Training recurrent neurocontrollers for real-time applications

IEEE Transactions on Neural Networks

Volumn 18, Issue 4, 2007, Pages 1003-1015

  Prokhorov, Danil V ^a  

^a TOYOTA MOTOR CORPORATION   (Japan)

Author keywords

Neurocontroller; Real time adaptation; Recurrent neural network (RNN); Simultaneous perturbation stochastic approximation (SPSA); Stochastic meta descent (SMD); Training for robustness

Indexed keywords

HIGH-FIDELITY MODELS; NEUROCONTROLLERS; REAL-TIME ADAPTATION; SIMULTANEOUS PERTURBATION STOCHASTIC APPROXIMATION (SPSA); STOCHASTIC META-DESCENT (SMD);

APPROXIMATION THEORY; KALMAN FILTERS; PERTURBATION TECHNIQUES; REAL TIME CONTROL; ROBUSTNESS (CONTROL SYSTEMS);

RECURRENT NEURAL NETWORKS;

ALGORITHM; ARTICLE; ARTIFICIAL NEURAL NETWORK; COMPUTER SIMULATION; COMPUTER SYSTEM; DECISION SUPPORT SYSTEM; FEEDBACK SYSTEM; THEORETICAL MODEL;

ALGORITHMS; COMPUTER SIMULATION; COMPUTER SYSTEMS; DECISION SUPPORT TECHNIQUES; FEEDBACK; MODELS, THEORETICAL; NEURAL NETWORKS (COMPUTER);

EID: 34547133026     PISSN: 10459227     EISSN: None     Source Type: Journal    
DOI: 10.1109/TNN.2007.899521     Document Type: Article

References (38)

