{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T21:40:41Z","timestamp":1769636441451,"version":"3.49.0"},"reference-count":98,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2022,5,20]],"date-time":"2022-05-20T00:00:00Z","timestamp":1653004800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,5,20]],"date-time":"2022-05-20T00:00:00Z","timestamp":1653004800000},"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":["Appl Intell"],"published-print":{"date-parts":[[2023,2]]},"DOI":"10.1007\/s10489-022-03510-7","type":"journal-article","created":{"date-parts":[[2022,5,20]],"date-time":"2022-05-20T08:04:05Z","timestamp":1653033845000},"page":"3048-3068","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":28,"title":["Modified model free dynamic programming :an augmented approach for unmanned aerial vehicle"],"prefix":"10.1007","volume":"53","author":[{"given":"Adnan Fayyaz Ud","family":"Din","sequence":"first","affiliation":[]},{"given":"Suhail","family":"Akhtar","sequence":"additional","affiliation":[]},{"given":"Adnan","family":"Maqsood","sequence":"additional","affiliation":[]},{"given":"Muzaffar","family":"Habib","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0277-8337","authenticated-orcid":false,"given":"Imran","family":"Mir","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,5,20]]},"reference":[{"key":"3510_CR1","doi-asserted-by":"crossref","unstructured":"Yanushevsky R (2011) Guidance of unmanned aerial vehicles. CRC press","DOI":"10.1201\/b10807"},{"key":"3510_CR2","doi-asserted-by":"crossref","unstructured":"Mir I, Eisa S, Taha H E, Gul F (2022) On the stability of dynamic soaring: Floquet-based investigation. In: AIAA SCITECH 2022 Forum, p 0882","DOI":"10.2514\/6.2022-0882"},{"key":"3510_CR3","doi-asserted-by":"crossref","unstructured":"Mir I, Eisa S, Maqsood A, Gul F (2022) Contraction analysis of dynamic soaring. In: AIAA SCITECH 2022 Forum, p 0881","DOI":"10.2514\/6.2022-0881"},{"issue":"4","key":"3510_CR4","doi-asserted-by":"publisher","first-page":"2347","DOI":"10.1007\/s11071-018-4493-6","volume":"94","author":"I Mir","year":"2018","unstructured":"Mir I, Taha H, Eisa S A, Maqsood A (2018) A controllability perspective of dynamic soaring. Nonlinear Dyn 94(4):2347\u20132362","journal-title":"Nonlinear Dyn"},{"key":"3510_CR5","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1016\/j.ast.2018.05.024","volume":"79","author":"I Mir","year":"2018","unstructured":"Mir I, Maqsood A, Eisa S A, Taha H, Akhtar S (2018) Optimal morphing\u2013augmented dynamic soaring maneuvers for unmanned air vehicle capable of span and sweep morphologies. Aerosp Sci Technol 79:17\u201336","journal-title":"Aerosp Sci Technol"},{"key":"3510_CR6","doi-asserted-by":"crossref","unstructured":"Mir I, Maqsood A, Akhtar S (2017) Optimization of dynamic soaring maneuvers to enhance endurance of a versatile uav. In: IOP Conference Series: Materials Science and Engineering, vol 211. IOP Publishing, p 012010","DOI":"10.1088\/1757-899X\/211\/1\/012010"},{"key":"3510_CR7","doi-asserted-by":"crossref","unstructured":"Mir I, Maqsood A, Akhtar S (2017) Optimization of dynamic soaring maneuvers to enhance endurance of a versatile uav. In: IOP Conference Series: Materials Science and Engineering, vol 211. IOP Publishing, p 012010","DOI":"10.1088\/1757-899X\/211\/1\/012010"},{"key":"3510_CR8","doi-asserted-by":"crossref","unstructured":"Paucar C, Morales L, Pinto K, S\u00e1nchez M, Rodr\u00edguez R, Gutierrez M, Palacios L (2018) Use of drones for surveillance and reconnaissance of military areas. In: International Conference of Research Applied to Defense and Security. Springer, pp 119\u2013132","DOI":"10.1007\/978-3-319-78605-6_10"},{"issue":"4","key":"3510_CR9","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1109\/MCOM.2018.1700444","volume":"56","author":"H Kim","year":"2018","unstructured":"Kim