Overview
These lecture notes review neural network techniques for achieving adaptivity in autonomous agents. They are structured around three main topics:
-
Neural learning algorithms. A distinction is made between the short- term and long-term levels of processing in neural networks. Long-term processing is what is referred to as “learning”, although it should be more properly called “adaptation”, and it amounts to modifying the connection weights. A classification of the learning tasks, learning rules and learning models that have appeared in the literature is presented. In particular, learning rules are grouped into three classes: correlational rules (Hebbian), error-minimization rules (perception, LMS, back-propagation) and reinforcement rules (associative search, associative reward-penalty)
-
Applications to robot control. Within the field of control, neural networks have been applied to system identification and to the design of controllers. The two main approaches that have arisen are direct-inverse modelling and forward modelling. In the more specific field of robot control, efforts have been oriented to the learning of inverse models (inverse robot kinematics and dynamics) and of goal-oriented sensorimotor mappings (path finding, hand-eye coordination). Two systems are next described in detail: topology-conserving maps for learning visuomotor coordination of a robot arm [32], where a correlational rule is combined with an error-minimization rule; and the reinforcement-based path finder for mobile robots described in [26]
-
Limitations of neural control: a need for planning? This block is intended to foster a discussion of what the advantages and limitations of subsymbolic and symbolic approaches are. Neural controllers obviate the programming phase by exploiting learning, but their generality and opacity make it impossible to take advantage of problem-specific information. This results in very long learning times. Motion planners, on the other hand, rely on geometric reasoning and heuristic search, thus allowing the use of domain-specific knowledge to gain efficiency. However, they are hard to program and computationally expensive when high precision is required. A case is made out for the combination of a one-shot symbolic acquisition of knowledge (initial setting of the system) and a subsymbolic adaptation of skills through repetitive trial and error (subsequent tuning).
The author acknowledges support from the comisión Interministerial de Ciencia y Tecnología (CICYT) under the project SUBSIM (TAP93-0451) and from the ESPRIT III Program of the European Community under contract No. 7274 (project “B-LEARN II: Behavioural Learning: Combining Sensing and Action”).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Aarts, E.H.L., Korst, J.H.M.: Boltzmann machines and their applications. In: de Bakker, J.W., Nijman, A.J., Treleaven, P.C. (eds.): Proceedings of Parallel Achitectures and Languages Europe (PARLE). Lecture Notes in Computer Science 258, Berlin: Springer-Verlag 1987, pp. 34–50
Amari, S.: Neural theory of association and concept-formation. Biological Cybernetics 26, 175–185 (1977)
Arbib, M.A., Kilmer, W.L., Spinelli, D.N.: Neural models of memory. In: Rozen zweig, M.R., Bennet, E.L.: Neural Mechanisms of Learning and Memory. Cambridge, MA: MIT Press 1976
Barto, A.G.: Learning by statistical cooperation of self-interested neuron-like computing elements. Human Neurobiology 4, 229–256 (1985)
Barto, A.G., Anandan, P.: Pattern-recognizing stochastic learning automata. IEEE Transactions on Systems, Man, and Cybernetics 15 (3), 360–375 (1985)
Barto, A.G., Sutton, R.S., Brouwer, P.S.: Associative Search Network: A reinforcement learning associative memory5. Biological Cybernetics 40, 201–211 (1981)
Bekey, O.A., Goldberg, K.Y.: Neural Networks in Robotics. Kluwer Academic Publishers 1993
Ceinbrano, G., Wells, G.: Neural networks for control. In: Artificial Intelligence in Process Control. Pergamon Press 1992
Feldman, J.A., Ballard, D.H.: Connectionist models and their properties. Cognitive Science 6, 205–254 (1982)
FogelinanSoulie, F.: Le connexionnisine. Support de cours MARI 87–COG– NITIVA 87, Paris, May 1987
Grossberg, S.: Competitive learning: from interactive activation to adaptive resonance. Cognitive Science 11, 23–63 (1987)
