CS545_Lecture_16

CS545_Lecture_16 - CS545—Contents XVI Adaptive Control...

Info iconThis preview shows pages 1–6. Sign up to view the full content.

View Full Document Right Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: CS545—Contents XVI Adaptive Control Model Reference Adaptive Control Self-Tuning Regulators Linear Regression Recursive Least Squares Gradient Descent Feedback-Error Learning Reading Assignment for Next Class See http://www-clmc.usc.edu/~cs545 The Adaptive Control Problem Characterize the desired behavior of the closed loop system Determine a suitable control law with adjustable parameters Find a mechanism for adjusting the parameters Implement the control law Model-Reference Adaptive Control (Direct Learning) Performance is given to correspond to a particular reference model E.g. Adjustment of controller is done directly E.g., adjust controller parameter by gradient descent m ˙ ˙ x + b ˙ x + c = u Controller Robot Adjustment Mechanism Model x desired u y y desired adjustment Model-Reference Adaptive Control – Example Consider the generic control system For this example, make this an even simpler system Assume that f is unkown and needs to be estimated by a learning process. Thus, we can formulated a control law: Where we replaced f with a simple linear function x = f x ( ) + g x ( ) u x = f x ( ) + u u = − ˆ f x ( ) + x d − k x − x d ( ) = − x ˆ θ + x d − k x − x d ( ) Model-Reference Adaptive Control – Example The goal of model-reference adaptive control is to adjust the open parameter and the control law such that the system is ALWAYS stable The system dynamics are now Define errors Thus: x = x θ − x ˆ θ + x d − k x − x d ( ) x = x θ + x d + ke = x θ + e + ke e = − x θ − ke e = x d − x θ = θ − ˆ θ Model-Reference Adaptive...
View Full Document

{[ snackBarMessage ]}

Page1 / 17

CS545_Lecture_16 - CS545—Contents XVI Adaptive Control...

This preview shows document pages 1 - 6. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online