H, Mokdad L, Ben-Othman J (2018) Designing uav surveillance frameworks for smart city and extensive ocean with differential perspectives. IEEE Commun Mag 56(4):98\u2013104","journal-title":"IEEE Commun Mag"},{"key":"3510_CR10","doi-asserted-by":"crossref","unstructured":"van Lieshout M, Friedewald M (2018) Drones\u2013dull, dirty or dangerous? the social construction of privacy and security technologies. In: Socially Responsible Innovation in Security. Routledge, pp 37\u201355","DOI":"10.4324\/9781351246903-3"},{"key":"3510_CR11","first-page":"758","volume":"14","author":"KG Nikolakopoulos","year":"2017","unstructured":"Nikolakopoulos K G, Soura K, Koukouvelas I K, Argyropoulos N G (2017) Uav vs classical aerial photogrammetry for archaeological studies. J Archaeol Sci: Rep 14:758\u2013773","journal-title":"J Archaeol Sci: Rep"},{"issue":"5","key":"3510_CR12","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1109\/MSP.2018.3761721","volume":"16","author":"S Winkler","year":"2018","unstructured":"Winkler S, Zeadally S, Evans K (2018) Privacy and civilian drone use: The need for further regulation. IEEE Secur Privacy 16(5):72\u201380","journal-title":"IEEE Secur Privacy"},{"key":"3510_CR13","doi-asserted-by":"crossref","unstructured":"Nurbani E S (2018) Environmental protection in international humanitarian law. Unram Law Rev 2(1)","DOI":"10.29303\/ulrev.v2i1.28"},{"issue":"02","key":"3510_CR14","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1142\/S2301385014300017","volume":"2","author":"G Cai","year":"2014","unstructured":"Cai G, Dias J, Seneviratne L (2014) A survey of small-scale unmanned aerial vehicles: Recent advances and future development trends. Unmanned Syst 2(02):175\u2013199","journal-title":"Unmanned Syst"},{"key":"3510_CR15","doi-asserted-by":"crossref","unstructured":"Mir I, Eisa S A, Taha HE, Maqsood A, Akhtar S, Islam T U (2021) A stability perspective of bio-inspired uavs performing dynamic soaring optimally. Bioinspir. Biomim","DOI":"10.1088\/1748-3190\/ac1918"},{"issue":"1261","key":"3510_CR16","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1017\/aer.2019.1","volume":"123","author":"I Mir","year":"2019","unstructured":"Mir I, Akhtar S, Eisa SA, Maqsood A (2019) Guidance and control of standoff air-to-surface carrier vehicle. Aeronaut J 123(1261):283\u2013309","journal-title":"Aeronaut J"},{"key":"3510_CR17","doi-asserted-by":"crossref","unstructured":"Mir I, Maqsood A, Taha H E, Eisa S A (2019) Soaring energetics for a nature inspired unmanned aerial vehicle. In: AIAA Scitech 2019 Forum, p 1622","DOI":"10.2514\/6.2019-1622"},{"issue":"12","key":"3510_CR18","doi-asserted-by":"publisher","first-page":"363","DOI":"10.3390\/aerospace8120363","volume":"8","author":"N Elmeseiry","year":"2021","unstructured":"Elmeseiry N, Alshaer N, Ismail T (2021) A detailed survey and future directions of unmanned aerial vehicles (uavs) with potential applications. Aerospace 8(12):363","journal-title":"Aerospace"},{"issue":"7","key":"3510_CR19","doi-asserted-by":"publisher","first-page":"3437","DOI":"10.1007\/s10064-020-01766-2","volume":"79","author":"D Giordan","year":"2020","unstructured":"Giordan D, Adams M S, Aicardi I, Alicandro M, Allasia P, Baldo M, De Berardinis P, Dominici D, Godone D, Hobbs P et al (2020) The use of unmanned aerial vehicles (uavs) for engineering geology applications. Bull Eng Geol Environ 79(7):3437\u20133481","journal-title":"Bull Eng Geol Environ"},{"issue":"4","key":"3510_CR20","doi-asserted-by":"publisher","first-page":"3117","DOI":"10.1007\/s11071-018-4540-3","volume":"94","author":"I Mir","year":"2018","unstructured":"Mir I, Eisa S A, Maqsood A (2018) Review of dynamic soaring: technical aspects, nonlinear modeling perspectives and future directions. Nonlinear Dyn 94(4):3117\u20133144","journal-title":"Nonlinear