{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T13:45:53Z","timestamp":1772113553589,"version":"3.50.1"},"reference-count":118,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T00:00:00Z","timestamp":1670198400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T00:00:00Z","timestamp":1670198400000},"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":["J Ambient Intell Human Comput"],"published-print":{"date-parts":[[2023,4]]},"DOI":"10.1007\/s12652-022-04467-8","type":"journal-article","created":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T12:06:07Z","timestamp":1670241967000},"page":"4005-4022","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":31,"title":["Development of reinforced learning based non-linear controller for unmanned aerial vehicle"],"prefix":"10.1007","volume":"14","author":[{"given":"Adnan Fayyaz Ud","family":"Din","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Imran","family":"Mir","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Faiza","family":"Gul","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Suhail","family":"Akhtar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,12,5]]},"reference":[{"issue":"3","key":"4467_CR1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10846-021-01352-y","volume":"101","author":"A Aboelezz","year":"2021","unstructured":"Aboelezz A, Mohamady O, Hassanalian M, Elhadidi B (2021) Nonlinear flight dynamics and control of a fixed-wing micro air vehicle: numerical, system identification and experimental investigations. J Intell Robot Syst 101(3):1\u201318","journal-title":"J Intell Robot Syst"},{"issue":"2","key":"4467_CR2","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1109\/87.238401","volume":"1","author":"RJ Adams","year":"1993","unstructured":"Adams RJ, Banda SS (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"},{"issue":"4","key":"4467_CR3","doi-asserted-by":"crossref","first-page":"737","DOI":"10.2514\/3.21262","volume":"17","author":"RJ Adams","year":"1994","unstructured":"Adams RJ, Buffington JM, Banda SS (1994) Design of nonlinear control laws for high-angle-of-attack flight. J Guid Control Dyn 17(4):737\u2013746","journal-title":"J Guid Control Dyn"},{"key":"4467_CR4","volume-title":"Robust multivariable flight control","author":"RJ Adams","year":"2012","unstructured":"Adams RJ, Buffington JM, Sparks AG, Banda SS (2012) Robust multivariable flight control. Springer Science & Business Media, Berlin"},{"key":"4467_CR5","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"},{"issue":"9","key":"4467_CR6","doi-asserted-by":"crossref","first-page":"999","DOI":"10.3390\/electronics10090999","volume":"10","author":"AT Azar","year":"2021","unstructured":"Azar AT, Koubaa A, Ali Mohamed N, Ibrahim HA, Ibrahim ZF, Kazim M, Ammar A, Benjdira B, Khamis AM, Hameed IA et al (2021) Drone deep reinforcement learning: a review. Electronics 10(9):999","journal-title":"Electronics"},{"key":"4467_CR7","unstructured":"Bansal T, Pachocki J, Sidor S, Sutskever I, Mordatch I (2017) Emergent complexity via multi-agent competition. arXiv preprint arXiv:1710.03748"},{"key":"4467_CR8","doi-asserted-by":"crossref","unstructured":"Bouhamed O, Ghazzai H, Besbes H, Massoud Y (2020) Autonomous UAV navigation: a DDPG-based deep reinforcement learning approach. In: 2020 IEEE International Symposium on circuits and systems (ISCAS), vol 1. IEEE, pp 1\u20135","DOI":"10.1109\/ISCAS45731.2020.9181245"},{"key":"4467_CR9","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, vol 1. IEEE, pp 616\u2013623","DOI":"10.1109\/FTCS.1993.627364"},{"key":"4467_CR10","first-page":"2004","volume":"4838","author":"PG Buning","year":"2004","unstructured":"Buning PG, Gomez RJ, Scallion WI (2004) Cfd approaches for simulation of wing-body stage separation. AIAA Paper 