Abstract
This paper presents a constructive learning approach for developing sensor-motor mapping in autonomous systems. The system’s adaptation to environment changes is discussed and three methods are proposed to deal with long term and short term changes. The proposed constructive learning allows autonomous systems to develop network topology and adjust network parameters. The approach is supported by findings from psychology and neuroscience especially during infants cognitive development at early stages. A growing radial basis function network is introduced as a computational substrate for sensory-motor mapping learning. Experiments are conducted on a robot eye/hand coordination testbed and results show the incremental development of sensory-motor mapping and its adaptation to changes such as in tool-use.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Bousquet, O, Balakrishnan, K., and Honavar, V (1998). Is the hippocampus a Kalman filter? In Pacific Symposium on Biocomputing, pages 655–666, Hawaii.
Hihara, S., Notoya, T., Tanaka, M., Ichinose, S., Ojima, H., Obayashi, S., Fujii, N., and Iriki, A. (2006). Extension of corticocortical afferents into the anterior bank of the intraparietal sulcus by tool-use training in adult monkeys. Neuropsychologia, 44(13):2636–2646.
Hihara, S., Obayashi, S., Tanaka, M., and Iriki, A. (2003). Rapid learning of sequential tool use by macaque monkeys. Physiology and Behavior, 78:427–434.
Huys, Quentin JM, Zemel, Richard S, Natarajan, Rama, and Dayan, Peter (2007). Fast population coding. Neural Computation, 19(2):404–441.
Imamizu, H., Miyauchi, S., Tamada, T., Sasaki, Y., Takino, R., Puetz, B., Yoshioka, T., and Kawato, M. (2000). Human cerebellar activity reflecting an acquired internal model of a novel tool. Nature, 403:192–195.
Johnson-Frey, Scott H. (2004). The neural bases of complex tool use in humans. Trends in Cognitive Science, 8(2):71–78.
Lee, M.H., Meng, Q., and Chao, F. (2007). Developmental learning for autonomous robots. Robotics and Autonomous Systems, 55(9):750–759.
Lu, Yingwei, Sundararajan, N., and Saratchandran, P. (1998). Performance evaluation of a sequential minimal radial basis function (RBF) neural network learning algorithm. IEEE Transactions on neural networks, 9(2):308–318.
Maguire, Eleanor A., Gadian, David G., Johnsrude, Ingrid S., Goodd, Catriona D., Ashburner, John, Frackowiak, Richard S. J., and Frith, Christopher D. (2000). Navigation-related structural change in the hippocampi of taxi drivers. PNAS, 97(8):4398–4403.
Maravita, A. and Iriki, A. (2004). Tools for the body (schema). Trends in Cognitive Science, 8(2):79–86.
O’Keefe, J. (1989). Computations the hippocampus might perform. In Nadel, L., Cooper, L.A., Culicover, P., and Harnish, R.M., editors, Neural connections, mental computation. MIT Press, Cambridge, MA.
Piaget, Jean (1952). The Origins of Intelligence in Children. Norton, New York, NY.
Poggio, Tomaso (1990). A theory of how the brain might work. MIT AI. memo No. 1253.
Poggio, Tomaso and Girosi, Federico (1990). Networks for approximation and learning. Proceedings of the IEEE, 78(9):1481–1497.
Pouget, A. and Snyder, L.H. (2000). Computational approaches to sensorimotor transformations. Nature Neuroscience supplement, 3:1192–1198.
Quartz, S.R. and Sejnowski, T.J. (1997). The neural basis of cognitive development: A constructivist manifesto. Brain and Behavioral Sciences, 20:537–596.
Rao, R. and Ballard, D. (1997). Dynamic model of visual recognition predicts neural response properties in the visual cortex. Neural Computation, 9(4):721–763.
Rao, R. and Ballard, D. (1999). Predictive coding in the visual cortex. Nature Neuroscience, 2(1):79–87.
Shultz, T.R (2006). Constructive learning in the modeling of psychological development. In Munakata, Y. and Johnson, M.H., editors, Processes of change in brain and cognitive development: Attention and performance XXI, pages 61–86. Oxford: Oxford University Press.
Shultz, T.R., Mysore, S.P., and Quartz, S. R. (2007). Why let networks grow. In Mareschal, D., Sirois, S., Westermann, G., and Johnson, M.H., editors, Neuroconstructivism: Perspectives and prospects, volume 2, chapter 4, pages 65–98. Oxford: Oxford University Press.
Szirtes, Gábor, Póczos, Barnabás, and Lőrincz, András (2005). Neural Kalman filter. Neurocomputing, 65–66:349–355.
Todorov, E. and Jordan, M.I. (2002). Optimal feedback control as a theory of motor coordination. Nature Neuroscience, 5(11):1226–1235.
Weng, Juyang, McClelland, James, Pentland, Alex, Sporns, Olaf, Stockman, Ida, Sur, Mriganka, and Thelen, Esther (2001). Autonomous mental development by robots and animals. Science, 291(5504):599–600.
Westermann, G. and Mareschal, D. (2004). From parts to wholes: Mechanisms of development in infant visual object processing. Infancy, 5(2):131–151.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer Science+Business Media B.V.
About this chapter
Cite this chapter
Meng, Q., Lee, M.H., Hinde, C.J. (2010). Robot Competence Development by Constructive Learning. In: Amouzegar, M. (eds) Advances in Machine Learning and Data Analysis. Lecture Notes in Electrical Engineering, vol 48. Springer, Dordrecht. https://doi.org/10.1007/978-90-481-3177-8_2
Download citation
DOI: https://doi.org/10.1007/978-90-481-3177-8_2
Published:
Publisher Name: Springer, Dordrecht
Print ISBN: 978-90-481-3176-1
Online ISBN: 978-90-481-3177-8
eBook Packages: EngineeringEngineering (R0)