Towards a Neural Hierarchy of Time Scales for Motor Control
Animals show remarkable rich motion skills which are still far from realizable with robots. Inspired by the neural circuits which generate rhythmic motion patterns in the spinal cord of all vertebrates, one main research direction points towards the use of central pattern generators in robots. On of the key advantages of this, is that the dimensionality of the control problem is reduced. In this work we investigate this further by introducing a multi-timescale control hierarchy with at its core a hierarchy of recurrent neural networks. By means of some robot experiments, we demonstrate that this hierarchy can embed any rhythmic motor signal by imitation learning. Furthermore, the proposed hierarchy allows the tracking of several high level motion properties (e.g.: amplitude and offset), which are usually observed at a slower rate than the generated motion. Although these experiments are preliminary, the results are promising and have the potential to open the door for rich motor skills and advanced control.
KeywordsLocomotion Control Hierarchy Adaptive control Feedback control Central Pattern Generator Reservoir computing (RC)
Unable to display preview. Download preview PDF.
- 1.Kiebel, S., Daunizeau, J., Friston, K.: A hierarchy of time-scales and the brain. PLoS Computational Biology 4(11), e1000209 (2008)Google Scholar
- 2.Stein, P.: Neurons, networks, and motor behavior. The MIT Press (1999)Google Scholar
- 8.Jaeger, H.: The “echo state” approach to analysing and training recurrent neural networks. German National Research Center for Information Technology, Tech. Rep. GMD Report 148 (2001)Google Scholar
- 14.Legenstein, R.A., Maass, W.: Edge of chaos and prediction of computational performance for neural microcircuit models. Neural Networks, 323–333 (2007)Google Scholar
- 16.Wyffels, F., Schrauwen, B.: Design of a central pattern generator using reservoir computing for learning human motion. In: Proceedings of the ECSIS Symposium on Advanced Technologies for Enhanced Quality of Life, pp. 118–122 (2009)Google Scholar
- 17.Waegeman, T., Wyffels, F., Schrauwen, B.: A discrete/rhythmic pattern generating RNN. In: Proceedings of the 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, pp. 567–572. Ciaco - i6doc.com, Louvain-la-Neuve (2012)Google Scholar
- 18.Li, J., Jaeger, H.: Minimal energy control of an ESN pattern generator. Jacobs University, Tech. Rep. (2011)Google Scholar
- 20.Waegeman, T., Wyffels, F., Schrauwen, B.: Feedback control by online learning an inverse model. IEEE Transactions on Neural Networks and Learning Systems (submitted)Google Scholar