Print Email Facebook Twitter Machine Learning for Flapping Wing Flight Control Title Machine Learning for Flapping Wing Flight Control Author Goedhart, Menno van Kampen, E. (TU Delft Control & Simulation) Armanini, S.F. (TU Delft Control & Simulation) de Visser, C.C. (TU Delft Control & Simulation) Chu, Q. P. (TU Delft Control & Simulation) Date 2018-01-08 Abstract Flight control of Flapping Wing Micro Air Vehicles is challenging, because of their complex dynamics and variability due to manufacturing inconsistencies. Machine Learning algorithms can be used to tackle these challenges. A Policy Gradient algorithm is used to tune the gains of a Proportional-Integral controller using Reinforcement Learning. A novel Classification Algorithm for Machine Learning control (CAML) is presented, which uses model identification and a neural network classifier to select from several predefined gain sets. The algorithms show comparable performance when considering variability only, but the Policy Gradient algorithm is more robust to noise, disturbances, nonlinearities and flapping motion. CAML seems to be promising for problems where no single gain set is available to stabilize the entire set of variable systems. To reference this document use: http://resolver.tudelft.nl/uuid:570432dd-8469-4303-bef1-d9551683898f DOI https://doi.org/10.2514/6.2018-2135 Publisher American Institute of Aeronautics and Astronautics Inc. (AIAA) Embargo date 2019-01-31 ISBN 978-1-62410-527-2 Source Proceedings of the 2018 AIAA Information Systems-AIAA Infotech @ Aerospace Event AIAA Information Systems-AIAA Infotech at Aerospace, 2018, 2018-01-08 → 2018-01-12, Kissimmee, United States Part of collection Institutional Repository Document type conference paper Rights © 2018 Menno Goedhart, E. van Kampen, S.F. Armanini, C.C. de Visser, Q. P. Chu Files PDF Machine_Learning_for_Flap ... ontrol.pdf 3.46 MB Close viewer /islandora/object/uuid:570432dd-8469-4303-bef1-d9551683898f/datastream/OBJ/view