:13:14Z","timestamp":1739434394000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["A dynamic control decision approach for fixed-wing aircraft games via hybrid action reinforcement learning"],"prefix":"10.1007","volume":"68","author":[{"given":"Xing","family":"Zhuang","sequence":"first","affiliation":[]},{"given":"Dongguang","family":"Li","sequence":"additional","affiliation":[]},{"given":"Hanyu","family":"Li","sequence":"additional","affiliation":[]},{"given":"Yue","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Jihong","family":"Zhu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,2,10]]},"reference":[{"key":"4217_CR1","doi-asserted-by":"publisher","first-page":"2144","DOI":"10.3390\/rs11182144","volume":"11","author":"P Fraga-Lamas","year":"2019","unstructured":"Fraga-Lamas P, Ramos L, Mond\u00e9jar-Guerra V, et al. A review on IoT deep learning UAV systems for autonomous obstacle detection and collision avoidance. Remote Sens, 2019, 11: 2144","journal-title":"Remote Sens"},{"key":"4217_CR2","first-page":"52540","volume":"11","author":"M A Tahir","year":"2023","unstructured":"Tahir M A, Mir I, Islam T U. A review of UAV platforms for autonomous applications: comprehensive analysis and future directions. IEEE Access, 2023, 11: 52540\u201352554","journal-title":"IEEE Access"},{"key":"4217_CR3","doi-asserted-by":"publisher","first-page":"15460","DOI":"10.1109\/JIOT.2022.3176903","volume":"9","author":"Z Wei","year":"2022","unstructured":"Wei Z, Zhu M, Zhang N, et al. UAV-assisted data collection for Internet of Things: a survey. IEEE Int Things J, 2022, 9: 15460\u201315483","journal-title":"IEEE Int Things J"},{"key":"4217_CR4","doi-asserted-by":"publisher","first-page":"323","DOI":"10.3390\/aerospace10040323","volume":"10","author":"K Hamajima","year":"2023","unstructured":"Hamajima K, Yasukawa K, Ueba M, et al. Design and evaluation on onboard antenna pointing control system for a wireless relay system using fixed-wing UAV. Aerospace, 2023, 10: 323","journal-title":"Aerospace"},{"key":"4217_CR5","doi-asserted-by":"publisher","first-page":"6837","DOI":"10.1007\/s13369-017-2881-8","volume":"43","author":"L Melkou","year":"2018","unstructured":"Melkou L, Hamerlain M, Rezoug A. Fixed-wing UAV attitude and altitude control via adaptive second-order sliding mode. Arab J Sci Eng, 2018, 43: 6837\u20136848","journal-title":"Arab J Sci Eng"},{"key":"4217_CR6","doi-asserted-by":"publisher","first-page":"5204","DOI":"10.1109\/TAES.2022.3169127","volume":"58","author":"J Choi","year":"2022","unstructured":"Choi J, Seo M, Shin H S, et al. Adversarial swarm defence using multiple fixed-wing unmanned aerial vehicles. IEEE Trans Aerosp Electron Syst, 2022, 58: 5204\u20135219","journal-title":"IEEE Trans Aerosp Electron Syst"},{"key":"4217_CR7","doi-asserted-by":"publisher","first-page":"9483","DOI":"10.1007\/s00500-021-05863-6","volume":"25","author":"A Giagkos","year":"2021","unstructured":"Giagkos A, Tuci E, Wilson M S, et al. UAV flight coordination for communication networks: genetic algorithms versus game theory. Soft Comput, 2021, 25: 9483\u20139503","journal-title":"Soft Comput"},{"key":"4217_CR8","first-page":"243","volume-title":"Proceedings of the 9th Electronics, Robotics and Automotive Mechanics Conference","author":"T Espinoza","year":"2012","unstructured":"Espinoza T, Dzul A, Garc\u00eda L, et al. Nonlinear controllers applied to fixed-wing UAV. In: Proceedings of the 9th Electronics, Robotics and Automotive Mechanics Conference, 2012. 243\u2013248"},{"key":"4217_CR9","first-page":"1081","volume-title":"Proceedings of International Conference on Unmanned Aircraft Systems (ICUAS)","author":"T Espinoza","year":"2014","unstructured":"Espinoza T, Parada R, Dzul A, et al. Linear controllers implementation for a fixed-wing MAV. In: Proceedings of International Conference on Unmanned Aircraft Systems (ICUAS), 2014. 