Dyn"},{"issue":"4","key":"3510_CR21","doi-asserted-by":"publisher","first-page":"1006","DOI":"10.1007\/s42405-018-0086-3","volume":"19","author":"I Mir","year":"2018","unstructured":"Mir I, Maqsood A, Akhtar S (2018) Biologically inspired dynamic soaring maneuvers for an unmanned air vehicle capable of sweep morphing. Int J Aeronaut Space Sci 19(4):1006\u20131016","journal-title":"Int J Aeronaut Space Sci"},{"key":"3510_CR22","doi-asserted-by":"crossref","unstructured":"Mir I, Maqsood A, Akhtar S (2017) Dynamic modeling & stability analysis of a generic uav in glide phase. In: MATEC Web of Conferences, vol 114. EDP Sciences, p 01007","DOI":"10.1051\/matecconf\/201711401007"},{"issue":"6","key":"3510_CR23","doi-asserted-by":"publisher","first-page":"066010","DOI":"10.1088\/1748-3190\/ac1918","volume":"16","author":"I Mir","year":"2021","unstructured":"Mir I, Eisa S A, Taha H, Maqsood A, Akhtar S, Islam T U (2021) A stability perspective of bioinspired unmanned aerial vehicles performing optimal dynamic soaring. Bioinspir Biomimetics 16 (6):066010","journal-title":"Bioinspir Biomimetics"},{"key":"3510_CR24","doi-asserted-by":"crossref","unstructured":"Gul F, Mir S, Mir I (2022) Coordinated multi-robot exploration: Hybrid stochastic optimization approach. In: AIAA SCITECH 2022 Forum, p 1414","DOI":"10.2514\/6.2022-1414"},{"key":"3510_CR25","doi-asserted-by":"crossref","unstructured":"Gul F, Mir S, Mir I (2022) Multi robot space exploration: A modified frequency whale optimization approach. In: AIAA SCITECH 2022 Forum, p 1416","DOI":"10.2514\/6.2022-1416"},{"key":"3510_CR26","doi-asserted-by":"publisher","first-page":"107738","DOI":"10.1109\/ACCESS.2021.3101210","volume":"9","author":"F Gul","year":"2021","unstructured":"Gul F, Mir I, Abualigah L, Sumari P (2021) Multi-robot space exploration: An augmented arithmetic approach. IEEE Access 9:107738\u2013107750","journal-title":"IEEE Access"},{"key":"3510_CR27","doi-asserted-by":"crossref","unstructured":"Gul F, Rahiman W, Alhady SS N, Ali A, Mir I, Jalil A (2020) Meta-heuristic approach for solving multi-objective path planning for autonomous guided robot using pso\u2013gwo optimization algorithm with evolutionary programming. J Ambient Intell Human Comput:1\u201318","DOI":"10.1007\/s12652-020-02514-w"},{"key":"3510_CR28","doi-asserted-by":"publisher","first-page":"22774","DOI":"10.1109\/ACCESS.2021.3055852","volume":"9","author":"F Gul","year":"2021","unstructured":"Gul F, Mir I, Rahiman W, Islam T U (2021) Novel implementation of multi-robot space exploration utilizing coordinated multi-robot exploration and frequency modified whale optimization algorithm. IEEE Access 9:22774\u201322787","journal-title":"IEEE Access"},{"issue":"18","key":"3510_CR29","doi-asserted-by":"publisher","first-page":"2250","DOI":"10.3390\/electronics10182250","volume":"10","author":"F Gul","year":"2021","unstructured":"Gul F, Mir I, Abualigah L, Sumari P, Forestiero A (2021) A consolidated review of path planning and optimization techniques: Technical perspectives and future directions. Electronics 10(18):2250","journal-title":"Electronics"},{"issue":"1","key":"3510_CR30","first-page":"552","volume":"20","author":"F Gul","year":"2020","unstructured":"Gul F, Alhady S S N, Rahiman W (2020) A review of controller approach for autonomous guided vehicle system. Ind J Electr Eng Comput Sci 20(1):552\u2013562","journal-title":"Ind J Electr Eng Comput Sci"},{"key":"3510_CR31","doi-asserted-by":"crossref","unstructured":"Gul F, Rahiman W (2019) An integrated approach for path planning for mobile robot using bi-rrt. In: IOP Conference Series: Materials Science and Engineering, vol 697. IOP Publishing, p 012022","DOI":"10.1088\/1757-899X\/697\/1\/012022"},{"issue":"1","key":"3510_CR32","doi-asserted-by":"publisher","first-page":"1632046","DOI":"10.1080\/23311916.2019.1632046","volume":"6","author":"F Gul","year":"2019","unstructured":"Gul