Performance of Nonlinear Approximate Adaptive Controllers

  • ID: 2181233
  • Book
  • 412 Pages
  • John Wiley and Sons Ltd
1 of 4
In recent years there has been wide interest in nonlinear adaptive control using function approximator models, either for tracking or regulation. Such techniques are often described as ′neural network based control′. In this book, the authors present a critical evaluation of the approximate model philosophy and its setting, showing situations in which its designs can be expected to surpass rival algorithms.

Describing complex concepts with a variety of theoretical and practical illustrations, this book also:

  • Develops a comprehensive set of performance based adaptive control results
  • Provides a constructive framework for estimating both upper and lower bounds of performance cost functionals
  • Presents theoretical principles and a mathematically well–founded introduction to the area of ′intelligent control′

Featuring a toolkit that allows quantitative comparisons between competing control designs, Performance of Nonlinear Approximate Adaptive Controllers will prove an invaluable reference for control practitioners and theorists, AI researchers, applied mathematicians and graduate students in adaptive control and stability.

Note: Product cover images may vary from those shown
2 of 4
Preface.

Introduction.

Approximation Theory.

Uncertainty Modelling, Control Design and System Performance.

The Chain of Integrators.

Function Approximator Designs for the Integrator Chain.

Resolution Divergence.

Resolution Scaling.

Strict Feedback Systems.

Output Feedback Control.

Comparison to Alternative Designs.

Conclusions and Outlook.

Appendix A: Lyapunov′s Direct Method.

Appendix B: Functional Bounds from System Identification.

References.

Index.

Note: Product cover images may vary from those shown
3 of 4

Loading
LOADING...

4 of 4
Mark French
Csaba Szepesvári
Eric Rogers
Note: Product cover images may vary from those shown
5 of 4
Note: Product cover images may vary from those shown
Adroll
adroll