4838:2004","journal-title":"AIAA Paper"},{"issue":"02","key":"4467_CR11","doi-asserted-by":"crossref","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":"4467_CR12","doi-asserted-by":"crossref","unstructured":"Chen J, Xiao Z, Xing H, Dai P, Luo S, Iqbal MA (2020) Stdpg: a spatio-temporal deterministic policy gradient agent for dynamic routing in sdn. In: ICC 2020-2020 IEEE International Conference on communications (ICC), vol 1. IEEE, pp 1\u20136","DOI":"10.1109\/ICC40277.2020.9148789"},{"issue":"24","key":"4467_CR13","doi-asserted-by":"crossref","first-page":"17508","DOI":"10.1109\/JIOT.2021.3081694","volume":"8","author":"J Chen","year":"2021","unstructured":"Chen J, Xing H, Xiao Z, Xu L, Tao T (2021) A drl agent for jointly optimizing computation offloading and resource allocation in mec. IEEE Internet Things J 8(24):17508\u201317524","journal-title":"IEEE Internet Things J"},{"key":"4467_CR14","doi-asserted-by":"crossref","unstructured":"Chowdhary G, Frazzoli E, How J, Liu H (2014) Nonlinear flight control techniques for unmanned aerial vehicles. In: Handbook of unmanned aerial vehicles, Springer, Houten","DOI":"10.1007\/978-90-481-9707-1_49"},{"key":"4467_CR15","unstructured":"CS231n S (2017) Convolutional neural networks for visual recognition. https:\/\/www.cs231ngithubio\/neural-networks-3\/#baby. Accessed 1 Sept 2020"},{"key":"4467_CR16","unstructured":"Dalal G, Dvijotham K, Vecerik M, Hester T, Paduraru C, Tassa Y (2018) Safe exploration in continuous action spaces. arXiv preprint arXiv:1801.08757"},{"issue":"1165","key":"4467_CR18","doi-asserted-by":"crossref","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"},{"key":"4467_CR19","doi-asserted-by":"publisher","unstructured":"Din AFU, Mir I, Gul F, Mir S, Alhady SSN, Nasar A, Rustom M, Alkhazaleh HA, Abualigah L (2022) Robust flight control system design of a fixed wing uav using optimal dynamic programming. Soft Comput. https:\/\/doi.org\/10.1007\/s00500-022-07484-z","DOI":"10.1007\/s00500-022-07484-z"},{"key":"4467_CR20","doi-asserted-by":"crossref","unstructured":"Dong Y, Zou X (2020) Mobile robot path planning based on improved ddpg reinforcement learning algorithm. In: 2020 IEEE 11th International Conference on software engineering and service science (ICSESS), vol 1. IEEE, pp 52\u201356","DOI":"10.1109\/ICSESS49938.2020.9237641"},{"key":"4467_CR21","doi-asserted-by":"crossref","unstructured":"Doyle J, Lenz K, Packard A (1987) Design examples using $$\\mu$$-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"},{"key":"4467_CR22","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, vol 1. p 6502","DOI":"10.2514\/6.2008-6502"},{"issue":"12","key":"4467_CR23","doi-asserted-by":"crossref","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"},{"key":"4467_CR24","unstructured":"Enomoto K, Yamasaki T, Takano H, Baba Y (2013) Guidance and control system design for chase uav. In: AIAA Guidance, Navigation and Control Conference and exhibit, vol 1. p 6842"},{"key":"4467_CR25","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, vol 1. pp 6\u2013pp","DOI":"10.1109\/ACC.2006.1657333"},{"key":"4467_CR26","unstructured":"Finck R, (US) AFFDL, Hoak D (1978) USAF stability and control DATCOM. Eng Doc"},{"issue":"7","key":"4467_CR27","doi-asserted-by":"crossref","first-page":"3437","DOI":"10.1007\/s10064-020-01766-2","volume":"79","author":"D Giordan","year":"2020","unstructured":"Giordan D, Adams MS, 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 Env 79(7):3437\u20133481","journal-title":"Bull Eng Geol Env"},{"issue":"2","key":"4467_CR28","doi-asserted-by":"crossref","first-page":"236","DOI":"10.1144\/qjegh2019-055","volume":"53","author":"M Golian","year":"2020","unstructured":"Golian M, Katibeh H, Singh VP, Ostad-Ali-Askari K, Rostami HT (2020) Prediction of