F, Rahiman W, Nazli Alhady S S (2019) A comprehensive study for robot navigation techniques. Cogent Eng 6(1):1632046","journal-title":"Cogent Eng"},{"key":"3510_CR33","doi-asserted-by":"publisher","first-page":"105644","DOI":"10.1016\/j.asoc.2019.105644","volume":"83","author":"R Szczepanski","year":"2019","unstructured":"Szczepanski R, Tarczewski T, Grzesiak L M (2019) Adaptive state feedback speed controller for pmsm based on artificial bee colony algorithm. Appl Soft Comput 83:105644","journal-title":"Appl Soft Comput"},{"issue":"20","key":"3510_CR34","doi-asserted-by":"publisher","first-page":"6642","DOI":"10.3390\/en14206642","volume":"14","author":"R Szczepanski","year":"2021","unstructured":"Szczepanski R, Bereit A, Tarczewski T (2021) Efficient local path planning algorithm using artificial potential field supported by augmented reality. Energies 14(20):6642","journal-title":"Energies"},{"key":"3510_CR35","doi-asserted-by":"crossref","unstructured":"Szczepanski R, Tarczewski T (2021) Global path planning for mobile robot based on artificial bee colony and dijkstra\u2019s algorithms. In: 2021 IEEE 19th International Power Electronics and Motion Control Conference (PEMC). IEEE, pp 724\u2013730","DOI":"10.1109\/PEMC48073.2021.9432570"},{"issue":"9","key":"3510_CR36","doi-asserted-by":"publisher","first-page":"999","DOI":"10.3390\/electronics10090999","volume":"10","author":"AT Azar","year":"2021","unstructured":"Azar A T, Koubaa A, Ali Mohamed N, Ibrahim H A, Ibrahim Z F, Kazim M, Ammar A, Benjdira B, Khamis A M, Hameed I A et al (2021) Drone deep reinforcement learning: A review. Electronics 10(9):999","journal-title":"Electronics"},{"key":"3510_CR37","unstructured":"Thorndike EL (1911) Animal intelligence, darien, ct. Hafner"},{"key":"3510_CR38","unstructured":"Sutton R S, Barto A G (1998) Planning and learning. In: Reinforcement Learning: An Introduction., ser. Adaptive Computation and Machine Learning. A Bradford Book, pp 227\u2013254"},{"key":"3510_CR39","unstructured":"Verma S (2020) A survey on machine learning applied to dynamic physical systems. arXiv:2009.09719"},{"issue":"5","key":"3510_CR40","doi-asserted-by":"publisher","first-page":"3215","DOI":"10.1007\/s10462-020-09938-y","volume":"54","author":"W Du","year":"2021","unstructured":"Du W, Ding S (2021) A survey on multi-agent deep reinforcement learning: from the perspective of challenges and applications. Artif Intell Rev 54(5):3215\u20133238","journal-title":"Artif Intell Rev"},{"key":"3510_CR41","unstructured":"Dalal G, Dvijotham K, Vecerik M, Hester T, Paduraru C, Tassa Y (2018) Safe exploration in continuous action spaces. arXiv:1801.08757"},{"issue":"1","key":"3510_CR42","first-page":"1437","volume":"16","author":"J Garc\u0131a","year":"2015","unstructured":"Garc\u0131a J, Fern\u00e1ndez F (2015) A comprehensive survey on safe reinforcement learning. J Mach Learn Res 16(1):1437\u20131480","journal-title":"J Mach Learn Res"},{"issue":"15","key":"3510_CR43","doi-asserted-by":"publisher","first-page":"1469","DOI":"10.1002\/rnc.670","volume":"11","author":"RM Kretchmar","year":"2001","unstructured":"Kretchmar R M, Young P M, Anderson C W, Hittle D C, Anderson M L, Delnero C C (2001) Robust reinforcement learning control with static and dynamic stability. Int J Robust Nonlinear Control: IFAC-Affil J 11(15):1469\u20131500","journal-title":"Int J Robust Nonlinear Control: IFAC-Affil J"},{"issue":"4","key":"3510_CR44","doi-asserted-by":"publisher","first-page":"1069","DOI":"10.1109\/TNNLS.2017.2654539","volume":"29","author":"T Mannucci","year":"2017","unstructured":"Mannucci T, van Kampen E-J, de Visser C, Chu Q (2017) Safe exploration algorithms for reinforcement learning controllers. IEEE Trans Neural Netw Learn Syst 29(4):1069\u20131081","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"7540","key":"3510_CR45","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 