1. Y. H. Kim and F. L. Lewis, High Level Feedback Control with Neural Networks. Singapore: World Scientific, 1998.
2. M. Norgaard, N. K. Poulsen, and O. Ravn, "New developments in state estimation for nonlinear systems," Automatica, vol. 36, pp. 1627-1638, 2000.
3. L. A. Feldkamp, T. M. Feldkamp, and D. V. Prokhorov, "Neural network training with the nprKF," in Proc. Int. Joint Conf. Neural Netw., Washington, DC, 2001, pp. 109-114.
4. L. A. Feldkamp, T. M. Feldkamp, and D. V. Prokhorov, "Recurrent neural network training by nprKF joint estimation," in Proc. Int. Joint Conf. Neural Netw., Hawaii, 2002.
5. D. V. Prokhorov, G. V. Puskorius, and L. A. Feldkamp, "Dynamical neural networks for control," in A Field Guide to Dynamical Recurrent Networks, J. Kolen and S. Kremer, Eds. Piscataway, NJ: IEEE Press, 2001, ch. 16, pp. 257-289.
6. G. Puskorius, L. Feldkamp, and L. Davis, "Dynamic neural network methods applied to on-vehicle idle speed control," Proc. IEEE, vol. 84, no. 10, pp. 1407-1420, Oct. 1996.
7. D. White and D. Sofge, Eds., Handbook of Intelligent Control. New York: Van Nostrand, 1992.
8. K. S. Narendra, "Neural networks for control: Theory and practice," Proc. IEEE, vol. 84, no. 10, pp. 1385-1406, Oct. 1996.
9. T. Hrycej, Neurocontrol: Towards an Industrial Control Methodology New York: Wiley, 1997.
10. M. Agarwal, "Asystematic classification of neural-network-based control," IEEE Control Syst. Mag., vol. 17, no. 2, pp. 75-93, Apr. 1997.
11. J. Suykens, J. Vandewalle, and B. De Moor, Artificial Neural Networks for Modeling and Control of Non-Linear Systems. Norwell, MA: Kulwer, 1996.
12. D. Mandic and J. Chambers, Recurrent Neural Networks for Prediction New York: Wiley, 2001.
13. H.-G. Zimmermann, R. Neuneier, and R. Grothmann, "Modeling of dynamical systems by error correction neural networks," in Modeling and Forecasting Financial Data: Techniques of Nonlinear Dynamics, A. Soofi and L. Cao, Eds. Norwell, MA: Kluwer, 2002, pp. 237-263.
14. D. Prokhorov, "Training recurrent neurocontrollers for robustness with derivative-free Kalman filter," IEEE Trans. Neural Netw., vol. 17, no. 6, pp. 1606-1616, Nov. 2006.
15. E. Wan and A. Nelson, "Dual Kalman filtering methods for nonlinear prediction, estimation, and smoothing," in Advances in Neural Information Processing Systems 9. Cambridge, MA: MIT Press, 1997.
16. E. N. Sanchez, A. Y. Alanis, and J. Rico, "Electric load demand prediction using neural networks trained by Kalman filtering," in Proc. Int. Joint Conf. Neural Netw., Budapest, Hungary, 2004, pp. 2771-2776.
17. C. Lizalde, A. G. Loukianov, and E. N. Sanchez, Force tracking neural control for an electro-hydraulic actuator via second order sliding mode," in Proc. IEEE Int. Symp. Intell. Control, Limassol, Cyprus, Jun. 27-29, 2005, pp. 292-297.
18. J. A. Perez-Ortizand, J. Schmidhuber, F. A. Gers, and D. Eck, "Improving long-term online prediction with decoupled extended Kalman filters," in Proc. Int. Cconf. Artif. Neural Netw., Berlin, Germany, 2002, pp. 1055-1060.
19. S. Younger, P. Conwell, and N. Cotter, "Fixed-weight on-line learning," IEEE Trans. Neural Netw., vol. 10, no. 2, pp. 272-283, Mar. 1999.
20. D. Prokhorov, L. Feldkamp, and I. Tyukin, "Adaptive behavior with fixed weights in RNN: Overview," in Proc. Int. Joint Conf. Neural Netw. Hawaii, 2002.
21. L. A. Feldkamp and G. V. Puskorius, "Training controllers for robustness: Multi-stream DEKF," in Proc. IEEE Int. Conf. Neural Netw., Orlando, FL, 1994, pp. 2377-2382.
22. P. J. Werbos, "Backpropagation through time: What it does and how to do it," Proc. IEEE, vol. 78, no. 10, pp. 1550-1560, Oct. 1990.
23. K. S. Narendra and K. Parthasarathy, "Identification and control of dynamical systems containing neural networks," IEEE Trans. Neural Netw., vol. 1, no. 1, pp. 4-27, Mar. 1990.
24. K. S. Narendra and K. Parthasarathy, "Gradient methods for the optimization of dynamical systems containing neural networks," IEEE Trans. Neural Netw., vol. 2, no. 1, pp. 252-262, Mar. 1991.
25. D. Prokhorov, "Backpropagation through time and derivative adaptive critics: A common framework for comparison," in Learning and Approximate Dynamic Programming, Si, Ed. Piscataway, NJ: IEEE Press, 2004, ch. 15.
26. L. A. Feldkamp and G. V. Puskorius, "A signal processing framework based on dynamic neural networks with application to problems in adaptation, filtering and classification," Proc. IEEE, vol. 86, no. 11, pp. 2259-2277, Nov. 1998.
27. S. Haykin, Ed., Kalman Filtering and Neural Networks. New York: Wiley, 2002.
28. W. H. Press, S. A. Teukolsky, W. T. Vetterling, and B. P. Flannery, Numerical Recipes in C: The Art of Scientific Computing, 2nd ed. New York: Cambridge Univ. Press, 1992.
29. K. S. Narendra and S. Mukhopadhyay, "Adaptive control of nonlinear multivariable systems using neural networks," Neural Netw., vol. 7, no. 5, pp. 737-752, 1994.
30. J. C. Spall and J. A. Cristion, "A neural network controller for systems with unmodeled dynamics with applications to wastewater treatment," IEEE Trans. Syst., Man, Cybern. B, Cybern., vol. 27, no. 3, pp. 369-375, Jun. 1997.
31. N. N. Schraudolph, "Fast curvature matrix-vector products for second-order gradient descent," Neural Comput., vol. 14, pp. 1723-1738, 2002.
32. D. V. Prokhorov, "Adaptive critic designs and their applications," Ph.D. dissertation, Dept. Electr. Eng., Texas Tech Univ., Lubbock, TX, 1997.
33. D. V. Prokhorov and D. C. Wunsch, "Adaptive critic designs," IEEE Trans. Neural Netw., vol. 8, no. 5, pp. 997-1007, Sep. 1997.
34. D. P. Bertsekas and J. N. Tsitsiklis, Neurodynamic Programming. Belmont, MA: Athena Scientific, 1996.
35. P. Dupont, V. Hayward, and B. A. Altpeter, "Single state elastoplastic friction models," IEEE Trans. Autom. Control, vol. 47, no. 5, pp. 787-792, May 2002.
36. D. Hermance, "Toyota hybrid system," in SAE TOPTEC Conf. Proc., Albany, NY, May 1999.
37. I. Tyukin, D. Prokhorov, and V. Terekhov, "Adaptive control with non-convex parameterization," IEEE Trans. Autom. Control, vol. 48, no. 4, pp. 554-567, Apr. 2003.
38. N. Barabanov and D. Prokhorov, "A new method for stability analysis of nonlinear discrete-time systems," IEEE Trans. Autom. Control, vol. 48, no. 12, pp. 2250-2255, Dec. 2003.