tunnelling impact on flow rates of adjacent extraction water wells. Q J Eng Geol Hydrogeol 53(2):236\u2013251","journal-title":"Q J Eng Geol Hydrogeol"},{"key":"4467_CR29","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, IOP Publishing, vol 697, p 012022","DOI":"10.1088\/1757-899X\/697\/1\/012022"},{"issue":"1","key":"4467_CR30","doi-asserted-by":"crossref","first-page":"1632046","DOI":"10.1080\/23311916.2019.1632046","volume":"6","author":"F Gul","year":"2019","unstructured":"Gul F, Rahiman W, Nazli Alhady SS (2019) A comprehensive study for robot navigation techniques. Cogent Eng 6(1):1632046","journal-title":"Cogent Eng"},{"issue":"1","key":"4467_CR31","first-page":"552","volume":"20","author":"F Gul","year":"2020","unstructured":"Gul F, Alhady SSN, Rahiman W (2020a) A review of controller approach for autonomous guided vehicle system. Indones J Electr Eng Comput Sci 20(1):552\u2013562","journal-title":"Indones J Electr Eng Comput Sci"},{"key":"4467_CR32","doi-asserted-by":"crossref","unstructured":"Gul F, Rahiman W, Alhady SN, Ali A, Mir I, Jalil A (2020b) Meta-heuristic approach for solving multi-objective path planning for autonomous guided robot using pso\u2013gwo optimization algorithm with evolutionary programming. J Ambient Intell Humaniz Comput pp 1\u201318","DOI":"10.1007\/s12652-020-02514-w"},{"key":"4467_CR33","doi-asserted-by":"crossref","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 (2021a) Multi-robot space exploration: an augmented arithmetic approach. IEEE Access 9:107738\u2013107750","journal-title":"IEEE Access"},{"issue":"18","key":"4467_CR34","doi-asserted-by":"crossref","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 (2021b) A consolidated review of path planning and optimization techniques: technical perspectives and future directions. Electronics 10(18):2250","journal-title":"Electronics"},{"key":"4467_CR35","doi-asserted-by":"crossref","first-page":"22774","DOI":"10.1109\/ACCESS.2021.3055852","volume":"9","author":"F Gul","year":"2021","unstructured":"Gul F, Mir I, Rahiman W, Islam TU (2021c) 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":"7","key":"4467_CR36","doi-asserted-by":"crossref","first-page":"7873","DOI":"10.1007\/s12652-020-02514-w","volume":"12","author":"F Gul","year":"2021","unstructured":"Gul F, Rahiman W, Alhady S, Ali A, Mir I, Jalil A (2021d) Meta-heuristic approach for solving multi-objective path planning for autonomous guided robot using pso-gwo optimization algorithm with evolutionary programming. J Ambient Intell Humaniz Comput 12(7):7873\u20137890","journal-title":"J Ambient Intell Humaniz Comput"},{"key":"4467_CR37","doi-asserted-by":"crossref","unstructured":"Gul F, Mir I, Abualigah L, Mir S, Altalhi M (2022a) Cooperative multi-function approach: a new strategy for autonomous ground robotics. Future Gener Comput Syst 134:361\u2013373","DOI":"10.1016\/j.future.2022.04.007"},{"key":"4467_CR38","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1016\/j.jpdc.2022.06.014","volume":"169","author":"F Gul","year":"2022","unstructured":"Gul F, Mir I, Alarabiat D, Alabool HM, Abualigah L, Mir S (2022b) Implementation of bio-inspired hybrid algorithm with mutation operator for robotic path planning. J Parallel Distrib Comput 169:171\u2013184","journal-title":"J Parallel Distrib Comput"},{"key":"4467_CR39","doi-asserted-by":"crossref","unstructured":"Gul F, Mir S, Mir I (2022c) Coordinated multi-robot exploration: hybrid stochastic optimization approach. In: AIAA SCITECH 2022 Forum, p 1414","DOI":"10.2514\/6.2022-1414"},{"key":"4467_CR40","doi-asserted-by":"crossref","unstructured":"Gul F, Mir S, Mir I (2022d) Multi robot space exploration: a modified frequency whale optimization approach. In: AIAA SCITECH 2022 Forum, p 