Neural Networks and Adaptive Control

This chapter provides an overview of some adaptive control methods and how artificial neural networks are being used as components of adaptive control systems. It suggests, however, that the adaptive control methods developed by control engineers can be misleading guides to thinking about control in biological systems. Furthermore, it suggests that neural networks, whether artificial or real, might be most effective when used as components of architectures that are not conservative extensions of conventional adaptive control architectures. After a brief discussion of control, several approaches to adaptive control as developed by control engineers are described, followed by presentation of a view of artificial neural networks and their potential roles in control systems. Two examples are described in which artificial neural networks have been applied successfully to difficult control problems, and a model of the cerebellum is discussed in light of conceptual schemes based on engineering control practice.

[1]  W. Ashby.  Design for a Brain , 1954 .

[2]  Robert B. McGhee,et al.  A Finite State Approach to the Synthesis of Bioengineering Control Systems , 1966 .

[3]  R. Bellman.  Dynamic programming. , 1957, Science.

[4]  D. Marr.  A theory of cerebellar cortex , 1969, The Journal of physiology.

[5]  J. Albus.  A Theory of Cerebellar Function , 1971 .

[6]  P. Werbos,et al.  Beyond Regression : "New Tools for Prediction and Analysis in the Behavioral Sciences , 1974 .

[7]  J. Hollerbach.  Computers, brains and the control of movement , 1982, Trends in Neurosciences.

[8]  Graham C. Goodwin,et al.  Adaptive filtering prediction and control , 1984 .

[9]  A G Barto,et al.  Learning by statistical cooperation of self-interested neuron-like computing elements. , 1985, Human neurobiology.

[10]  Yann LeCun,et al.  Une procedure d'apprentissage pour reseau a seuil asymmetrique (A learning scheme for asymmetric threshold networks) , 1985 .

[11]  B. Ydstie.  Bifurcations and complex dynamics in adaptive control systems , 1986, 1986 25th IEEE Conference on Decision and Control.

[12]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[13]  David L. Waltz,et al.  Toward memory-based reasoning , 1986, CACM.

[14]  Rodney A. Brooks,et al.  A Robust Layered Control Syste For A Mobile Robot , 2022 .

[15]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[16]  David J. Reinkensmeyer,et al.  Using associative content-addressable memories to control robots , 1988, Proceedings of the 27th IEEE Conference on Decision and Control.

[17]  Philip E. Agre,et al.  The dynamic structure of everyday life , 1988 .

[18]  Andrew G. Barto,et al.  From Chemotaxis to cooperativity: abstract exercises in neuronal learning strategies , 1989 .

[19]  Kumpati S. Narendra,et al.  Learning automata - an introduction , 1989 .

[20]  Richard Durbin,et al.  The computing neuron , 1989 .

[21]  Vijaykumar Gullapalli,et al.  A stochastic reinforcement learning algorithm for learning real-valued functions , 1990, Neural Networks.

[22]  Richard S. Sutton,et al.  Neural networks for control , 1990 .

[23]  Mitsuo Kawato,et al.  Computational schemes and neural network models for formulation and control of multijoint arm trajectory , 1990 .

[24]  C. E. Rohrs.  Rethinking adaptive control for the 1990s , 1990, 29th IEEE Conference on Decision and Control.

[25]  Andrew G. Barto,et al.  Connectionist learning for control: an overview , 1990 .

[26]  Ernst D. Dickmanns,et al.  An integrated spatio-temporal approach to automatic visual guidance of autonomous vehicles , 1990, IEEE Trans. Syst. Man Cybern..

[27]  Dean A. Pomerleau,et al.  Combining artificial neural networks and symbolic processing for autonomous robot guidance , 1991 .

[28]  Michael I. Jordan,et al.  Task Decomposition Through Competition in a Modular Connectionist Architecture: The What and Where Vision Tasks , 1990, Cogn. Sci..

[29]  Michael P. Wellman,et al.  Planning and Control , 1991 .

[30]  Lynn Nadel,et al.  1990 Lectures in Complex Systems , 1991 .

[31]  R.J. Williams,et al.  Reinforcement learning is direct adaptive optimal control , 1991, IEEE Control Systems.

[32]  Roderic A. Grupen,et al.  Learning reactive admittance control , 1992, Proceedings 1992 IEEE International Conference on Robotics and Automation.

[33]  Michael I. Jordan,et al.  Forward Models: Supervised Learning with a Distal Teacher , 1992, Cogn. Sci..

[34]  A. Barto,et al.  Distributed sensorimotor learning , 1992 .

[35]  Vijaykumar Gullapalli,et al.  Reinforcement learning and its application to control , 1992 .

[36]  Satinder Singh,et al.  Distributed Representation of Limb Motor Programs in Arrays of Adjustable Pattern Generators , 1993, Journal of Cognitive Neuroscience.