| contributor | IPVS, Bildverstehen | ||||||||||||
| creator |
Oubbati, Mohamed
| Levi, Paul
| Schanz, Michael
| date |
2005-02
| description |
In this paper, we demonstrate the ability of a single fixed-weight
RNN to act as a dynamic controller for several (here 3) distinct
wheeled mobile robots, without exact knowledge about their dynamics
parameters. The controller is properly trained to exhibit adaptive
behaviour after its weights have been fixed. This capability is a
natural consequence of prior meta-learning used recently in the area
of RNNs.
| |
| identifier | http://www.informatik.uni-stuttgart.de/cgi-bin/NCSTRL/NCSTRL_view.pl?id=INPROC-2005-20&engl=1 |
| language | eng |
| publisher | Austria: ACTA Press |
| relation | IASTED |
| source | In: Proceedings of the 24th IASTED International Conference on MODELLING, IDENTIFICATION, AND CONTROL: MIC 2005; Innsbruck, Austria, February 16-18, 2005., pp. 277-282 |
| subject | Robotics (CR I.2.9) |
| Mobile Robot | |
| Recurrent Neural Networks | |
| Meta-Learning | |
| Adaptive Control | |
| title | A Fixed-Weight RNN Dynamic Controller for Multiple Mobile Robots |
| type | Text |
| Article in Proceedings |