Back to Search
Start Over
Neurodynamic Programming and Zero-Sum Games for Constrained Control Systems.
- Source :
- IEEE Transactions on Neural Networks; Jul2008, Vol. 19 Issue 7, p1243-1252, 10p
- Publication Year :
- 2008
-
Abstract
- Abstract-In this paper, neural networks are used along with two-player policy iterations to solve for the feedback strategies of a continuous-time zero-sum game that appears in L<subscript>2</subscript>-gain optimal control, suboptimal H<subscript>∞</subscript> control, of nonlinear systems affine in input with the control policy having saturation constraints. The result is a closed-form representation, on a prescribed compact set chosen a priori, of the feedback strategies and the value function that solves the associated Hamilton-Jacobi-Isaacs (HJI) equation. The closed-loop stability, L<subscript>2</subscript>-gain disturbance attenuation of the neural network saturated control feedback strategy, and uniform convergence results are proven. Finally, this approach is applied to the rotational/translational actuator (RTAC) nonlinear benchmark problem under actuator saturation, offering guaranteed stability and disturbance attenuation. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 10459227
- Volume :
- 19
- Issue :
- 7
- Database :
- Complementary Index
- Journal :
- IEEE Transactions on Neural Networks
- Publication Type :
- Academic Journal
- Accession number :
- 33411414
- Full Text :
- https://doi.org/10.1109/TNN.2008.2000204