K, Ostrovski G et al (2015) Human-level control through deep reinforcement learning. nature 518(7540):529\u2013533","journal-title":"nature"},{"issue":"1-4","key":"3510_CR46","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1007\/s10846-012-9708-3","volume":"70","author":"F Rinaldi","year":"2013","unstructured":"Rinaldi F, Chiesa S, Quagliotti F (2013) Linear quadratic control for quadrotors uavs dynamics and formation flight. J Intell Robot Syst 70(1-4):203\u2013220","journal-title":"J Intell Robot Syst"},{"key":"3510_CR47","doi-asserted-by":"crossref","unstructured":"Araar O, Aouf N (2014) Full linear control of a quadrotor uav, lq vs hinf. In: 2014 UKACC International Conference on Control (CONTROL). IEEE, pp 133\u2013138","DOI":"10.1109\/CONTROL.2014.6915128"},{"key":"3510_CR48","doi-asserted-by":"crossref","unstructured":"Bri\u00e8re D, Traverse P (1993) Airbus a320\/a330\/a340 electrical flight controls-a family of fault-tolerant systems. In: FTCS-23 The Twenty-Third International Symposium on Fault-Tolerant Computing. IEEE, pp 616\u2013623","DOI":"10.1109\/FTCS.1993.627364"},{"issue":"4","key":"3510_CR49","doi-asserted-by":"publisher","first-page":"1192","DOI":"10.1109\/TCST.2017.2709274","volume":"26","author":"P Poksawat","year":"2017","unstructured":"Poksawat P, Wang L, Mohamed A (2017) Gain scheduled attitude control of fixed-wing uav with automatic controller tuning. IEEE Trans Control Syst Technol 26(4):1192\u20131203","journal-title":"IEEE Trans Control Syst Technol"},{"key":"3510_CR50","doi-asserted-by":"crossref","unstructured":"Doyle J, Lenz K, Packard A (1987) Design examples using \u03bc-synthesis: Space shuttle lateral axis fcs during reentry. In: Modelling, Robustness and Sensitivity Reduction in Control Systems. Springer, pp 127\u2013154","DOI":"10.1007\/978-3-642-87516-8_9"},{"issue":"1-2","key":"3510_CR51","first-page":"131","volume":"28","author":"B Kulcsar","year":"2000","unstructured":"Kulcsar B (2000) Lqg\/ltr controller design for an aircraft model. Period Polytech Transp Eng 28(1-2):131\u2013142","journal-title":"Period Polytech Transp Eng"},{"key":"3510_CR52","doi-asserted-by":"crossref","unstructured":"Hussain A, Hussain I, Mir I, Afzal W, Anjum U, Channa B A (2020) Target parameter estimation in reduced dimension stap for airborne phased array radar. In: 2020 IEEE 23rd International Multitopic Conference (INMIC). IEEE, pp 1\u20136","DOI":"10.1109\/INMIC50486.2020.9318130"},{"key":"3510_CR53","doi-asserted-by":"crossref","unstructured":"Hussain A, Anjum U, Channa B A, Afzal W, Hussain I, Mir I (2021) Displaced phase center antenna processing for airborne phased array radar. In: 2021 International Bhurban Conference on Applied Sciences and Technologies (IBCAST). IEEE, pp 988\u2013992","DOI":"10.1109\/IBCAST51254.2021.9393224"},{"key":"3510_CR54","doi-asserted-by":"crossref","unstructured":"Escareno J, Salazar-Cruz S, Lozano R (2006) Embedded control of a four-rotor uav. In: 2006 American Control Conference. IEEE, pp 6\u2013pp","DOI":"10.1109\/ACC.2006.1657333"},{"issue":"1165","key":"3510_CR55","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1017\/S0001924000005571","volume":"115","author":"L Derafa","year":"2011","unstructured":"Derafa L, Ouldali A, Madani T, Benallegue A (2011) Non-linear control algorithm for the four rotors uav attitude tracking problem. Aeronaut J 115(1165):175\u2013185","journal-title":"Aeronaut J"},{"issue":"2","key":"3510_CR56","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1109\/87.238401","volume":"1","author":"RJ Adams","year":"1993","unstructured":"Adams R J, Banda S S (1993) Robust flight control design using dynamic inversion and structured singular value synthesis. IEEE Trans Control Syst Technol 1(2):80\u201392","journal-title":"IEEE Trans Control Syst Technol"},{"key":"3510_CR57","unstructured":"Zhou