Tilburg, Gerrit van (2021) Echo State Network based Helicopter Control. Master's Thesis / Essay, Applied Mathematics.
|
Text
mAppM_2021_TilburgGKvan.pdf Download (1MB) | Preview |
|
![[img]](https://fse.studenttheses.ub.rug.nl/style/images/fileicons/text.png) |
Text
toestemming.pdf Restricted to Registered users only Download (126kB) |
Abstract
In an Echo State Network (ESN), a large recurrent neural network is used as a "reservoir" of dynamics and for training, only the connection weights from the reservoir to the output units are calculated. ESNs can be trained easily and efficiently, and have proven to be applicable on multiple tasks, including control problems. This is done by presenting the ESN dynamics of the to be controlled system, from which the ESN can learn how the system behaves and exploit this to generate system inputs for control purposes. Autonomous helicopter flight represents a challenging nonholonomic control problem with complex, noisy, non-linear dynamics. In this work, the application of ESNs for various stabilization and tracking tasks on a model helicopter is explored.
| Item Type: | Thesis (Master's Thesis / Essay) |
|---|---|
| Supervisor name: | Jaeger, H. and Besselink, B. |
| Degree programme: | Applied Mathematics |
| Thesis type: | Master's Thesis / Essay |
| Language: | English |
| Date Deposited: | 02 Feb 2021 12:24 |
| Last Modified: | 02 Feb 2021 12:24 |
| URI: | https://fse.studenttheses.ub.rug.nl/id/eprint/23878 |
Actions (login required)
 |
View Item |