This paper discusses software engineering aspects of neurocontrol algorithm design. Cutting edge algorithm development often outstrips the capability of routinely available software packages. Hence, it is difficult to perform adequate algorithm validation and verification (algorithm V & V). The basic building blocks of a software neurocontroller (data sampling, state prediction and control selection) are developed. The underlying artificial neural architecture used here is the CMAC, although much of the discussion is fairly generic. Code fragments are provided that illus trate implementation details for the CMAC architecture, the sampling of the data stream, local con troller estimates and so forth.
Get full access to this article
View all access options for this article.
References
1.
Abutaleb, A.1987"Time Delay Estimation and Optimal Control Concepts" , Signal Processing, 12 -291-3Cr7
2.
Albus, J.1975a "A New Approach to Mampulator Control. The Cerebellar Model Articulation Controller (CMAC)", J Dynamic Systems, Measurement and Control, pp 220-227
3.
Albus, J.1975. "Data Storage in the Cerebellar Model Articulation Controller (CMAC)", J. Dynamic Systems, Measurement and Control , pp. 228-233
4.
Albus, J.1979"Mechanisms of Planning and Problem Solving in the Brain" , Math Biosciences, 45·247-293.
5.
Carlson, R., C. Lee and K. Rothermel1992"Real Time Neural Control of an Active Structure" , in Intelligent Engineering Systems through Artificial Neural Networks, Proceedings of the Artificial Neural Networks in Engineering (ANNIE '92) Conference, November, 1992, C Dagli, L. Burke and Y. Shin, eds. , ASME Press, pp 623-628.
6.
Jalali, A. and M. Ferguson1992"Computationally Efficient Algorithms for On-Line Optimization of Markov Decision Processes", Auloinatica , 28(1) 107-118
7.
Kasonga, R.1990"Parameter Estimation by Deterministic Approximation of a Solution of a Stochastic Differenhal Equation", Commun. Statis- Stochastic Models, 6(l) 59-67
8.
Miller, W.1987"Sensor-Based Control of Robotic Manipulators Using a General Learning Algorithm", IEEE J Robot Automat. , RA-3(2).157-165
9.
Miller, W.1989"Real Time Application of Neural Networks for Sensor Based Control of Robots with Vision", IEEE Systems, Man and Cvbernetics, 19825-831
10.
Nguyen, D. and B. Widrow1990"Neural Networks for Self-Learning Control Systems" , IEEE Control Sys. Mag. , 10(3):18-23
11.
Peterson, J.1992"On-Line Estimation of Optimal Control Sequences Pontryagm Estimators", in Intelligent Engineering Systems through Artificial Neural Networks, Proceedings of the Artificial Neural Networks in Engineering (ANNIE '92) Conference , November, 1992, C Dagli, L Burke and Y Shin, eds , ASME Press, pp 579-584
12.
Peterson, J.1993a "On-Line Estimation of the Optimal Value Function. HJB Estimators", in Advances in Neural Information Processing Systems, 5, S Hanson, J. Cowan and C. Giles, eds , Morgan Kaufmann Publishers, pp. 319-326
13.
Peterson, J.1993b. "CMAC Tutorial"; in Proceedings of the 3rd Workshop on Neural Networks: AcademicllndustriallNASAlDefense, WNN 92, Feb. 10-12, Auburn University, Auburn, AL and Nov. 4-6, 1992, South Shore Harbor, Houston, TX, Simulation Councils Incorporated, M. Padgett, ed., pp. 630-649.
14.
Peterson, J.1993c. "The Use of Pontryagin Estimators for On-line Optimal Control Sequence Estimation: The Truck Backer-Upper Case Study," to appear in Special Issue on Artificial Neural Networks for Mathematical and Computer Modeling
15.
Shelton, R. and J. Peterson.1992. "Controlling a Truck with an Adaptive Critic CMAC Design" , Simulation, Special Issue on Neural Networks , 58(5):319-326.
16.
Sutton, R.1988. "Learning to Predict by the Method of Temporal Differences" , Machine Learning, 3(9):9-44.
17.
Tataru, D.1992"Viscosity Solutions for the Dynamic Programming Equations" , Appl Math. Optim , 25109-126.
18.
Werbos, P.1990a. "Consistency of HDP Applied to a Simple Reinforcement Learning Problem", Neural Networks, 3:179-189.
19.
Werbos, P.1990b. "A Menu of Designs for Reinforcement Learning Over Time" , in Neural Networks for Control , W. Miller, W. Sutton and P. Werbos, eds , pp 67-96
20.
Zhou, X.1990"Maximum Principle, Dynamic Programming, and Their Connection in Deterministic Control", Journal of Optimization Theory and Applications, 65(2) 363-373
