Abstract
A hierarchical network of neural network planning and control is employed to successfully accomplish a task such as grasping in a cluttered real world environment. In order for the individual robot joint controllers to follow their specific reference commands, information is shared with other neural network controllers and planners within the hierarchy. Each joint controller is initialized with weights that will acceptably control given a change in any of several crucial parameters across a broad operating range. When increased accuracy is needed as parameters drift, the diagnostic node fuzzy supervisor interprets the controller network's diagnostic outputs and transitions the weights to a closest fit specificchild controller. Future reference commands are in turn influenced by the diagnostic outputs of every robot joint neural network controller. The neural network controller and diagnostics are demonstrated for linear and nonlinear plants.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Fijany, A. and Bejczy, A. K.: A class of parallel algorithms for computation of the manipulator inertia matrix,IEEE Trans. on Robotics and Automation 5 (1989), 600–615.
Kuperstein, M.: Adaptive visual motor coordination in multijoint robots using parallel architecture, inProc. IEEE Int. Conf. on Robotics and Automation, 1987, pp. 1595–1602.
Massone, L. and Bizzi, E.: Generation of limb trajectories with a sequential network, inIEEE Int. Conf. on Neural Networks, Vol 2, Sheraton Harbor Island, San Diego, CA, July 24–27, 1988, p. 345.
Yeung, Dit-yan: Handling Dimensionality and Nonlinearity in Connectionist Learning, PhD Thesis, University of Southern California, December 1989.
Miller, D. and Davison, E.: Adaptive control of a family of plants, in D. Hinrichsen and B. Martensson (eds),Control of Uncertain Systems, Birkhauser, Boston, 1990, pp. 197–219.
Elsley, R. K.: A learning architecture for control based on back-propagation neural network,IEEE Int. Conf. on Neural Networks, Vol. 2, Sheraton Harbor Island, San Diego, CA, July 24–27, 1988, p. 587.
Josin, G., Charney, D., and White, D.: Robot control using neural networks,IEEE Int. Conf. on Neural Networks, Vol. 2, Sheraton Harbor Island, San Diego, CA, July 24–27, 1988, p. 625.
Suddarth, S., Sutton, S., and Holden, A.: A symbolic-neural method for solving control problems, inIEEE Int. Conf. on Neural Networks, Vol. 1, Sheraton Harbor Island, San Diego, CA, July 24–27, 1988, p. 516.
Kawato, M., Uno, Y., Isobe, M., and Suzuki, R.: A hierarchical model for voluntary movement and its application to robotics, inIEEE Int. Conf. on Neural Networks, San Diego, CA, 1987, pp. 573–582.
Miyamoto, H., Kawato, M., Setoyama, T., and Suzuki, R.: Feedback-error-learning neural network for trajectory control of a robotic manipulator,Neural Networks 1 (1988), 251–265.
Bassi, D. and Bekey, G.: Decomposition of neural network models of robot dynamics: a feasibility study, in W. Webster, (ed.),Simulation and AI, Society for Computer Simulation, 1989.
Wang, H., Lee, T. T., and Gruver, W. A.: A neuromorphic controller for a three-link biped robot,IEEE Trans. on Systems, Man, and Cybernetics 22(1) (January/February 1992).
Yamaguchi, T., Goto, K., Yoshida, M., and Mita, T.: Fuzzy associative memory system and its applications to a helicopter control, in T. Terano, M. Sugeno, M. Mukaidono, and K. Shigemasu (eds),Fuzzy Engineering Toward Human Friendly Systems, IOS Press, Washington, DC, 1992.
Simons, A.: Robotic Trajectory Control Employing Anyanet Neural Architecture, Master's Thesis, Rensselaer Polytechnic Institute, 1992.
Goldberg, K. and Perlmutter, B.: Using a Neural Network to Learn the Dynamics of the CMU Direct-drive Arm II, Report CMU-CS-88-160, Department of Computer Science, Carnegie Mellon University, 1988.
Jordan, M. and Jacobs, R.: Hierarchical mixtures of experts and the EM algorithm,Neural Computation (1993).
Pomerleau, D. A.: Input reconstruction reliability estimation, in C. Giles, S. Hanson and J. Cowan (eds),Advances in Neural Information Processing Systems, Vol. 5, Morgan Kaufmann, San Mateo, CA, 1993.
Kornhauser, A. L. and Huber, E. C.: Lateral control of highway vehicles using image processing and neural networks,Proc. of the 2nd Regional Conf. on Control Systems NJIT, New Jersey, August 1993.
Kazlas, P., Monsen, P. and LeBlanc, M.: Neural network-based helicopter gearbox health monitoring system,Neural Networks for Signal Processing III, Proc. 1993 IEEE-SP Workshop, Linthicum Heights, Maryland, September 6–9, 1993.
Tascillo, A., Skormin, V., and Bourbakis, N.: Neurofuzzy grasp control of a robotic hand, in Kamn, Kuhn, Yoon, Chellappa, and Kung (eds),Neural Networks for Signal Processing III, Proc. 1993 IEEE-SP Workshop, September 1993, pp. 507–516.
Tascillo, A. and Skormin, V.: Neural adaptive control of systems with drifting parameters, in Mozer, Smolensky, Touretsky, Elman, and Weigend (eds),Proc. 1993 Connectionist Models Summer School, 1993, pp. 280–287.
Yamada, T. and Yabuta, T.: Neural network controller using autotuning method for nonlinear functions,IEEE Trans. on Neural Networks 3(4) (July 1992).
Kanojia, C.: Design and Control of a Three-Fingered Hand Based on the Anthropomorphic Model, M. S. Thesis, Northeastern University, Boston, Massachusetts, June 1993.
Tarn, T. J., Bejczy, A. K., Marth, G. T., and Ramadorai, A. K.: Kinematic Characterization of the PUMA 560 Manipulator, Robotics Laboratory Report SSM-RL-92-15, Department of Systems Science and Mathematics, Washington University, Saint Louis, Missouri, December 1991.
Tarn, T. J., Bejczy, A. K., Marth, G. T. and Ramadorai, A. K.: Performance comparison of four manipulator servo schemes,IEEE Control Systems, February 1993.
Armstrong, B., Khatib, O., and Burdick, J.: The explicit dynamic model and inertial parameters of the PUMA 560 Arm,IEEE International Conference on Robotics and Automation, San Francisco, CA, 1986.
Kuo, Benjamin C.:Automatic Control Systems, Prentice-Hall, Englewood Cliffs, NJ, 1991.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Tascillo, A. Diagnostic neural adaptive control of drifting systems. J Intell Robot Syst 14, 303–321 (1995). https://doi.org/10.1007/BF01258354
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/BF01258354