Publication
Natural inspiration for artificial adaptivity: Some neurocomputing experiences in robotics
Conference Article
Conference
International Conference on Unconventional Models of Computation (UC)
Edition
4th
Pages
32-45
Doc link
http://dx.doi.org/10.1007/11560319_5
File
Abstract
The biological world offers a full range of adaptive mechanisms, from which technology researchers try to get inspiration. Among the several disciplines attempting to reproduce these mechanisms artificially, this paper concentrates on the field of Neural Networks and its contributions to attain sensorimotor adaptivity in robots. Essentially this type of adaptivity requires tuning nonlinear mappings on the basis of input-output information. Several experimental robotic systems are described, which rely on inverse kinematics and visuomotor mappings. Finally, the main trends in the evolution of neural computing are highlighted, followed by some remarks drawn from the surveyed applications.
Categories
cybernetics.
Scientific reference
C. Torras. Natural inspiration for artificial adaptivity: Some neurocomputing experiences in robotics, 4th International Conference on Unconventional Models of Computation, 2005, Sevilla, Espanya, in Theoretical Computer Science and General Issues, Vol 3699 of Lecture Notes in Computer Science, pp. 32-45, 2005, Springer, Berlin, Alemanya.
Follow us!