1416","DOI":"10.2514\/6.2022-1416"},{"issue":"1\u20132","key":"4467_CR41","doi-asserted-by":"crossref","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\u20132):137\u2013169","journal-title":"Mach Learn"},{"key":"4467_CR42","unstructured":"Heess N, Hunt JJ, Lillicrap TP, Silver D (2015) Memory-based control with recurrent neural networks. arXiv preprint arXiv:1512.04455"},{"key":"4467_CR43","doi-asserted-by":"crossref","unstructured":"Henderson P, Islam R, Bachman P, Pineau J, Precup D, Meger D (2018) Deep reinforcement learning that matters. In: Proceedings of the AAAI Conference on artificial intelligence, vol 32. pp 1\u201312","DOI":"10.1609\/aaai.v32i1.11694"},{"key":"4467_CR44","volume":"98","author":"Z Hou","year":"2020","unstructured":"Hou Z, Lu P, Tu Z (2020) Nonsingular terminal sliding mode control for a quadrotor uav with a total rotor failure. Aerosp Sci Technol 98:105716","journal-title":"Aerosp Sci Technol"},{"issue":"5","key":"4467_CR45","doi-asserted-by":"crossref","first-page":"777","DOI":"10.1631\/FITEE.1900641","volume":"21","author":"H Hu","year":"2020","unstructured":"Hu H, Ql Wang (2020) Proximal policy optimization with an integral compensator for quadrotor control. Front Inf Technol Electron Eng 21(5):777\u2013795","journal-title":"Front Inf Technol Electron Eng"},{"key":"4467_CR46","doi-asserted-by":"crossref","unstructured":"Hussain A, Hussain I, Mir I, Afzal W, Anjum U, Channa BA (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":"4467_CR47","doi-asserted-by":"crossref","unstructured":"Hussain A, Anjum U, Channa BA, 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":"4467_CR48","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","volume":"4","author":"LP Kaelbling","year":"1996","unstructured":"Kaelbling LP, Littman ML, Moore AW (1996) Reinforcement learning: a survey. J Artif Intell Res 4:237\u2013285","journal-title":"J Artif Intell Res"},{"issue":"4","key":"4467_CR49","doi-asserted-by":"crossref","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":"4467_CR50","unstructured":"Kimathi S (2017) Application of reinforcement learning in heading control of a fixed wing uav using x-plane platform"},{"key":"4467_CR51","unstructured":"Kinga DA (2015) A method for stochastic optimization. In: Anon International Conference on learning representations, San Diego: ICLR"},{"key":"4467_CR52","unstructured":"Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980"},{"issue":"2","key":"4467_CR53","doi-asserted-by":"crossref","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"},{"key":"4467_CR54","unstructured":"Kroezen D (2019) Online reinforcement learning for flight control: an adaptive critic design without prior model knowledge"},{"issue":"1\u20132","key":"4467_CR55","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\u20132):131\u2013142","journal-title":"Period Polytech Transp Eng"},{"key":"4467_CR56","doi-asserted-by":"crossref","DOI":"10.1016\/j.ast.2019.105306","volume":"93","author":"M Labbadi","year":"2019","unstructured":"Labbadi M, Cherkaoui M (2019) Robust adaptive backstepping fast terminal sliding mode controller for uncertain quadrotor uav. Aerosp Sci Technol 93:105306","journal-title":"Aerosp Sci Technol"},{"key":"4467_CR57","unstructured":"Laroche R, Feraud R (2017) Reinforcement learning algorithm selection. arXiv preprint arXiv:1701.08810"},{"key":"4467_CR58","doi-asserted-by":"crossref","unstructured":"Lei C (2021) Deep reinforcement learning. In: Deep learning and practice with MindSpore, Springer, pp 217\u2013243","DOI":"10.1007\/978-981-16-2233-5_10"},{"key":"4467_CR59","unstructured":"Lillicrap TP, Hunt JJ, Pritzel A, Heess N, Erez T, Tassa Y, Silver D, Wierstra D (2015) Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971"},{"key":"4467_CR60","doi-asserted-by":"crossref","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"},{"key":"4467_CR61","doi-asserted-by":"crossref","first-page":"149328","DOI":"10.1109\/ACCESS.2019.2947546","volume":"7","author":"X