1081\u20131090"},{"key":"4217_CR10","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1007\/s11424-022-1030-y","volume":"35","author":"B Wang","year":"2022","unstructured":"Wang B, Zhang Y, Zhang W. A composite adaptive fault-tolerant attitude control for a quadrotor UAV with multiple uncertainties. J Syst Sci Complex, 2022, 35: 81\u2013104","journal-title":"J Syst Sci Complex"},{"key":"4217_CR11","first-page":"1738","volume":"59","author":"X Zheng","year":"2022","unstructured":"Zheng X, Li H, Ahn C K, et al. NN-based fixed-time attitude tracking control for multiple unmanned aerial vehicles with nonlinear faults. IEEE Trans Aerosp Electron Syst, 2022, 59: 1738\u20131748","journal-title":"IEEE Trans Aerosp Electron Syst"},{"key":"4217_CR12","doi-asserted-by":"publisher","first-page":"169","DOI":"10.3390\/drones7030169","volume":"7","author":"G Gugan","year":"2023","unstructured":"Gugan G, Haque A. Path planning for autonomous drones: challenges and future directions. Drones, 2023, 7: 169","journal-title":"Drones"},{"key":"4217_CR13","doi-asserted-by":"publisher","first-page":"120254","DOI":"10.1016\/j.eswa.2023.120254","volume":"227","author":"L Liu","year":"2023","unstructured":"Liu L, Wang X, Yang X, et al. Path planning techniques for mobile robots: review and prospect. Expert Syst Appl, 2023, 227: 120254","journal-title":"Expert Syst Appl"},{"key":"4217_CR14","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1016\/j.isatra.2022.07.032","volume":"134","author":"Z Zhang","year":"2023","unstructured":"Zhang Z, Jiang J, Wu J, et al. Efficient and optimal penetration path planning for stealth unmanned aerial vehicle using minimal radar cross-section tactics and modified A-Star algorithm. ISA Trans, 2023, 134: 42\u201357","journal-title":"ISA Trans"},{"key":"4217_CR15","doi-asserted-by":"publisher","first-page":"2291","DOI":"10.3390\/app13042291","volume":"13","author":"S Lu","year":"2023","unstructured":"Lu S, Liu D, Li D, et al. Enhanced teaching-learning-based optimization algorithm for the mobile robot path planning problem. Appl Sci, 2023, 13: 2291","journal-title":"Appl Sci"},{"key":"4217_CR16","doi-asserted-by":"publisher","first-page":"735","DOI":"10.1016\/j.asoc.2018.09.011","volume":"73","author":"X Wu","year":"2018","unstructured":"Wu X, Bai W, Xie Y, et al. A hybrid algorithm of particle swarm optimization, metropolis criterion and RTS smoother for path planning of UAVs. Appl Soft Comput, 2018, 73: 735\u2013747","journal-title":"Appl Soft Comput"},{"key":"4217_CR17","doi-asserted-by":"publisher","first-page":"119269","DOI":"10.1109\/ACCESS.2022.3218685","volume":"10","author":"S Lin","year":"2022","unstructured":"Lin S, Li F, Li X, et al. Improved artificial bee colony algorithm based on multi-strategy synthesis for UAV path planning. IEEE Access, 2022, 10: 119269","journal-title":"IEEE Access"},{"key":"4217_CR18","volume-title":"Proceedings of IOP Conference Series: Materials Science and Engineering","author":"F Wang","year":"2019","unstructured":"Wang F, Wang J, Chen X. Evacuation entropy path planning model based on hybrid ant colony-artificial fish swarm algorithms. In: Proceedings of IOP Conference Series: Materials Science and Engineering, 2019"},{"key":"4217_CR19","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1016\/j.asoc.2015.01.067","volume":"30","author":"M A Contreras-Cruz","year":"2015","unstructured":"Contreras-Cruz M A, Ayala-Ramirez V, Hernandez-Belmonte U H. Mobile robot path planning using artificial bee colony and evolutionary programming. Appl Soft Comput, 2015, 30: 319\u2013328","journal-title":"Appl Soft Comput"},{"key":"4217_CR20","doi-asserted-by":"publisher","first-page":"114541","DOI":"10.1016\/j.eswa.2020.114541","volume":"170","author":"J Wang","year":"2021","unstructured":"Wang J, Li B, Meng M Q H. Kinematic constrained bi-directional