Y (2018) Online reinforcement learning control for aerospace systems"},{"key":"3510_CR58","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1613\/jair.301","volume":"4","author":"LP Kaelbling","year":"1996","unstructured":"Kaelbling L P, Littman M L, Moore A W (1996) Reinforcement learning: A survey. J Artif Intell Res 4:237\u2013285","journal-title":"J Artif Intell Res"},{"key":"3510_CR59","doi-asserted-by":"crossref","unstructured":"Zhou C, He H, Yang P, Lyu F, Wu W, Cheng N, Shen X (2019) Deep rl-based trajectory planning for aoi minimization in uav-assisted iot. In: 2019 11th International Conference on Wireless Communications and Signal Processing (WCSP). IEEE, pp 1\u2013 6","DOI":"10.1109\/WCSP.2019.8928091"},{"key":"3510_CR60","unstructured":"Bansal T, Pachocki J, Sidor S, Sutskever I, Mordatch I (2017) Emergent complexity via multi-agent competition. arXiv:1710.03748"},{"issue":"10","key":"3510_CR61","doi-asserted-by":"publisher","first-page":"2947","DOI":"10.1007\/s13042-021-01385-7","volume":"12","author":"W Du","year":"2021","unstructured":"Du W, Ding S, Zhang C, Du S (2021) Modified action decoder using bayesian reasoning for multi-agent deep reinforcement learning. Int J Mach Learn Cybern 12(10):2947\u20132961","journal-title":"Int J Mach Learn Cybern"},{"key":"3510_CR62","doi-asserted-by":"publisher","first-page":"105671","DOI":"10.1016\/j.ast.2019.105671","volume":"98","author":"Y Liu","year":"2020","unstructured":"Liu Y, Liu H, Tian Y, Sun C (2020) Reinforcement learning based two-level control framework of uav swarm for cooperative persistent surveillance in an unknown urban area. Aerosp Sci Technol 98:105671","journal-title":"Aerosp Sci Technol"},{"key":"3510_CR63","doi-asserted-by":"publisher","first-page":"232","DOI":"10.1016\/j.ast.2019.05.058","volume":"92","author":"D Xu","year":"2019","unstructured":"Xu D, Hui Z, Liu Y, Chen G (2019) Morphing control of a new bionic morphing uav with deep reinforcement learning. Aerosp Sci Technol 92:232\u2013243","journal-title":"Aerosp Sci Technol"},{"key":"3510_CR64","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1016\/j.neucom.2020.07.042","volume":"415","author":"X Lin","year":"2020","unstructured":"Lin X, Liu J, Yu Y, Sun C (2020) Event-triggered reinforcement learning control for the quadrotor uav with actuator saturation. Neurocomputing 415:135\u2013145","journal-title":"Neurocomputing"},{"issue":"4","key":"3510_CR65","doi-asserted-by":"publisher","first-page":"1076","DOI":"10.2514\/1.G001739","volume":"40","author":"D Kim","year":"2017","unstructured":"Kim D, Oh G, Seo Y, Kim Y (2017) Reinforcement learning-based optimal flat spin recovery for unmanned aerial vehicle. J Guid Control Dyn 40(4):1076\u20131084","journal-title":"J Guid Control Dyn"},{"key":"3510_CR66","doi-asserted-by":"crossref","unstructured":"Dutoi B, Richards N, Gandhi N, Ward D, Leonard J (2008) Hybrid robust control and reinforcement learning for optimal upset recovery. In: AIAA Guidance, Navigation and Control Conference and Exhibit, p 6502","DOI":"10.2514\/6.2008-6502"},{"issue":"4","key":"3510_CR67","doi-asserted-by":"publisher","first-page":"815","DOI":"10.2514\/1.33819","volume":"31","author":"AM Wickenheiser","year":"2008","unstructured":"Wickenheiser A M, Garcia E (2008) Optimization of perching maneuvers through vehicle morphing. J Guid Control Dyn 31(4):815\u2013823","journal-title":"J Guid Control Dyn"},{"key":"3510_CR68","unstructured":"Novati G, Mahadevan L, Koumoutsakos P (2018) Deep-reinforcement-learning for gliding and perching bodies. arXiv:1807.03671"},{"key":"3510_CR69","unstructured":"Kroezen D (2019) Online reinforcement learning for flight control: An adaptive critic design without prior model knowledge"},{"issue":"12","key":"3510_CR70","doi-asserted-by":"publisher","first-page":"4303","DOI":"10.1007\/s10489-019-01501-9","volume":"49","author":"S