Luo","year":"2019","unstructured":"Luo X, Zhang Y, He Z, Yang G, Ji Z (2019) A two-step environment-learning-based method for optimal uav deployment. IEEE Access 7:149328\u2013149340","journal-title":"IEEE Access"},{"key":"4467_CR72","doi-asserted-by":"crossref","unstructured":"Mir I, Maqsood A, Akhtar S (2017a) Dynamic modeling & stability analysis of a generic uav in glide phase. In: MATEC Web of Conferences, EDP Sciences, vol 114, p 01007","DOI":"10.1051\/matecconf\/201711401007"},{"key":"4467_CR73","doi-asserted-by":"crossref","unstructured":"Mir I, Maqsood A, Akhtar S (2017b) Optimization of dynamic soaring maneuvers to enhance endurance of a versatile uav. In: IOP Conference series: materials science and engineering, IOP Publishing, vol 211, p 012010","DOI":"10.1088\/1757-899X\/211\/1\/012010"},{"key":"4467_CR74","doi-asserted-by":"crossref","unstructured":"Mir I, Maqsood A, Akhtar S (2017c) Optimization of dynamic soaring maneuvers to enhance endurance of a versatile uav. In: IOP Conference series: materials science and engineering, IOP Publishing, vol 211, p 012010","DOI":"10.1088\/1757-899X\/211\/1\/012010"},{"issue":"4","key":"4467_CR62","doi-asserted-by":"crossref","first-page":"3117","DOI":"10.1007\/s11071-018-4540-3","volume":"94","author":"I Mir","year":"2018","unstructured":"Mir I, Eisa SA, Maqsood A (2018a) 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":"4467_CR63","doi-asserted-by":"crossref","first-page":"1006","DOI":"10.1007\/s42405-018-0086-3","volume":"19","author":"I Mir","year":"2018","unstructured":"Mir I, Maqsood A, Akhtar S (2018b) Biologically inspired dynamic soaring maneuvers for an unmanned air vehicle capable of sweep morphing. Int J Aeronaut Sp Sci 19(4):1006\u20131016","journal-title":"Int J Aeronaut Sp Sci"},{"key":"4467_CR64","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1016\/j.ast.2018.05.024","volume":"79","author":"I Mir","year":"2018","unstructured":"Mir I, Maqsood A, Eisa SA, Taha H, Akhtar S (2018c) Optimal morphing-augmented dynamic soaring maneuvers for unmanned air vehicle capable of span and sweep morphologies. Aerosp Sci Technol 79:17\u201336","journal-title":"Aerosp Sci Technol"},{"issue":"4","key":"4467_CR65","doi-asserted-by":"crossref","first-page":"2347","DOI":"10.1007\/s11071-018-4493-6","volume":"94","author":"I Mir","year":"2018","unstructured":"Mir I, Taha H, Eisa SA, Maqsood A (2018d) A controllability perspective of dynamic soaring. Nonlinear Dyn 94(4):2347\u20132362","journal-title":"Nonlinear Dyn"},{"issue":"1261","key":"4467_CR66","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1017\/aer.2019.1","volume":"123","author":"I Mir","year":"2019","unstructured":"Mir I, Akhtar S, Eisa S, Maqsood A (2019a) Guidance and control of standoff air-to-surface carrier vehicle. Aeronaut J 123(1261):283\u2013309","journal-title":"Aeronaut J"},{"key":"4467_CR75","doi-asserted-by":"crossref","unstructured":"Mir I, Maqsood A, Taha HE, Eisa SA (2019b) Soaring energetics for a nature inspired unmanned aerial vehicle. In: AIAA Scitech 2019 Forum, p 1622","DOI":"10.2514\/6.2019-1622"},{"key":"4467_CR69","doi-asserted-by":"crossref","unstructured":"Mir I, Eisa SA, Taha H, Maqsood A, Akhtar S, Islam TU (2021a) A stability perspective of bio-inspired uavs performing dynamic soaring optimally. Bioinspir Biomim 16(6):066010","DOI":"10.1088\/1748-3190\/ac1918"},{"issue":"6","key":"4467_CR67","volume":"16","author":"I Mir","year":"2021","unstructured":"Mir I, Eisa SA, Taha H, Maqsood A, Akhtar S, Islam TU (2021b) A stability perspective of bioinspired unmanned aerial vehicles performing optimal dynamic soaring. Bioinspir Biomim 