RRT with efficient branch pruning for robot path planning. Expert Syst Appl, 2021, 170: 114541","journal-title":"Expert Syst Appl"},{"key":"4217_CR21","doi-asserted-by":"publisher","first-page":"105942","DOI":"10.1016\/j.engappai.2023.105942","volume":"121","author":"C Huang","year":"2023","unstructured":"Huang C, Zhou X, Ran X, et al. Adaptive cylinder vector particle swarm optimization with differential evolution for UAV path planning. Eng Appl Artif Intell, 2023, 121: 105942","journal-title":"Eng Appl Artif Intell"},{"key":"4217_CR22","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1016\/j.cja.2020.12.018","volume":"34","author":"Y Zhou","year":"2021","unstructured":"Zhou Y, Su Y, Xie A, et al. A newly bio-inspired path planning algorithm for autonomous obstacle avoidance of UAV. Chin J Aeronautics, 2021, 34: 199\u2013209","journal-title":"Chin J Aeronautics"},{"key":"4217_CR23","doi-asserted-by":"publisher","first-page":"323","DOI":"10.3390\/drones7050323","volume":"7","author":"Q Diao","year":"2023","unstructured":"Diao Q, Zhang J, Liu M, et al. A disaster relief UAV path planning based on APF-IRRT* fusion algorithm. Drones, 2023, 7: 323","journal-title":"Drones"},{"key":"4217_CR24","doi-asserted-by":"publisher","first-page":"132","DOI":"10.1109\/TII.2012.2198665","volume":"9","author":"V Roberge","year":"2012","unstructured":"Roberge V, Tarbouchi M, Labonte G. Comparison of parallel genetic algorithm and particle swarm optimization for real-time UAV path planning. IEEE Trans Ind Inf, 2012, 9: 132\u2013141","journal-title":"IEEE Trans Ind Inf"},{"key":"4217_CR25","doi-asserted-by":"publisher","first-page":"135","DOI":"10.3390\/aerospace9030135","volume":"9","author":"A Sandberg","year":"2022","unstructured":"Sandberg A, Sands T. Autonomous trajectory generation algorithms for spacecraft slew maneuvers. Aerospace, 2022, 9: 135","journal-title":"Aerospace"},{"key":"4217_CR26","doi-asserted-by":"publisher","first-page":"7066","DOI":"10.3390\/s22187066","volume":"22","author":"K Raigoza","year":"2022","unstructured":"Raigoza K, Sands T. Autonomous trajectory generation comparison for de-orbiting with multiple collision avoidance. Sensors, 2022, 22: 7066","journal-title":"Sensors"},{"key":"4217_CR27","doi-asserted-by":"publisher","first-page":"232","DOI":"10.3390\/drones7040232","volume":"7","author":"K Li","year":"2023","unstructured":"Li K, Wang Y, Zhuang X, et al. A penetration method for UAV based on distributed reinforcement learning and demonstrations. Drones, 2023, 7: 232","journal-title":"Drones"},{"key":"4217_CR28","doi-asserted-by":"publisher","first-page":"246","DOI":"10.3390\/drones7040246","volume":"7","author":"Y Wang","year":"2023","unstructured":"Wang Y, Li X, Zhuang X, et al. A sampling-based distributed exploration method for UAV cluster in unknown environments. Drones, 2023, 7: 246","journal-title":"Drones"},{"key":"4217_CR29","first-page":"239","volume-title":"Proceedings of the 3rd International Conference on Unmanned Systems (ICUS)","author":"Y Zhen","year":"2020","unstructured":"Zhen Y, Hao M, Sun W. Deep reinforcement learning attitude control of fixed-wing UAVs. In: Proceedings of the 3rd International Conference on Unmanned Systems (ICUS), 2020. 239\u2013244"},{"key":"4217_CR30","first-page":"4722","volume-title":"Proceedings of Chinese Automation Congress (CAC)","author":"X Huang","year":"2019","unstructured":"Huang X, Luo W, Liu J. Attitude control of fixed-wing UAV based on DDQN. In: Proceedings of Chinese Automation Congress (CAC), 2019. 