Neural-network based online policy iteration for continuous-time infinite-horizon optimal control of nonlinear systems

Files

hdl_93639.pdf (457.16 KB)
  (Accepted version)

Date

2015

Authors

Tang, D.
Chen, L.
Tian, Z.

Editors

Advisors

Journal Title

Journal ISSN

Volume Title

Type:

Conference paper

Citation

Proceedings of the 2015 IEEE China Summit & International Conference on Signal and Information processing, 2015, pp.792-796

Statement of Responsibility

Difan Tang, Lei Chen, and Zhao Feng Tian

Conference Name

3rd IEEE China Summit & International Conference on Signal and Information processing (ChinaSIP 2015) (12 Jul 2015 - 15 Jul 2015 : Chengdu, China)

Abstract

A new policy-iteration algorithm based on neural networks (NNs) is proposed in this paper to synthesize optimal control laws online for continuous-time nonlinear systems. Latest advances in this field have enabled synchronous policy iteration but require an additional tuning loop or a logic switch mechanism to maintain system stability. A new algorithm is thus derived in this paper to address this limitation. The optimal control law is found by solving the Hamilton-Jacobi- Bellman (HJB) equation for the associated value function via synchronous policy iteration in a critic-actor configuration. As a major contribution, a new form of NN approximation for the value function is proposed, offering the closed-loop system asymptotic stability without additional tuning scheme or logic switch mechanism. As a second contribution, an extended Kalman filter is introduced to estimate the critic NN parameters for fast convergence. The efficacy of the new algorithm is verified by simulations.

School/Discipline

Dissertation Note

Provenance

Description

IEEE Catalog Number: CFP15SIP-USB

Access Status

Rights

© 2015 IEEE

License

Grant ID

Call number

Persistent link to this record