16(6):066010","journal-title":"Bioinspir Biomim"},{"key":"4467_CR70","doi-asserted-by":"crossref","unstructured":"Mir I, Eisa S, Maqsood A, Gul F (2022a) Contraction analysis of dynamic soaring. In: AIAA SCITECH 2022 Forum, p 0881","DOI":"10.2514\/6.2022-0881"},{"key":"4467_CR71","doi-asserted-by":"crossref","unstructured":"Mir I, Eisa S, Taha HE, Gul F (2022b) On the stability of dynamic soaring: Floquet-based investigation. In: AIAA SCITECH 2022 Forum, p 0882","DOI":"10.2514\/6.2022-0882"},{"issue":"18","key":"4467_CR68","doi-asserted-by":"crossref","first-page":"2801","DOI":"10.3390\/electronics11182801","volume":"11","author":"I Mir","year":"2022","unstructured":"Mir I, Gul F, Mir S, Khan MA, Saeed N, Abualigah L, Abuhaija B, Gandomi AH (2022c) A survey of trajectory planning techniques for autonomous systems. Electronics 11(18):2801","journal-title":"Electronics"},{"issue":"7540","key":"4467_CR76","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, Graves A, Riedmiller M, Fidjeland AK, Ostrovski G et al (2015) Human-level control through deep reinforcement learning. Nature 518(7540):529\u2013533","journal-title":"Nature"},{"key":"4467_CR93","doi-asserted-by":"crossref","unstructured":"Napolitano MR, An Y, Seanor BA (2000) A fault tolerant flight control system for sensor and actuator failures using neural networks. Aircraft Design 3(2):103\u2013128","DOI":"10.1016\/S1369-8869(00)00009-4"},{"key":"4467_CR77","first-page":"758","volume":"14","author":"KG Nikolakopoulos","year":"2017","unstructured":"Nikolakopoulos KG, Soura K, Koukouvelas IK, Argyropoulos NG (2017) Uav vs classical aerial photogrammetry for archaeological studies. J Archaeol Sci Rep 14:758\u2013773","journal-title":"J Archaeol Sci Rep"},{"key":"4467_CR78","unstructured":"Novati G, Mahadevan L, Koumoutsakos P (2018) Deep-reinforcement-learning for gliding and perching bodies. arXiv preprint arXiv:1807.03671"},{"issue":"1","key":"4467_CR79","doi-asserted-by":"crossref","first-page":"1","DOI":"10.29303\/ulrev.v2i1.28","volume":"2","author":"ES Nurbani","year":"2018","unstructured":"Nurbani ES (2018) Environmental protection in international humanitarian law. Unram Law Rev 2(1):1\u201312","journal-title":"Unram Law Rev"},{"issue":"1","key":"4467_CR80","doi-asserted-by":"crossref","first-page":"134","DOI":"10.1007\/s12205-016-0572-8","volume":"21","author":"K Ostad-Ali-Askari","year":"2017","unstructured":"Ostad-Ali-Askari K, Shayannejad M, Ghorbanizadeh-Kharazi H (2017) Artificial neural network for modeling nitrate pollution of groundwater in marginal area of zayandeh-rood river, isfahan, iran. KSCE J Civ Eng 21(1):134\u2013140","journal-title":"KSCE J Civ Eng"},{"issue":"6","key":"4467_CR81","doi-asserted-by":"crossref","first-page":"2227","DOI":"10.1109\/TNNLS.2018.2806087","volume":"29","author":"J Pan","year":"2018","unstructured":"Pan J, Wang X, Cheng Y, Yu Q (2018) Multisource transfer double dqn based on actor learning. IEEE Trans Neural Netw Learn Syst 29(6):2227\u20132238","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"4467_CR82","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":"02","key":"4467_CR83","doi-asserted-by":"crossref","first-page":"2150009","DOI":"10.1142\/S2737480721500096","volume":"1","author":"K Peng","year":"2021","unstructured":"Peng K (2021) Autonomous mission management based nonlinear flight control design for a class of hybrid unmanned aerial vehicles. Guid Navig Control 1(02):2150009","journal-title":"Guid Navig Control"},{"key":"4467_CR84","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"},{"issue":"7","key":"4467_CR85","doi-asserted-by":"crossref","first-page":"3257","DOI":"10.3390\/app11073257","volume":"11","author":"CH Pi","year":"2021","unstructured":"Pi CH, Ye WY, Cheng S (2021) Robust quadrotor control through reinforcement