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 robotic applications.
Keywords
- Conditioned Stimulus
- Inverse Kinematic
- Neural Computing
- Instrumental Conditioning
- Adaptive Resonance Theory
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
A more detailed version of this review, although less up to date, can be found in [48].
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 subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Albus, J.S.: A new approach to manipulator control: The cerebellar model articulation controller (CMAC). Transactions of the ASME. Journal of Dynamic Systems, Measurement and Control 97, 220–227 (1975)
An, G.: The effects of adding noise during backpropagation training on generalization performance. Neural Computation 8, 643–674 (1996)
Arbib, M.A.: Handbook of Brain Theory and Neural Networks. MIT Press, Cambridge (1995); (An updated second edition will appear in November 2002)
Bäck, T., Fogel, D.B., Michalewicz, Z. (eds.): Handbook of Evolutionary Computation. Oxford University Press, New York, and Institute of Physics Publishing, Bristol (1997)
Beyer, H.-G., Schwefel, H.-P.: Evolution strategies - A comprehensive introduction. Natural Computing 1(1), 3–52 (2002)
Bishop, C.: Neural Networks for Pattern Recognition. Oxford University Press, Oxford (1995)
Cherkassky, V.: Model complexity control and statistical learning theory. Natural Computing 1(1), 109–133 (2002)
D’Souza, A., Vijayakumar, S., Schaal, S.: Learning inverse kinematics. In: Proc. IEEE/RSJ Conf. on Intel. Robots and Systems, Maui, Hawaii, USA, pp. 298–303 (2001)
Dorigo, M.(ed): Special issue on ‘Learning Autonomous Robots’. IEEE Trans. on Systems, Man and Cybernetics, Part B: Cybernetics 26(3) (1996)
Espiau, B., Chaumette, F., Rives, P.: A new approach to visual servoing in robotics. IEEE Trans. on Robotics and Automation 8(3), 313–326 (1992)
Goldberg, D.E.: Genetic Algorithms in Search, Optimization and Machine Learning. Addison-Wesley, Reading (1989)
Grossberg, S.: Competitive learning: from interactive activation to adaptive resonance. Cognitive Science 11, 23–63 (1987)
Hebb, D.O.: The Organization of Behavior. Wiley, New York (1949)
Higuchi, T., Iwata, M., Liu, W. (eds.): Evolvable Systems: From Biology to Hardware. Springer, Heidelberg (1997)
Husbands, P., Meyer, J.A.: Proc. 1st European Workshop on Evolutionary Robotics (EvoRobot 1998). Springer, Heidelberg (1998)
Kohonen, T.: Self-Organizing Maps, 3rd edn. Series in Information Sciences, vol. 30. Springer, Heidelberg (2001)
Koza, J.R.: Genetic Programming: On Programming Computers by means of Natural Selection. MIT Press, Cambridge (1992)
Kröse, B.J.A., van der Smagt, P.P.: An Introduction to Neural Networks, 5th edn. University of Amsterdam (1993)
LeCun, Y.: Une procedure d’aprentissage pour reseau au seuil assymetrique. In: Proc. of COGNITIVA, pp. 599–604 (1985)
Millán, J.R., Torras, C.: A reinforcement learning connectionist approach to robot path finding in non-maze-like environments. Machine Learning 8(3/4), 363–395 (1992)
Millán, J.R., Torras, C.: Learning sensor-based navigation. In: Morik, K., Kaiser, M., Klingspor, V. (eds.) Making Robots Smarter: Combining Sensing and Action through Robot Learning. Kluwer Academic Publishers, Boston (1999)
Mitchell, T., Franklin, J., Thrun, S.: Recent Advances in Robot Learning. Kluwer Academic Publishers, Boston (1996)
Morik, K., Kaiser, M., Klingspor, V.: Making Robots Smarter: Combining Sensing and Action through Robot Learning. Kluwer Academic Publishers, Boston (1999)
Omidvar, O., van der Smagt, P.: Neural Systems for Robotics. Academic Press, San Diego (1997)
Park, D.C., El-Sharkawi, M.A., Marks II, R.J.: An adaptively trained neural network. IEEE Trans. on Neural Networks 2(3), 334–345 (1991)
Pavlov, I.P.: Conditioned Reflexes. Oxford University Press, Oxford (1927)
Ritter, H., Martinetz, T., Schulten, K.: Neural Computation and Self-Organizing Maps. Addison Wesley, New York (1992)
Ruiz de Angulo, V., Torras, C.: On-line learning with minimum degradation in feedforward networks. IEEE Trans. on Neural Networks 6(3), 657–668 (1995)
