Abstract
Neural networks are a popular technique for learning the adaptive control of non-linear plants. When applied to the complex control of android robots, however, they suffer from serious limitations such as the moving target problem, i.e. the interference between old and newly learned knowledge. However, in order to achieve lifelong learning, it is important that robots are able to acquire new motor skills without forgetting previously learned ones. To overcome these problems, we propose a new framework for motor learning, which is based on consolidation. The framework contains a new rehearsal algorithm for retaining previously acquired knowledge and a growing neural network. In experiments, the framework was successfully applied to an artifical benchmark problem and a real-world android robot.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Fahlman, S., Lebiere, C.: The cascade-correlation learning architecture. Technical Report CMU-CS-90-100, Carnegie Mellon, University, Pittsburgh (1991)
Kawato, M.: Feedback-error-learning neural network for supervised motor learning. In: Advanced Neural Computers, pp. 365–472 (1990)
Li, Y., Asakura, T.: Occurence of trajectory chaos and it’s stabilizing control due to dead time of a pneumatic manipulator. JSME International Journal Series C 48(4), 640–648 (2005)
Robins, A.: Catastrophic forgetting, rehearsal and pseudorehearsal. Connect. Sci. 7(2), 123–146 (1995)
Schaal, S., Atkeson, C.G.: Constructive incremental learning from only local information. Neural Comput. 10(9), 2047–2084 (1998)
Shadmehr, R., Holcomb, H.: Neural correlates of motor memory consolidation. Science 277, 821–825 (1997)
Silver, D.L., Poirier, R.: Sequential consolidation of learned task knowledge. In: Canadian Conference on AI, pp. 217–232 (2004)
Stanley, K.O., Miikkulainen, R.: Evolving neural networks through augmenting topologies. Evolutionary Computation 10, 99–127 (2002), http://nn.cs.utexas.edu/keyword?stanley:ec02
Tani, J.: An interpretation of the ’self’ from the dynamical systems perspective: A constructivist approach. Journal of Cosciousness Studies 5(5-6) (1998)
Thrun, S.: Lifelong Learning Algorithms, pp. 181–209. Kluwer Academic Publishers, Norwell (1998)
Vijayakumar, S., Schaal, S.: Fast and efficient incremental learning for high-dimensional movement systems. In: Proc. IEEE Int’l Conf. Robotics and Automation, pp. 1894–1899. IEEE Computer Society Press, Piscataway (2000), citeseer.ist.psu.edu/vijayakumar00fast.html
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer Berlin Heidelberg
About this paper
Cite this paper
Ben Amor, H., Ikemoto, S., Minato, T., Jung, B., Ishiguro, H. (2007). A Neural Framework for Robot Motor Learning Based on Memory Consolidation. In: Beliczynski, B., Dzielinski, A., Iwanowski, M., Ribeiro, B. (eds) Adaptive and Natural Computing Algorithms. ICANNGA 2007. Lecture Notes in Computer Science, vol 4432. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-71629-7_72
Download citation
DOI: https://doi.org/10.1007/978-3-540-71629-7_72
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-71590-0
Online ISBN: 978-3-540-71629-7
eBook Packages: Computer ScienceComputer Science (R0)