Ding","year":"2019","unstructured":"Ding S, Zhao X, Xu X, Sun T, Jia W (2019) An effective asynchronous framework for small scale reinforcement learning problems. Appl Intell 49(12):4303\u20134318","journal-title":"Appl Intell"},{"key":"3510_CR71","unstructured":"Rastogi D (2017) Deep reinforcement learning for bipedal robots"},{"key":"3510_CR72","doi-asserted-by":"crossref","unstructured":"Haarnoja T, Ha S, Zhou A, Tan J, Tucker G, Levine S (2018) Learning to walk via deep reinforcement learning. arXiv:1812.11103","DOI":"10.15607\/RSS.2019.XV.011"},{"issue":"7587","key":"3510_CR73","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver D, Huang A, Maddison C J, Guez A, Sifre L, Van Den Driessche G, Schrittwieser J, Antonoglou I, Panneershelvam V, Lanctot M et al (2016) Mastering the game of go with deep neural networks and tree search. Nature 529(7587):484\u2013489","journal-title":"Nature"},{"key":"3510_CR74","doi-asserted-by":"crossref","unstructured":"Xenou K, Chalkiadakis G, Afantenos S (2018) Deep reinforcement learning in strategic board game environments. In: European Conference on Multi-Agent Systems. Springer, pp 233\u2013248","DOI":"10.1007\/978-3-030-14174-5_16"},{"issue":"2","key":"3510_CR75","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3301273","volume":"3","author":"W Koch","year":"2019","unstructured":"Koch W, Mancuso R, West R, Bestavros A (2019) Reinforcement learning for uav attitude control. ACM Trans Cyber-Phys Syst 3(2):1\u201321","journal-title":"ACM Trans Cyber-Phys Syst"},{"issue":"5","key":"3510_CR76","doi-asserted-by":"publisher","first-page":"777","DOI":"10.1631\/FITEE.1900641","volume":"21","author":"H Hu","year":"2020","unstructured":"Hu H, Wang Q- (2020) Proximal policy optimization with an integral compensator for quadrotor control. Front Inf Technol Electr Eng 21(5):777\u2013795","journal-title":"Front Inf Technol Electr Eng"},{"key":"3510_CR77","unstructured":"Kimathi S (2017) Application of reinforcement learning in heading control of a fixed wing uav using x-plane platform"},{"key":"3510_CR78","unstructured":"Pham H X, La H M, Feil-Seifer D, Nguyen L V (2018) Autonomous uav navigation using reinforcement learning. arXiv:1801.05086"},{"issue":"1-2","key":"3510_CR79","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, De La Puente P, Campoy P (2019) A deep reinforcement learning strategy for uav autonomous landing on a moving platform. J Intell Robot Syst 93(1-2):351\u2013366","journal-title":"J Intell Robot Syst"},{"key":"3510_CR80","unstructured":"Roskam J (1985) Airplane design 8vol"},{"key":"3510_CR81","first-page":"2006","volume":"1259","author":"K Petterson","year":"2006","unstructured":"Petterson K (2006) Cfd analysis of the low-speed aerodynamic characteristics of a ucav. AIAA Paper 1259:2006","journal-title":"AIAA Paper"},{"key":"3510_CR82","unstructured":"Finck RD, (US) A F F D L, Hoak DE (1978) Usaf stability and control datcom. Engineering Documents"},{"key":"3510_CR83","first-page":"2004","volume":"4838","author":"PG Buning","year":"2004","unstructured":"Buning P G, Gomez R J, Scallion W I (2004) Cfd approaches for simulation of wing-body stage separation. AIAA Paper 4838:2004","journal-title":"AIAA Paper"},{"key":"3510_CR84","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1016\/j.sbspro.2013.12.027","volume":"106","author":"GK Uyan\u0131k","year":"2013","unstructured":"Uyan\u0131k G K, G\u00fcler N (2013) A study on multiple linear regression analysis. Procedia-Soc Behav Sci 106:234\u2013240","journal-title":"Procedia-Soc Behav Sci"},{"key":"3510_CR85","doi-asserted-by":"crossref","unstructured":"Olive D J (2017) Multiple linear regression. In: Linear regression. Springer, pp 17\u201383","DOI":"10.1007\/978-3-319-55252-1_2"},{"key":"3510_CR86","unstructured":"Roaskam J (2001) Airplane flight dynamics and automatic