Neural Networks in Robot Control

Neural nets (NNs) are large scale systems involving a large number of special type nonlinear processors called “neurons” [1–4]. Biological neurons are nerve cells that have a number of internal parameters called synaptic weights. The human brain consists of over ten million neurons. The weights are adjusted adaptively according to the task under execution such that to improve the overall system performance. Here we are dealing with artificial NNs the neurons of which are characterized by a state, a list of weighted inputs from other neurons, and an equation governing their dynamic operation. The NN weights can take new values through a learning process which is accomplished by the minimization of a certain objective function through the step-by-step adjustment of the weights. The optimal values of the weights are stored as the strengths of the neurons’ inteconnections. The NN approach to computation is suitable for problems for which more conventional computation approaches are not effective. Such problems involve systems or processes that cannot be modelled with concise and accurate mathematical expressions, typical examples being machine vision, speech and patern recognition, control systems and robotic systems. The implementation of NNs was made possible by the recent developments in fast parallel architectures (VLSI, electrooptical, and other). The principal features of NNs are: associative storage and retrieval signal regularity extraction convergence rate independent of number of nodes.

[1]  Dejan J. Sobajic,et al.  Artificial Neural-Net Based Intelligent Robotics Control , 1988, Other Conferences.

[2]  Moshe Kam,et al.  Neuromorphic architectures for fast adaptive robot control , 1988, Proceedings. 1988 IEEE International Conference on Robotics and Automation.

[3]  Filson H. Glanz,et al.  Application of a General Learning Algorithm to the Control of Robotic Manipulators , 1987 .

[4]  C. Y. Ho,et al.  The application of spline functions to trajectory generation for computer-controlled manipulators , 1984 .

[5]  Ten-Huei Guo,et al.  Adaptive linear controller for robotic manipulators , 1983 .

[6]  J. Albus.  Mechanisms of planning and problem solving in the brain , 1979 .

[7]  Ronald C. Arkin,et al.  Intelligent Robotic Systems , 1995, IEEE Expert.

[8]  S. Shankar Sastry,et al.  Adaptive Control of Mechanical Manipulators , 1987 .

[9]  James S. Albus,et al.  Data Storage in the Cerebellar Model Articulation Controller (CMAC) , 1975 .

[10]  Richard P. Lippmann,et al.  An introduction to computing with neural nets , 1987 .

[11]  Kazuyoshi Tsutsumi,et al.  Neural computation for controlling the configuration of 2-dimensional truss structure , 1988, IEEE 1988 International Conference on Neural Networks.

[12]  Toshio Fukuda,et al.  An iterative learning control for noisy systems by using linear neural networks , 1992 .

[13]  A. Guez,et al.  A trainable neuromorphic controller , 1988 .

[14]  A. Guez,et al.  Solution to the inverse kinematics problem in robotics by neural networks , 1988, IEEE 1988 International Conference on Neural Networks.

[15]  Kumpati S. Narendra,et al.  Neural networks in control systems , 1992, [1992] Proceedings of the 31st IEEE Conference on Decision and Control.

[16]  Karl Johan Åström,et al.  Theory and applications of adaptive control - A survey , 1983, Autom..

[17]  Igor Aleksander,et al.  Introduction to Neural Computing , 1990 .

[18]  G. Ambrosino,et al.  Robust model tracking control for a class of nonlinear plants , 1985 .

[19]  Madan M. Gupta,et al.  Neuro-controller with dynamic learning and adaptation , 1993, J. Intell. Robotic Syst..

[20]  George A. Bekey,et al.  Adaptive Load Balancing Between Mobile Robots Through Learning in an Artificial Neural System , 1988, 1988 American Control Conference.

[21]  Weiping Li,et al.  Adaptive manipulator control a case study , 1987, Proceedings. 1987 IEEE International Conference on Robotics and Automation.

[22]  F. Miyazaki,et al.  Bettering operation of dynamic systems by learning: A new control theory for servomechanism or mechatronics systems , 1984, The 23rd IEEE Conference on Decision and Control.

[23]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[24]  Naresh K. Sinha,et al.  An iterative learning scheme for motion control of robots using neural networks: A case study , 1993, J. Intell. Robotic Syst..

[25]  Martin Peckerar,et al.  Neutral networks for tactile perception , 1988, Proceedings. 1988 IEEE International Conference on Robotics and Automation.

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

[27]  R. K. Elsley,et al.  A learning architecture for control based on back-propagation neural networks , 1988, IEEE 1988 International Conference on Neural Networks.

[28]  Suguru Arimoto.  Robustness of learning control for robot manipulators , 1990, Proceedings., IEEE International Conference on Robotics and Automation.

[29]  Derrick H. Nguyen,et al.  Neural networks for self-learning control systems , 1990 .

[30]  Thea Iberall.  A Neural Network for Planning Hand Shapes in Human Prehension , 1988, 1988 American Control Conference.

[31]  Allon Guez,et al.  Neurocontroller design via supervised and unsupervised learning , 1989, J. Intell. Robotic Syst..

[32]  Stephen Grossberg,et al.  Neural dynamics of adaptive sensory-motor control : ballistic eye movements , 1986 .

[33]  Richard S. Sutton,et al.  Neuronlike adaptive elements that can solve difficult learning control problems , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[34]  A. Guez,et al.  Neural network architecture for control , 1988, IEEE Control Systems Magazine.

[35]  Spyros G. Tzafestas,et al.  Learning algorithms for neural networks with the Kalman filters , 1990, J. Intell. Robotic Syst..

[36]  Teuvo Kohonen,et al.  Self-Organization and Associative Memory , 1988 .

[37]  F. Smith.  A trainable nonlinear function generator , 1966 .

[38]  Mitsuo Kawato,et al.  Feedback-error-learning neural network for trajectory control of a robotic manipulator , 1988, Neural Networks.

[39]  M. Kawato,et al.  Hierarchical neural network model for voluntary movement with application to robotics , 1988, IEEE Control Systems Magazine.

[40]  James S. Albus,et al.  I A New Approach to Manipulator Control: The I Cerebellar Model Articulation Controller , 1975 .

[41]  Daniel E. Whitney,et al.  Resolved Motion Rate Control of Manipulators and Human Prostheses , 1969 .

[42]  Spyros G. Tzafestas,et al.  Some computer-aided estimators in stochastic control systems identification† , 1970 .

[43]  A. Sideris,et al.  A multilayered neural network controller , 1988, IEEE Control Systems Magazine.