4722\u20134726"},{"key":"4217_CR31","doi-asserted-by":"publisher","first-page":"3168","DOI":"10.1109\/TNNLS.2023.3263430","volume":"35","author":"E B\u00f8hn","year":"2024","unstructured":"B\u00f8hn E, Coates E M, Reinhardt D, et al. Data-efficient deep reinforcement learning for attitude control of fixed-wing UAVs: field experiments. IEEE Trans Neural Netw Learn Syst, 2024, 35: 3168\u20133180","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"4217_CR32","doi-asserted-by":"publisher","first-page":"477","DOI":"10.1016\/j.isatra.2022.06.006","volume":"132","author":"T Xie","year":"2023","unstructured":"Xie T, Xian B, Gu X. Fixed-time convergence attitude control for a tilt trirotor unmanned aerial vehicle based on reinforcement learning. ISA Trans, 2023, 132: 477\u2013489","journal-title":"ISA Trans"},{"key":"4217_CR33","doi-asserted-by":"publisher","first-page":"1307","DOI":"10.3390\/pr10071307","volume":"10","author":"A F ud Din","year":"2022","unstructured":"ud Din A F, Mir I, Gul F, et al. Deep reinforcement learning for integrated non-linear control of autonomous UAVs. Processes, 2022, 10: 1307","journal-title":"Processes"},{"key":"4217_CR34","doi-asserted-by":"publisher","first-page":"25449","DOI":"10.1109\/JIOT.2022.3196842","volume":"9","author":"L Zhang","year":"2022","unstructured":"Zhang L, Jabbari B, Ansari N. Deep reinforcement learning driven UAV-assisted edge computing. IEEE Int Things J, 2022, 9: 25449\u201325459","journal-title":"IEEE Int Things J"},{"key":"4217_CR35","doi-asserted-by":"publisher","first-page":"1706","DOI":"10.1109\/TMECH.2022.3220653","volume":"28","author":"Y Liu","year":"2022","unstructured":"Liu Y, Wang H, Liu B, et al. Learning-based compound docking control for UAV aerial recovery: methodology and implementation. IEEE ASME Trans Mechatron, 2022, 28: 1706\u20131717","journal-title":"IEEE ASME Trans Mechatron"},{"key":"4217_CR36","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1016\/j.neucom.2022.08.011","volume":"507","author":"Q Wei","year":"2022","unstructured":"Wei Q, Yang Z, Su H, et al. Monte Carlo-based reinforcement learning control for unmanned aerial vehicle systems. Neurocomputing, 2022, 507: 282\u2013291","journal-title":"Neurocomputing"},{"key":"4217_CR37","doi-asserted-by":"publisher","first-page":"640","DOI":"10.3390\/rs12040640","volume":"12","author":"K Wan","year":"2020","unstructured":"Wan K, Gao X, Hu Z, et al. Robust motion control for UAV in dynamic uncertain environments using deep reinforcement learning. Remote Sens, 2020, 12: 640","journal-title":"Remote Sens"},{"key":"4217_CR38","first-page":"53","volume-title":"Proceedings of Information Science and Applications","author":"W Lee","year":"2019","unstructured":"Lee W, Park G, Joe I. UAV path planning based on reinforcement learning for fair resource allocation in UAV-relayed cellular networks. In: Proceedings of Information Science and Applications, 2019. 53\u201363"},{"key":"4217_CR39","doi-asserted-by":"publisher","first-page":"1590","DOI":"10.1109\/LWC.2022.3167568","volume":"11","author":"B Omoniwa","year":"2022","unstructured":"Omoniwa B, Galkin B, Dusparic I. Optimizing energy efficiency in UAV-assisted networks using deep reinforcement learning. IEEE Wireless Commun Lett, 2022, 11: 1590\u20131594","journal-title":"IEEE Wireless Commun Lett"},{"key":"4217_CR40","doi-asserted-by":"publisher","first-page":"3389","DOI":"10.1109\/TVT.2022.3144277","volume":"71","author":"S Xu","year":"2022","unstructured":"Xu S, Zhang X, Li C, et al. Deep reinforcement learning approach for joint trajectory design in multi-UAV IoT networks. IEEE Trans Veh Technol, 2022, 71: 3389\u20133394","journal-title":"IEEE Trans Veh Technol"},{"key":"4217_CR41","doi-asserted-by":"publisher","first-page":"19214","DOI":"10.1109\/JIOT.2022.3165220","volume":"9","author":"Silvirianti","year":"2022","unstructured":"Silvirianti, Shin S Y. Energy-efficient multidimensional trajectory of UAV-aided IoT networks with reinforcement learning. IEEE Int Things J, 2022, 9: 19214\u201319226","journal-title":"IEEE Int Things J"},{"key":"4217_CR42","doi-asserted-by":"publisher","first-page":"1117","DOI":"10.1109\/TVT.2019.2952549","volume":"69","author":"H