flight controls. vol Part1"},{"issue":"1-2","key":"3510_CR87","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1007\/s10994-011-5235-x","volume":"84","author":"R Hafner","year":"2011","unstructured":"Hafner R, Riedmiller M (2011) Reinforcement learning in feedback control. Mach Learn 84 (1-2):137\u2013169","journal-title":"Mach Learn"},{"key":"3510_CR88","unstructured":"Laroche R, Feraud R (2017) Reinforcement learning algorithm selection. arXiv:1701.08810"},{"key":"3510_CR89","unstructured":"Kingma D P, Ba J (2014) Adam: A method for stochastic optimization. arXiv:1412.6980"},{"issue":"3731","key":"3510_CR90","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1126\/science.153.3731.34","volume":"153","author":"R Bellman","year":"1966","unstructured":"Bellman R (1966) Dynamic programming. Science 153(3731):34\u201337","journal-title":"Science"},{"key":"3510_CR91","unstructured":"Bellman R E, Dreyfus S E (2015) Applied dynamic programming. Princeton university press"},{"key":"3510_CR92","doi-asserted-by":"crossref","unstructured":"Liu D, Wei Q, Wang D, Yang X, Li H (2017) Adaptive dynamic programming with applications in optimal control. Springer","DOI":"10.1007\/978-3-319-50815-3"},{"issue":"10","key":"3510_CR93","doi-asserted-by":"publisher","first-page":"3341","DOI":"10.1109\/TCYB.2016.2623859","volume":"47","author":"B Luo","year":"2016","unstructured":"Luo B, Liu D, Wu H-N, Wang D, Lewis F L (2016) Policy gradient adaptive dynamic programming for data-based optimal control. IEEE Trans Cybern 47(10):3341\u20133354","journal-title":"IEEE Trans Cybern"},{"issue":"4","key":"3510_CR94","doi-asserted-by":"publisher","first-page":"528","DOI":"10.1002\/net.21864","volume":"72","author":"P Bouman","year":"2018","unstructured":"Bouman P, Agatz N, Schmidt M (2018) Dynamic programming approaches for the traveling salesman problem with drone. Networks 72(4):528\u2013542","journal-title":"Networks"},{"key":"3510_CR95","unstructured":"Silver D, Lever G, Heess N, Degris T, Wierstra D, Riedmiller M (2014) Deterministic policy gradient algorithms"},{"key":"3510_CR96","doi-asserted-by":"crossref","unstructured":"Matignon L, Laurent G J, Le Fort-Piat N (2006) Reward function and initial values: better choices for accelerated goal-directed reinforcement learning. In: International Conference on Artificial Neural Networks. Springer, pp 840\u2013849","DOI":"10.1007\/11840817_87"},{"key":"3510_CR97","unstructured":"Gleave A, Dennis M, Legg S, Russell S, Leike J (2020) Quantifying differences in reward functions. arXiv:2006.13900"},{"issue":"7","key":"3510_CR98","doi-asserted-by":"publisher","first-page":"7873","DOI":"10.1007\/s12652-020-02514-w","volume":"12","author":"F Gul","year":"2021","unstructured":"Gul F, Rahiman W, Alhady SS, Ali A, Mir I, Jalil A (2021) Meta-heuristic approach for solving multi-objective path planning for autonomous guided robot using pso\u2013gwo optimization algorithm with evolutionary programming. J Ambient Intell Human Comput 12(7):7873\u20137890","journal-title":"J Ambient Intell Human Comput"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-022-03510-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-022-03510-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-022-03510-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,11]],"date-time":"2023-01-11T11:52:48Z","timestamp":1673437968000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-022-03510-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,20]]},"references-count":98,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,2]]}},"alternative-id":["3510"],"URL":"https:\/\/doi.org\/10.1007\/s10489-022-03510-7","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,5,20]]},"assertion":[{"value":"12 March 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 May 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}