Adaptive feedback control by constrained approximate dynamic programming.

Published

Journal Article

A constrained approximate dynamic programming (ADP) approach is presented for designing adaptive neural network (NN) controllers with closed-loop stability and performance guarantees. Prior knowledge of the linearized equations of motion is used to guarantee that the closed-loop system meets performance and stability objectives when the plant operates in a linear parameter-varying (LPV) regime. In the presence of unmodeled dynamics or failures, the NN controller adapts to optimize its performance online, whereas constrained ADP guarantees that the LPV baseline performance is preserved at all times. The effectiveness of an adaptive NN flight controller is demonstrated for simulated control failures, parameter variations, and near-stall dynamics.

Full Text

Duke Authors

Cited Authors

  • Ferrari, S; Steck, JE; Chandramohan, R

Published Date

  • August 2008

Published In

Volume / Issue

  • 38 / 4

Start / End Page

  • 982 - 987

PubMed ID

  • 18632388

Pubmed Central ID

  • 18632388

Electronic International Standard Serial Number (EISSN)

  • 1941-0492

International Standard Serial Number (ISSN)

  • 1083-4419

Digital Object Identifier (DOI)

  • 10.1109/tsmcb.2008.924140

Language

  • eng