Ruiz de Angulo, V., Torras, C.: Self-calibration of a space robot. IEEE Trans. on Neural Networks 8(4), 951–963 (1997)
Ruiz de Angulo, V., Torras, C.: A framework to deal with interference in connectionist systems. AI Communications 13(4), 259–274 (2000)
Ruiz de Angulo, V., Torras, C.: Architecture-independent approximation of functions. Neural Computation 13(5), 1119–1135 (2001)
Ruiz de Angulo, V., Torras, C.: Neural learning invariant to network size changes. In: Dorffner, G., Bischof, H., Hornik, K. (eds.) ICANN 2001. LNCS, vol. 2130, pp. 33–40. Springer, Heidelberg (2001)
Ruiz de Angulo, V., Torras, C.: Learning inverse kinematics via cross-point function decomposition. In: Dorronsoro, J.R. (ed.) ICANN 2002. LNCS, vol. 2415, pp. 856–861. Springer, Heidelberg (2002)
Ruiz de Angulo, V., Torras, C.: Sequential learning in feedforward networks: Proactive and retroactive interference minimization. In: Dorronsoro, J.R. (ed.) ICANN 2002. LNCS, vol. 2415, pp. 1339–1344. Springer, Heidelberg (2002)
Ruiz de Angulo, V., Torras, C.: A deterministic algorithm that emulates learning with random weights. Neurocomputing 48(1-4), 975–1002 (2002)
Ruiz de Angulo, V., Torras, C.: Neural learning methods yielding functional invariance. Theoretical Computer Science 320(1), 111–121 (2004)
Ruiz de Angulo, V., Torras, C.: Speeding up the learning of robot kinematics through function decomposition. IEEE Trans. on Neural Networks (November 2005)
Ruiz de Angulo, V., Torras, C.: Using pSOMs to learn inverse kinematics through virtual decomposition of the robot. In: Cabestany, J., Prieto, A.G., Sandoval, F. (eds.) IWANN 2005. LNCS, vol. 3512, pp. 701–708. Springer, Heidelberg (2005)
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Letters to Nature 323, 533–535 (1986)
Simon, H.A.: The Sciences of the Artificial. MIT Press, Cambridge (1969)
Skinner, B.F.: The Behavior of Organisms: An Experimental Analysis. Appleton Century (1938)
Steels, L.: The Biology and Technology of Intelligent Autonomous Agents. NATO ASI Series F. Springer, Heidelberg (1995)
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)
Torras, C.: Temporal-Pattern Learning in Neural Models. Lecture Notes in Biomathematics, vol. 63. Springer, Heidelberg (1985)
Torras, C.: Sensorimotor integration in robots. In: Ewert, P., Arbib, M.A. (eds.) Visuomotor Coordination: Experiments, Comparisons, Models and Robots, pp. 673–689. Plenum Press, New York (1989)
Torras, C.: Symbolic planning versus neural control in robots. In: Rudomín, P., Arbib, M.A., Cervantes-Pérez, F., Romo, R. (eds.) Neuroscience: From Neural Networks to Artificial Intelligence, Research Notes in Neural Computing, vol. 4, pp. 509–523. Springer, Heidelberg (1993)
Torras, C.(ed): Special issue on ‘Neural Networks at IJCAI 2001. Intl. Journal of Computational Intelligence and Applications 1(4) (2001)
Torras, C.: Neural computing increases robot adaptivity. Natural Computing 1(4), 391–425 (2002)
van de Velde, W.(ed): Special issue on ‘Towards Learning Robots’. Robotics and Autonomous Systems 8(1-2) (1993)
Walter, J., Ritter, H.: Rapid learning with parametrized self-organizing maps. Neurocomputing 12, 131–153 (1996)
Wells, G., Torras, C.: Assessing image features for vision-based robot positioning. Journal of Intelligent and Robotic Systems 30(1), 95–118 (2001)
Wells, G., Venaille, C., Torras, C.: Vision-based robot positioning using neural networks. Image and Vision Computing 14, 715–732 (1996)
Ziemke, T., Sharkey, N.(eds): Special issue on ‘Biorobotics’. Connection Science 10(3-4) (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Torras, C. (2005). Natural Inspiration for Artificial Adaptivity: Some Neurocomputing Experiences in Robotics. In: Calude, C.S., Dinneen, M.J., Păun, G., Pérez-Jímenez, M.J., Rozenberg, G. (eds) Unconventional Computation. UC 2005. Lecture Notes in Computer Science, vol 3699. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11560319_5
Download citation
DOI: https://doi.org/10.1007/11560319_5
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-29100-8
Online ISBN: 978-3-540-32022-7
eBook Packages: Computer ScienceComputer Science (R0)