Hebb, D.O.: The Organization of Behavior. New York: Wiley 1949
Hecht-Nielsen, R.: Neurocomputing. Reading, MA: Addison-Wesley 1990
Hinton, G.E.: Learning translation invariant recognition in massive parallel networks. Iii: de Bakker, J.W., Nijman, A. J., Treleaven, P.C. (eds.): Proceedings of Parallel Achitectures and Languages Europe (PARLE). Lecture Notes in Computer Science 258, Berlin: Springer-Verlag 1987, pp. 1–13
Hinton, G.E., Anderson, J. A.: Parallel Models of Associative Memory. Hillsdale, NJ: Erlbaum 1981
Hinton, G.E.: Connectionist learning procedures. Artificial Intelligence 40, 185– 234 (1989)
Hopfield, J.J.: Neural networks and physical systems with emergent collective computational abilities. Proceedings National Academy of Sciences USA 79, 2554–2558 (1982)
Jordan, M.I., Ruinelhart, D.E.: Forward models: Supervised learning with a distal teacher. Cognitive Science 16, 307–354 (1992)
Kohonen, T.: Associative Memory: A System Theoretic Approach. Berlin: SpringerVerlag 1977
Kohonen, T.: Self-Organization and Associative Memory ( second edition ). Berlin: Springer-Verlag 1988
Kohonen, T., Oja, E.: Fast adaptative formation of orthogonalizing filters and associative memory in recurrent networks of neuron-like elements. Biological Cybernetics 21, 85–95 (1976)
Kröse, B.J.A., van der Smagt, P.P.: An Introduction to Neural Networks, 5th edition. University of Amsterdam 1993
Kung, S-Y., Hwang, J-N.: Neural network architectures for robotic applications. IEEE Transactions on Robotics and Automation 5 (5), 641–657 (1989)
LeCun, Y.: Une procedure daprentissage pour reseau au seuil assyinetrique. Proceedings of COGNITIVA, 1985, pp. 599–604
Millan, J. del R.: Building reactive path-finders through reinforcement connectionist learning: Three issues and an architecture. Proc. 10th European Conf. on Artificial Intelligence (ECAI92), 1992, pp. 661–665
Millan, J. del R., Torras, C.: A reinforcement connectionist approach to robot path finding in non-maze-like environments. Machine Learning 8(3/4), 363– 395 (1992)
Millan, J. del R., Torras, C.: Efficient reinforcement learning of navigation strategies in an autonomous robot. Proc. Intl. Conf. on Intelligent Robotics Systems (IROS94), September 1994
Miller, W.T., Sutton, R.S., Werbos, P.J.: Neural Networks for Control. Cainbridge, MA: MIT Press 1990
Minsky, M., Papert, S.: Perceptions: An Introduction to Computational Geometry. Cambridge, MA: MIT Press 1969
Nilsson, N.J.: Learning Machines. McGraw-Hill 1965
Pavlov, I.P.: Conditioned Reflexes. Oxford University Press 1927
Ritter, H., Martinetz, T., Schulten, K.: Neural Computation and Self- Organizing Maps. New York: Addison-Wesley 1992
Rosenblatt, F.: Principles of Neurodynamics. Spartan Books 1962
Rumelhart, D.E., Zipser, D.: Feature discovery by competitive learning. Cognitive Science 9, 75–112 (1985)
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back–propagating errors. Letters to Nature 323, 533–535 (1986)
Skinner, B.F.: The Behavior of Organisms: An Experimental Analysis. Apple– ton Century 1938
Sutton, R.S.: Learning to predict by the methods of temporal differences. Machine Learning 3, 9–44 (1988)
Torr as, C.: Temporal-Pattern Learning in Neural Models. Lecture Notes in Biomatliematics No. 63, Berlin: Springer-Verlag 1985
Torras, C.: Relaxation and neural learning: points of convergence and divergence. Journal of Parallel and Distributed Computing 6, 217–244 (1989)
Torras, C.: From geometric motion planning to neural motor control in robotics. AI Communications 6 (1), 3–17 (1993)
von der Malsburg, C.: Self-organization of orientation sensitive cells in the striate cortex. Kybernetik 14, 80–100 (1973)
Widrow, B., Hoff, M.E.: Adaptative switching capatibility and its relation to the mechanisms of association. Kybernetik 12, 204–215 (1960)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Torras, C. (1995). Robot Adaptivity. In: Steels, L. (eds) The Biology and Technology of Intelligent Autonomous Agents. NATO ASI Series, vol 144. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-79629-6_3
Download citation
DOI: https://doi.org/10.1007/978-3-642-79629-6_3
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-79631-9
Online ISBN: 978-3-642-79629-6
eBook Packages: Springer Book Archive