Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/93639
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Tang, D. | - |
dc.contributor.author | Chen, L. | - |
dc.contributor.author | Tian, Z. | - |
dc.date.issued | 2015 | - |
dc.identifier.citation | Proceedings of the 2015 IEEE China Summit & International Conference on Signal and Information processing, 2015, pp.792-796 | - |
dc.identifier.isbn | 9781479919475 | - |
dc.identifier.uri | http://hdl.handle.net/2440/93639 | - |
dc.description | IEEE Catalog Number: CFP15SIP-USB | - |
dc.description.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. | - |
dc.description.statementofresponsibility | Difan Tang, Lei Chen, and Zhao Feng Tian | - |
dc.language.iso | en | - |
dc.publisher | Institute of Electrical and Electronics Engineers (IEEE) | - |
dc.rights | © 2015 IEEE | - |
dc.source.uri | http://dx.doi.org/10.1109/chinasip.2015.7230513 | - |
dc.subject | machine learning; neural network; policy iteration; optimal control; nonlinear system | - |
dc.title | Neural-network based online policy iteration for continuous-time infinite-horizon optimal control of nonlinear systems | - |
dc.type | Conference paper | - |
dc.contributor.conference | 3rd IEEE China Summit & International Conference on Signal and Information processing (ChinaSIP 2015) (12 Jul 2015 - 15 Jul 2015 : Chengdu, China) | - |
dc.identifier.doi | 10.1109/ChinaSIP.2015.7230513 | - |
pubs.publication-status | Published | - |
dc.identifier.orcid | Tang, D. [0000-0002-7143-0441] | - |
dc.identifier.orcid | Chen, L. [0000-0002-2269-2912] | - |
dc.identifier.orcid | Tian, Z. [0000-0001-9847-6004] | - |
Appears in Collections: | Aurora harvest 7 Mechanical Engineering publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
hdl_93639.pdf | Accepted version | 457.16 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.