learning with disturbance compensation. Appl Sci 11(7):3257","journal-title":"Appl Sci"},{"issue":"4","key":"4467_CR86","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1504\/IJGENVI.2018.095063","volume":"17","author":"M Pirnazar","year":"2018","unstructured":"Pirnazar M, Hasheminasab H, Karimi AZ, Ostad-Ali-Askari K, Ghasemi Z, Haeri-Hamedani M, Mohri-Esfahani E, Eslamian S (2018) The evaluation of the usage of the fuzzy algorithms in increasing the accuracy of the extracted land use maps. Int J Glob Environ Issues 17(4):307\u2013321","journal-title":"Int J Glob Environ Issues"},{"issue":"4","key":"4467_CR87","doi-asserted-by":"crossref","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":"4467_CR88","unstructured":"Rastogi D (2017) Deep reinforcement learning for bipedal robots, Student Thesis"},{"issue":"1\u20134","key":"4467_CR89","doi-asserted-by":"crossref","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\u20134):203\u2013220","journal-title":"J Intell Robot Syst"},{"key":"4467_CR90","unstructured":"Roaskam J (2001) Airplane flight dynamics and automatic flight controls. vol"},{"issue":"1\u20132","key":"4467_CR91","doi-asserted-by":"crossref","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\u20132):351\u2013366","journal-title":"J Intell Robot Syst"},{"issue":"1","key":"4467_CR92","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1002\/acs.2955","volume":"33","author":"C Rosales","year":"2019","unstructured":"Rosales C, Soria CM, Rossomando FG (2019) Identification and adaptive pid control of a hexacopter uav based on neural networks. Int J Adapt Control Signal Process 33(1):74\u201391","journal-title":"Int J Adapt Control Signal Process"},{"key":"4467_CR94","unstructured":"Ruder S (2016) An overview of gradient descent optimization algorithms. arXiv preprint arXiv:1609.04747"},{"key":"4467_CR95","unstructured":"Schulman J, Levine S, Abbeel P, Jordan M, Moritz P (2015) Trust region policy optimization. In: International Conference on machine learning, PMLR, pp 1889\u20131897"},{"key":"4467_CR96","unstructured":"Schulman J, Wolski F, Dhariwal P, Radford A, Klimov O (2017) Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347"},{"key":"4467_CR97","unstructured":"Silver D (2015) Lecture 2: Markov decision processes. UCL Retrieved from www.0csuclacuk\/staff\/dsilver\/web\/Teaching_files\/MDPpdf"},{"key":"4467_CR99","unstructured":"Silver D, Lever G, Heess N, Degris T, Wierstra D, Riedmiller M (2014) Deterministic policy gradient algorithms"},{"issue":"7587","key":"4467_CR98","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver D, Huang A, Maddison CJ, 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":"4467_CR100","unstructured":"Sutton RS, Barto AG (1998) Planning and learning. In: Reinforcement learning: an introduction., ser. Adaptive computation and machine learning. A Bradford Book, pp 227\u2013254"},{"key":"4467_CR101","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2019.105644","volume":"83","author":"R Szczepanski","year":"2019","unstructured":"Szczepanski R, Tarczewski T, Grzesiak LM (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":"4467_CR102","doi-asserted-by":"crossref","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":"4467_CR103","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":"3","key":"4467_CR104","doi-asserted-by":"crossref","first-page":"1203","DOI":"10.1109\/TCST.2020.3001117","volume":"29","author":"E Tal","year":"2020","unstructured":"Tal E, Karaman S (2020) Accurate tracking of aggressive quadrotor trajectories using incremental nonlinear dynamic inversion and differential flatness. IEEE Trans Control Syst Technol 29(3):1203\u20131218","journal-title":"IEEE Trans Control Syst Technol"},{"key":"4467_CR105","unstructured":"Tang Y (2016) Tf. learn: