Adaptive Critics Design with Support Vector Machine for Spacecraft Finite-Horizon Optimal Control

Yunjoong Kim, Youdan Kim, Chandeok Park

Research output: Contribution to journalArticle

Abstract

In this study, an adaptive critics design based on a support vector machine (SVM) is adopted to design a finite-horizon optimal feedback controller. The adaptive critics design consists of actor and critic networks. The actor (control input) and critic (cost-to-go) network are trained off-line with respect to various initial states and final times within a finite step. Using the well-trained actor-critic, the near-optimal feedback control solution can be obtained online. In the process of applying SVM to the adaptive critics, an adequate kernel function and parameters depending on the kernel function must be selected. In this study, a polynomial function and radial basis function are used for the SVM kernel function to implement the algorithm. A minimum control effort problem with final constraints for spacecraft rendezvous is considered to demonstrate the performance of the proposed the developed algorithm with respect to each kernel function and to show its potential for designing an optimal controller.

Original languageEnglish
Article number04018111
JournalJournal of Aerospace Engineering
Volume32
Issue number1
DOIs
Publication statusPublished - 2019 Jan 1

Fingerprint

Support vector machines
Spacecraft
Space rendezvous
Controllers
Feedback control
Polynomials
Feedback
Costs

All Science Journal Classification (ASJC) codes

  • Civil and Structural Engineering
  • Materials Science(all)
  • Aerospace Engineering
  • Mechanical Engineering

Cite this

@article{b2641717cf2d4d1fa9d17633954f6d41,
title = "Adaptive Critics Design with Support Vector Machine for Spacecraft Finite-Horizon Optimal Control",
abstract = "In this study, an adaptive critics design based on a support vector machine (SVM) is adopted to design a finite-horizon optimal feedback controller. The adaptive critics design consists of actor and critic networks. The actor (control input) and critic (cost-to-go) network are trained off-line with respect to various initial states and final times within a finite step. Using the well-trained actor-critic, the near-optimal feedback control solution can be obtained online. In the process of applying SVM to the adaptive critics, an adequate kernel function and parameters depending on the kernel function must be selected. In this study, a polynomial function and radial basis function are used for the SVM kernel function to implement the algorithm. A minimum control effort problem with final constraints for spacecraft rendezvous is considered to demonstrate the performance of the proposed the developed algorithm with respect to each kernel function and to show its potential for designing an optimal controller.",
author = "Yunjoong Kim and Youdan Kim and Chandeok Park",
year = "2019",
month = "1",
day = "1",
doi = "10.1061/(ASCE)AS.1943-5525.0000941",
language = "English",
volume = "32",
journal = "Journal of Aerospace Engineering",
issn = "0893-1321",
publisher = "American Society of Civil Engineers (ASCE)",
number = "1",

}

Adaptive Critics Design with Support Vector Machine for Spacecraft Finite-Horizon Optimal Control. / Kim, Yunjoong; Kim, Youdan; Park, Chandeok.

In: Journal of Aerospace Engineering, Vol. 32, No. 1, 04018111, 01.01.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Adaptive Critics Design with Support Vector Machine for Spacecraft Finite-Horizon Optimal Control

AU - Kim, Yunjoong

AU - Kim, Youdan

AU - Park, Chandeok

PY - 2019/1/1

Y1 - 2019/1/1

N2 - In this study, an adaptive critics design based on a support vector machine (SVM) is adopted to design a finite-horizon optimal feedback controller. The adaptive critics design consists of actor and critic networks. The actor (control input) and critic (cost-to-go) network are trained off-line with respect to various initial states and final times within a finite step. Using the well-trained actor-critic, the near-optimal feedback control solution can be obtained online. In the process of applying SVM to the adaptive critics, an adequate kernel function and parameters depending on the kernel function must be selected. In this study, a polynomial function and radial basis function are used for the SVM kernel function to implement the algorithm. A minimum control effort problem with final constraints for spacecraft rendezvous is considered to demonstrate the performance of the proposed the developed algorithm with respect to each kernel function and to show its potential for designing an optimal controller.

AB - In this study, an adaptive critics design based on a support vector machine (SVM) is adopted to design a finite-horizon optimal feedback controller. The adaptive critics design consists of actor and critic networks. The actor (control input) and critic (cost-to-go) network are trained off-line with respect to various initial states and final times within a finite step. Using the well-trained actor-critic, the near-optimal feedback control solution can be obtained online. In the process of applying SVM to the adaptive critics, an adequate kernel function and parameters depending on the kernel function must be selected. In this study, a polynomial function and radial basis function are used for the SVM kernel function to implement the algorithm. A minimum control effort problem with final constraints for spacecraft rendezvous is considered to demonstrate the performance of the proposed the developed algorithm with respect to each kernel function and to show its potential for designing an optimal controller.

UR - http://www.scopus.com/inward/record.url?scp=85053212652&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85053212652&partnerID=8YFLogxK

U2 - 10.1061/(ASCE)AS.1943-5525.0000941

DO - 10.1061/(ASCE)AS.1943-5525.0000941

M3 - Article

VL - 32

JO - Journal of Aerospace Engineering

JF - Journal of Aerospace Engineering

SN - 0893-1321

IS - 1

M1 - 04018111

ER -