Print Email Facebook Twitter Reinforcement Learning for Flight Control of the Flying V Title Reinforcement Learning for Flight Control of the Flying V Author Völker, Willem (TU Delft Aerospace Engineering) Contributor van Kampen, E. (mentor) Li, Y. (graduation committee) Degree granting institution Delft University of Technology Programme Aerospace Engineering Date 2022-07-04 Abstract Recent research on the Flying V - a flying-wing long-range passenger aircraft - shows that its airframe design is 25% more aerodynamically efficient than a conventional tube-and-wing airframe. The Flying V is therefore a promising contribution towards reduction in climate impact of long-haul flights. However, some design aspects of the Flying V still remain to be investigated, one of which is automatic flight control. Due to the unconventional airframe shape of the Flying V, aerodynamic modelling cannot rely on validated aerodynamic-modelling tools and the accuracy of the aerodynamic model is uncertain. Therefore, this contribution investigates how an automatic flight controller that is robust to aerodynamic-model uncertainty can be developed, by utilising Twin-Delayed Deep Deterministic Policy Gradient (TD3) - a recent deep-reinforcement-learning algorithm. The results show that an offline-trained single-loop altitude controller that is fully based on TD3 can track a given altitude-reference signal and is robust to aerodynamic-model uncertainty of more than 25%. Subject Reinforcement LearningFlying VDeep Deterministic Policy GradientsTD3Robust Controlflight controlAutomatic Flight Control Systemoffline learningfixed-wingflying wingaltitude controlautopilot To reference this document use: http://resolver.tudelft.nl/uuid:a6b645d2-8d47-44d3-a4ad-1d5a6024f13f Part of collection Student theses Document type master thesis Rights © 2022 Willem Völker Files PDF Volker_W_Reinforcement_Le ... Thesis.pdf 8.45 MB Close viewer /islandora/object/uuid:a6b645d2-8d47-44d3-a4ad-1d5a6024f13f/datastream/OBJ/view