Huang","year":"2019","unstructured":"Huang H, Yang Y, Wang H, et al. Deep reinforcement learning for UAV navigation through massive MIMO technique. IEEE Trans Veh Technol, 2019, 69: 1117\u20131121","journal-title":"IEEE Trans Veh Technol"},{"key":"4217_CR43","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1049\/ell2.12485","volume":"58","author":"H J Byun","year":"2022","unstructured":"Byun H J, Nam H. Autonomous control of unmanned aerial vehicle for chemical detection using deep reinforcement learning. Electron Lett, 2022, 58: 423\u2013425","journal-title":"Electron Lett"},{"key":"4217_CR44","doi-asserted-by":"publisher","first-page":"14101","DOI":"10.1007\/s10489-022-03254-4","volume":"52","author":"A Puente-Castro","year":"2022","unstructured":"Puente-Castro A, Rivero D, Pazos A, et al. UAV swarm path planning with reinforcement learning for field prospecting. Appl Intell, 2022, 52: 14101\u201314118","journal-title":"Appl Intell"},{"key":"4217_CR45","doi-asserted-by":"publisher","first-page":"1890","DOI":"10.3390\/s20071890","volume":"20","author":"Z Hu","year":"2020","unstructured":"Hu Z, Wan K, Gao X, et al. Deep reinforcement learning approach with multiple experience pools for UAV\u2019s autonomous motion planning in complex unknown environments. Sensors, 2020, 20: 1890","journal-title":"Sensors"},{"key":"4217_CR46","first-page":"1","volume":"72","author":"B Ma","year":"2023","unstructured":"Ma B, Liu Z, Dang Q, et al. Deep reinforcement learning of UAV tracking control under wind disturbances environments. IEEE Trans Instrum Meas, 2023, 72: 1\u201313","journal-title":"IEEE Trans Instrum Meas"},{"key":"4217_CR47","doi-asserted-by":"publisher","first-page":"3789","DOI":"10.3390\/rs12223789","volume":"12","author":"B Li","year":"2020","unstructured":"Li B, Gan Z, Chen D, et al. UAV maneuvering target tracking in uncertain environments based on deep reinforcement learning and meta-learning. Remote Sens, 2020, 12: 3789","journal-title":"Remote Sens"},{"key":"4217_CR48","first-page":"694","volume-title":"Proceedings of International Conference on Unmanned Aircraft Systems (ICUAS)","author":"S Bhagat","year":"2020","unstructured":"Bhagat S, Sujit P B. UAV target tracking in urban environments using deep reinforcement learning. In: Proceedings of International Conference on Unmanned Aircraft Systems (ICUAS), 2020. 694\u2013701"},{"key":"4217_CR49","doi-asserted-by":"publisher","first-page":"58","DOI":"10.3390\/drones3030058","volume":"3","author":"M A Akhloufi","year":"2019","unstructured":"Akhloufi M A, Arola S, Bonnet A. Drones chasing drones: reinforcement learning and deep search area proposal. Drones, 2019, 3: 58","journal-title":"Drones"},{"key":"4217_CR50","first-page":"15","volume-title":"Proceedings of IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR)","author":"Y Ajmera","year":"2020","unstructured":"Ajmera Y, Singh S P. Autonomous UAV-based target search, tracking and following using reinforcement learning and YOLOFlow. In: Proceedings of IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR), 2020. 15\u201320"},{"key":"4217_CR51","doi-asserted-by":"publisher","first-page":"15441","DOI":"10.1109\/JIOT.2021.3073973","volume":"8","author":"J Moon","year":"2021","unstructured":"Moon J, Papaioannou S, Laoudias C, et al. Deep reinforcement learning multi-UAV trajectory control for target tracking. IEEE Int Things J, 2021, 8: 15441\u201315455","journal-title":"IEEE Int Things J"},{"key":"4217_CR52","doi-asserted-by":"publisher","first-page":"4347","DOI":"10.1007\/s11042-018-5739-5","volume":"78","author":"T Wang","year":"2019","unstructured":"Wang T, Qin R, Chen Y, et al. A reinforcement learning approach for UAV target searching and tracking. Multimed Tools Appl, 2019, 78: 4347\u20134364","journal-title":"Multimed Tools