Print Email Facebook Twitter Guidance & Control Networks for Time-Optimal Quadcopter Flight Title Guidance & Control Networks for Time-Optimal Quadcopter Flight Author Origer, Sebastien (TU Delft Aerospace Engineering) Contributor de Wagter, C. (mentor) de Croon, G.C.H.E. (mentor) Izzo, Dario (mentor) Ferede, R. (mentor) Degree granting institution Delft University of Technology Programme Aerospace Engineering Date 2023-04-05 Abstract Reaching fast and autonomous flight requires computationally efficient and robust algorithms. To this end, we train Guidance & Control Networks to approximate optimal control policies ranging from energy-optimal to time-optimal flight. We show that the policies become more difficult to learn the closer we get to the time-optimal ’bang-bang’ control profile. We also assess the importance of knowing the maximum angular rotor velocity of the quadcopter and show that over- or underestimating this limit leads to less robust flight. We propose an algorithm to identify the current maximum angular rotor velocity onboard and a network that adapts its policy based on the identified limit. Finally, we extend previous work on Guidance & Control Networks by learning to take consecutive waypoints into account. We fly a 4×3m track in similar lap times as the differential-flatness-based minimum snap benchmark controller while benefiting from the flexibility that Guidance & Control Networks offer. To reference this document use: http://resolver.tudelft.nl/uuid:efa9ee47-b200-4a52-b61d-d2c8e5b6fb78 Embargo date 2024-04-10 Part of collection Student theses Document type master thesis Rights © 2023 Sebastien Origer Files PDF Thesis_Guidance_and_Contr ... Flight.pdf 14.44 MB Close viewer /islandora/object/uuid:efa9ee47-b200-4a52-b61d-d2c8e5b6fb78/datastream/OBJ/view