Flexible internal body models for motor control: On the convergence of constrained dual quaternion mean of multiple computation networks
Schilling M, Paskarbeit J, Schneider A, Cruse H (2012)
In: Proceedings of the International Joint Conference on Neural Networks 2012., doi: 10.1109/IJCNN.2012.6252846. .
Konferenzbeitrag
| Veröffentlicht | Englisch
Download
Es wurden keine Dateien hochgeladen. Nur Publikationsnachweis!
Einrichtung
Abstract / Bemerkung
While internal models are recruited in many tasks
and can subserve in this way perception and cognition, it is important
that they are grounded and embodied in sensorimotor
representation. In this paper we analyze an internal model of
the body and show how it can be used for motor control. We
extend the Mean of Multiple Computation principle to a dual
quaternion representation of transformation and show how this
can be directly applied to the control of a simulated robot leg.
The model is encoded as a recurrent neural network acting as
an autoassociator that is able to solve any kinematic problem in
an iterative fashion. We will analyze the convergence properties,
especially when additional constraints (acting on the joint level)
are introduced that restrict the attractor space.
Erscheinungsjahr
2012
Titel des Konferenzbandes
Proceedings of the International Joint Conference on Neural Networks 2012
Band
doi: 10.1109/IJCNN.2012.6252846
Konferenz
International Joint Conference on Neural Networks 2012
Konferenzort
Brisbane AUS
Page URI
https://pub.uni-bielefeld.de/record/2550051
Zitieren
Schilling M, Paskarbeit J, Schneider A, Cruse H. Flexible internal body models for motor control: On the convergence of constrained dual quaternion mean of multiple computation networks. In: Proceedings of the International Joint Conference on Neural Networks 2012. Vol doi: 10.1109/IJCNN.2012.6252846. 2012.
Schilling, M., Paskarbeit, J., Schneider, A., & Cruse, H. (2012). Flexible internal body models for motor control: On the convergence of constrained dual quaternion mean of multiple computation networks. Proceedings of the International Joint Conference on Neural Networks 2012, doi: 10.1109/IJCNN.2012.6252846. doi:10.1109/ijcnn.2012.6252846
Schilling, Malte, Paskarbeit, Jan, Schneider, Axel, and Cruse, Holk. 2012. “Flexible internal body models for motor control: On the convergence of constrained dual quaternion mean of multiple computation networks”. In Proceedings of the International Joint Conference on Neural Networks 2012. Vol. doi: 10.1109/IJCNN.2012.6252846.
Schilling, M., Paskarbeit, J., Schneider, A., and Cruse, H. (2012). “Flexible internal body models for motor control: On the convergence of constrained dual quaternion mean of multiple computation networks” in Proceedings of the International Joint Conference on Neural Networks 2012, vol. doi: 10.1109/IJCNN.2012.6252846,.
Schilling, M., et al., 2012. Flexible internal body models for motor control: On the convergence of constrained dual quaternion mean of multiple computation networks. In Proceedings of the International Joint Conference on Neural Networks 2012. no.doi: 10.1109/IJCNN.2012.6252846
M. Schilling, et al., “Flexible internal body models for motor control: On the convergence of constrained dual quaternion mean of multiple computation networks”, Proceedings of the International Joint Conference on Neural Networks 2012, vol. doi: 10.1109/IJCNN.2012.6252846, 2012.
Schilling, M., Paskarbeit, J., Schneider, A., Cruse, H.: Flexible internal body models for motor control: On the convergence of constrained dual quaternion mean of multiple computation networks. Proceedings of the International Joint Conference on Neural Networks 2012. doi: 10.1109/IJCNN.2012.6252846, (2012).
Schilling, Malte, Paskarbeit, Jan, Schneider, Axel, and Cruse, Holk. “Flexible internal body models for motor control: On the convergence of constrained dual quaternion mean of multiple computation networks”. Proceedings of the International Joint Conference on Neural Networks 2012. 2012.Vol. doi: 10.1109/IJCNN.2012.6252846.
Google Scholar