Appl"},{"key":"4217_CR53","doi-asserted-by":"publisher","first-page":"8227","DOI":"10.1109\/TVT.2019.2923214","volume":"68","author":"S Yin","year":"2019","unstructured":"Yin S, Zhao S, Zhao Y, et al. Intelligent trajectory design in UAV-aided communications with reinforcement learning. IEEE Trans Veh Technol, 2019, 68: 8227\u20138231","journal-title":"IEEE Trans Veh Technol"},{"key":"4217_CR54","doi-asserted-by":"publisher","first-page":"3365","DOI":"10.1109\/TNNLS.2023.3281403","volume":"35","author":"Z Yu","year":"2024","unstructured":"Yu Z, Li J, Xu Y, et al. Reinforcement learning-based fractional-order adaptive fault-tolerant formation control of networked fixed-wing UAVs with prescribed performance. IEEE Trans Neural Netw Learn Syst, 2024, 35: 3365\u20133379","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"4217_CR55","first-page":"104","volume-title":"Proceedings of International Conference on Computing, Robotics and System Sciences (ICRSS)","author":"Z Jiang","year":"2022","unstructured":"Jiang Z, Song G. A deep reinforcement learning strategy for UAV autonomous landing on a platform. In: Proceedings of International Conference on Computing, Robotics and System Sciences (ICRSS), 2022. 104\u2013109"},{"key":"4217_CR56","doi-asserted-by":"publisher","first-page":"5630","DOI":"10.3390\/s20195630","volume":"20","author":"J Xie","year":"2020","unstructured":"Xie J, Peng X, Wang H, et al. UAV autonomous tracking and landing based on deep reinforcement learning strategy. Sensors, 2020, 20: 5630","journal-title":"Sensors"},{"key":"4217_CR57","doi-asserted-by":"publisher","first-page":"8825","DOI":"10.3390\/su14148825","volume":"14","author":"N A Mosali","year":"2022","unstructured":"Mosali N A, Shamsudin S S, Mostafa S A, et al. An adaptive multi-level quantization-based reinforcement learning model for enhancing UAV landing on moving targets. Sustainability, 2022, 14: 8825","journal-title":"Sustainability"},{"key":"4217_CR58","doi-asserted-by":"publisher","first-page":"351","DOI":"10.1007\/s10846-018-0891-8","volume":"93","author":"A Rodriguez-Ramos","year":"2019","unstructured":"Rodriguez-Ramos A, Sampedro C, Bavle H, et al. A deep reinforcement learning strategy for UAV autonomous landing on a moving platform. J Intell Robot Syst, 2019, 93: 351\u2013366","journal-title":"J Intell Robot Syst"},{"key":"4217_CR59","doi-asserted-by":"publisher","first-page":"6177","DOI":"10.1109\/JIOT.2018.2876513","volume":"6","author":"J Hu","year":"2018","unstructured":"Hu J, Zhang H, Song L. Reinforcement learning for decentralized trajectory design in cellular UAV networks with sense-and-send protocol. IEEE Int Things J, 2018, 6: 6177\u20136189","journal-title":"IEEE Int Things J"},{"key":"4217_CR60","doi-asserted-by":"publisher","first-page":"4015","DOI":"10.1109\/JIOT.2021.3118949","volume":"9","author":"S Ouahouah","year":"2021","unstructured":"Ouahouah S, Bagaa M, Prados-Garzon J, et al. Deep-reinforcement-learning-based collision avoidance in UAV environment. IEEE Int Things J, 2021, 9: 4015\u20134030","journal-title":"IEEE Int Things J"},{"key":"4217_CR61","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1109\/TITS.2019.2954952","volume":"22","author":"A Singla","year":"2019","unstructured":"Singla A, Padakandla S, Bhatnagar S. Memory-based deep reinforcement learning for obstacle avoidance in UAV with limited environment knowledge. IEEE Trans Intell Transp Syst, 2019, 22: 107\u2013118","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"4217_CR62","first-page":"784","volume-title":"Proceedings of the 20th International Conference on Control, Automation and Systems (ICCAS)","author":"S Kim","year":"2020","unstructured":"Kim S, Park J, Yun J K, et al. Motion planning by reinforcement learning for an unmanned aerial vehicle in virtual open space with static obstacles. In: Proceedings of the 20th International Conference on Control, Automation and Systems (ICCAS), 2020. 