Intelligent Flapping Wing Control

Intelligent Flapping Wing Control: Reinforcement Learning for the DelFly

Goedhart, Menno (TU Delft Aerospace Engineering; TU Delft Control & Simulation)

van Kampen, E. (mentor)
Armanini, S.F. (mentor)
de Visser, C.C. (mentor)
Sharpanskykh, Alexei (graduation committee)
Chu, Q. P. (graduation committee)

Delft University of Technology

Aerospace Engineering

2017-06-23

Flight control of the DelFly is challenging, because of its 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. Furthermore, 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.

Reinforcement Learning
DelFly
Flapping Wing
Classification
Machine Learning
Policy Gradient

http://resolver.tudelft.nl/uuid:0f103559-d985-47b7-b145-fc814527f307

Student theses

master thesis

© 2017 Menno Goedhart