tensorflow\u2019s high-level module for distributed machine learning. arXiv preprint arXiv:1612.04251"},{"key":"4467_CR106","doi-asserted-by":"crossref","unstructured":"Thorndike EL (1898) Animal intelligence. Nature 58(1504):390","DOI":"10.1038\/058390b0"},{"key":"4467_CR107","unstructured":"Verma S (2020) A survey on machine learning applied to dynamic physical systems. arXiv preprint arXiv:2009.09719"},{"key":"4467_CR108","unstructured":"Wang S, Jia D, Weng X (2018) Deep reinforcement learning for autonomous driving. arXiv preprint arXiv:1811.11329"},{"key":"4467_CR109","unstructured":"Werbos PJ, Miller W, Sutton R (1990) A menu of designs for reinforcement learning over time. In: Neural networks for control, pp 67\u201395"},{"issue":"4","key":"4467_CR110","doi-asserted-by":"crossref","first-page":"815","DOI":"10.2514\/1.33819","volume":"31","author":"AM Wickenheiser","year":"2008","unstructured":"Wickenheiser AM, Garcia E (2008) Optimization of perching maneuvers through vehicle morphing. J Guid Control Dyn 31(4):815\u2013823","journal-title":"J Guid Control Dyn"},{"issue":"5","key":"4467_CR111","doi-asserted-by":"crossref","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":"4467_CR112","unstructured":"Wu Y, Mansimov E, Grosse RB, Liao S, Ba J (2017) Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation. In: Advances in neural information processing systems, p 30"},{"key":"4467_CR113","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"},{"key":"4467_CR114","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1016\/j.ins.2021.04.053","volume":"571","author":"Z Xiao","year":"2021","unstructured":"Xiao Z, Xu X, Xing H, Luo S, Dai P, Zhan D (2021) Rtfn: a robust temporal feature network for time series classification. Inf Sci 571:65\u201386","journal-title":"Inf Sci"},{"key":"4467_CR115","doi-asserted-by":"crossref","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":"4467_CR116","doi-asserted-by":"crossref","unstructured":"Yang Y, Zhu J, Yang J (2020) Indi-based transitional flight control and stability analysis of a tail-sitter uav. In: 2020 IEEE International Conference on systems, man, and cybernetics (SMC), IEEE, pp 1420\u20131426","DOI":"10.1109\/SMC42975.2020.9283378"},{"key":"4467_CR117","doi-asserted-by":"crossref","DOI":"10.1201\/b10807","volume-title":"Guidance of unmanned aerial vehicles","author":"R Yanushevsky","year":"2011","unstructured":"Yanushevsky R (2011) Guidance of unmanned aerial vehicles. CRC Press, Boca Raton"},{"key":"4467_CR118","unstructured":"Zhou Y (2018) Online reinforcement learning control for aerospace systems"},{"key":"4467_CR119","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\u20136","DOI":"10.1109\/WCSP.2019.8928091"}],"container-title":["Journal of Ambient Intelligence and Humanized Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12652-022-04467-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12652-022-04467-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12652-022-04467-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,28]],"date-time":"2023-03-28T13:07:08Z","timestamp":1680008828000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s12652-022-04467-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,5]]},"references-count":118,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,4]]}},"alternative-id":["4467"],"URL":"https:\/\/doi.org\/10.1007\/s12652-022-04467-8","relation":{},"ISSN":["1868-5137","1868-5145"],"issn-type":[{"value":"1868-5137","type":"print"},{"value":"1868-5145","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,5]]},"assertion":[{"value":"24 December 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 October 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 December 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}