784\u2013787"},{"key":"4217_CR63","doi-asserted-by":"publisher","first-page":"747","DOI":"10.1007\/978-981-15-0474-7_70","volume-title":"Proceedings of the 11th International Conference on Modelling, Identification and Control (ICMIC2019)","author":"J Liu","year":"2020","unstructured":"Liu J, Wang Z, Zhang Z. The algorithm for UAV obstacle avoidance and route planning based on reinforcement learning. In: Proceedings of the 11th International Conference on Modelling, Identification and Control (ICMIC2019), 2020. 747\u2013754"},{"key":"4217_CR64","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1007\/s10846-022-01601-8","volume":"104","author":"G Xu","year":"2022","unstructured":"Xu G, Jiang W, Wang Z, et al. Autonomous obstacle avoidance and target tracking of UAV based on deep reinforcement learning. J Intell Robot Syst, 2022, 104: 60","journal-title":"J Intell Robot Syst"},{"key":"4217_CR65","doi-asserted-by":"publisher","first-page":"93","DOI":"10.23919\/USNC\/URSI49741.2020.9321625","volume-title":"Proceedings of IEEE USNC-CNC-URSI North American Radio Science Meeting (Joint with AP-S Symposium)","author":"Y Li","year":"2020","unstructured":"Li Y, Zhang S, Ye F, et al. A UAV path planning method based on deep reinforcement learning. In: Proceedings of IEEE USNC-CNC-URSI North American Radio Science Meeting (Joint with AP-S Symposium), 2020. 93\u201394"},{"key":"4217_CR66","first-page":"3397","volume-title":"Proceedings of the 36th Chinese Control Conference (CCC)","author":"Y J Zhao","year":"2017","unstructured":"Zhao Y J, Zheng Z, Zhang X Y, et al. Q learning algorithm based UAV path learning and obstacle avoidence approach. In: Proceedings of the 36th Chinese Control Conference (CCC), 2017. 3397\u20133402"},{"key":"4217_CR67","doi-asserted-by":"publisher","first-page":"57","DOI":"10.3390\/act12020057","volume":"12","author":"G T Tu","year":"2023","unstructured":"Tu G T, Juang J G. UAV path planning and obstacle avoidance based on reinforcement learning in 3D environments. Actuators, 2023, 12: 57","journal-title":"Actuators"},{"key":"4217_CR68","first-page":"1","volume":"2022","author":"J Zhu","year":"2022","unstructured":"Zhu J, Fu X, Qiao Z, et al. UAVs maneuver decision \u2014 making method based on transfer reinforcement learning. Comput Intell Neurosci, 2022, 2022: 1\u201312","journal-title":"Comput Intell Neurosci"},{"key":"4217_CR69","first-page":"1","volume-title":"Proceedings of IEEE Canadian Conference on Electrical and Computer Engineering (CCECE)","author":"F AlMahamid","year":"2021","unstructured":"AlMahamid F, Grolinger K. Reinforcement learning algorithms: an overview and classification. In: Proceedings of IEEE Canadian Conference on Electrical and Computer Engineering (CCECE), 2021. 1\u20137"}],"container-title":["Science China Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-023-4217-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11432-023-4217-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-023-4217-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,13]],"date-time":"2025-02-13T08:47:48Z","timestamp":1739436468000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11432-023-4217-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,10]]},"references-count":69,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,3]]}},"alternative-id":["4217"],"URL":"https:\/\/doi.org\/10.1007\/s11432-023-4217-8","relation":{},"ISSN":["1674-733X","1869-1919"],"issn-type":[{"value":"1674-733X","type":"print"},{"value":"1869-1919","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,10]]},"assertion":[{"value":"1 August 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 March 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 May 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 February 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"132201"}}