Robustness and Fault Tolerance Issues In Artificial Neural Network Based Robotic Control Applications
In control theory, in order to meet certain performance objectives with less precise advanced knowledge of system dynamics, it is necessary to develop control algorithms with high levels of autonomy. Learning control systems are good examples of such highly autonomous controllers. Within this class of controllers, neurologically inspired control algorithms have been gaining much attention in recent years. Artificial Neural Network (ANN) based control algorithms have been successfully applied for the tracking control of nonlinear systems with unknown or changing dynamics [1, 2, 3]. There is also much research on the stability properties of these, rather unconventional, control algorithms [4, 5]. Performance of ANN based controllers is mainly due to these networks’ remarkable capabilities of approximating arbitrary nonlinear functions over compact spaces. Fault tolerance is also another much pronounced property of ANNs .
KeywordsArtificial Neural Networks learning control robotics fault tolerance robustness
Unable to display preview. Download preview PDF.
- 1.K. Ciliz and C. Işik, “Trajectory learning control of robotic manipulators using Neural Networks,” in IEEE International Symposium on Intelligent Control,(Fairfax, VA), pp. 536–540, 1990.Google Scholar
- 3.M. Kawato, “Computational schemes and neural network models for formation and control of multi-joint arm trajectory,” in Neural Networks for Control, pp. 197–228, MIT Press, 1990.Google Scholar
- 4.T. Yabuta and T. Yamada, “Possibility of neural networks controller for robot manipulators,” in IEEE International Conference on Decision and Control, (Honolulu, Hawaii), pp. 1686–1691, December 1990.Google Scholar
- 5.K. Ciliz and C. Işik, “Stability and convergence of neurologic model based robotic controllers,” in IEEE International Conference on Robotics and Automation, (Nice, France), pp. 2051–2056, May 1992.Google Scholar
- 7.K. Ciliz, Artificial Neural Network Based Control of Nonlinear Systems With Application to Robotic Manipulators. PhD thesis, Syracuse University, Electrical Engineering Department, 1990.Google Scholar
- 10.G. Cybenko, “Approximations by superpositions of a sigmoidal function,” tech. rep., University of Illinois, Center for Supercomputer Research and Development, Urbana, IL, 1989.Google Scholar
- 11.J. Craig, Adaptive Control of Mechanical Manipulators. Reading, Massachusetts: Addison-Wesley, 1989.Google Scholar
- 12.M. Vidyasagar, Nonlinear Systems Analysis. New Jersey: Prentice Hall, 1978.Google Scholar