Performance improvement for formation-keeping control using a neural network HJI approach

Erfu Yang, Dongbing Gu, Huosheng Hu

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

This article deals with the performance improvement issues for nonlinear formation-keeping control systems by using a neural network HamiltonJacobi-Isaacs (HJI) approach. The associated HJI equation is successively solved by approximating its value function with a neural network and the successive Galerkin approximation (SGA) method. The neural network is also used to approximate the control laws achieved by successive policy iterations rather than data-based training. As a case study, we present the application of this approach to the nonlinear optimal (nearly) and robust formation control of multiple autonomous underwater robotic vehicles (AURVs). A nonlinear change of coordinates and feedback is made such that the SGA algorithm developed for time-invariant nonlinear systems can be implemented to the formation control system under consideration in this article. The formation-keeping performance is significantly improved by solving the associated HJI equation with the SGA algorithm. The synthesized formation-keeping controller, which is expressed by a neural network, also has nearly optimal and robust properties in comparison with the original control law designed by taking advantage of Lyapunov’s direct method. Simulation results are presented to demonstrate the improved formation-keeping performance of a leader-follower formation of AURVs in nonholonomic chained form.
LanguageEnglish
Title of host publicationTrends in Neural Computation
EditorsKe Chen, Lipo Wang
Pages419-442
Number of pages24
DOIs
Publication statusPublished - 2007

Publication series

NameStudies in Computational Intelligence
Volume35
ISSN (Print)1860-949X

Fingerprint

Neural networks
Approximation algorithms
Robotics
Control systems
Nonlinear systems
Feedback
Controllers

Keywords

  • computational engineering
  • artificial intelligence
  • performance improvement

Cite this

Yang, E., Gu, D., & Hu, H. (2007). Performance improvement for formation-keeping control using a neural network HJI approach. In K. Chen, & L. Wang (Eds.), Trends in Neural Computation (pp. 419-442). (Studies in Computational Intelligence; Vol. 35). https://doi.org/10.1007/978-3-540-36122-0_17
Yang, Erfu ; Gu, Dongbing ; Hu, Huosheng. / Performance improvement for formation-keeping control using a neural network HJI approach. Trends in Neural Computation. editor / Ke Chen ; Lipo Wang. 2007. pp. 419-442 (Studies in Computational Intelligence).
@inbook{fdb5efd3ceb74ea9984049319461eeba,
title = "Performance improvement for formation-keeping control using a neural network HJI approach",
abstract = "This article deals with the performance improvement issues for nonlinear formation-keeping control systems by using a neural network HamiltonJacobi-Isaacs (HJI) approach. The associated HJI equation is successively solved by approximating its value function with a neural network and the successive Galerkin approximation (SGA) method. The neural network is also used to approximate the control laws achieved by successive policy iterations rather than data-based training. As a case study, we present the application of this approach to the nonlinear optimal (nearly) and robust formation control of multiple autonomous underwater robotic vehicles (AURVs). A nonlinear change of coordinates and feedback is made such that the SGA algorithm developed for time-invariant nonlinear systems can be implemented to the formation control system under consideration in this article. The formation-keeping performance is significantly improved by solving the associated HJI equation with the SGA algorithm. The synthesized formation-keeping controller, which is expressed by a neural network, also has nearly optimal and robust properties in comparison with the original control law designed by taking advantage of Lyapunov’s direct method. Simulation results are presented to demonstrate the improved formation-keeping performance of a leader-follower formation of AURVs in nonholonomic chained form.",
keywords = "computational engineering, artificial intelligence, performance improvement",
author = "Erfu Yang and Dongbing Gu and Huosheng Hu",
year = "2007",
doi = "10.1007/978-3-540-36122-0_17",
language = "English",
isbn = "978-3-540-36121-3",
series = "Studies in Computational Intelligence",
pages = "419--442",
editor = "Ke Chen and Lipo Wang",
booktitle = "Trends in Neural Computation",

}

Yang, E, Gu, D & Hu, H 2007, Performance improvement for formation-keeping control using a neural network HJI approach. in K Chen & L Wang (eds), Trends in Neural Computation. Studies in Computational Intelligence, vol. 35, pp. 419-442. https://doi.org/10.1007/978-3-540-36122-0_17

Performance improvement for formation-keeping control using a neural network HJI approach. / Yang, Erfu; Gu, Dongbing; Hu, Huosheng.

Trends in Neural Computation. ed. / Ke Chen; Lipo Wang. 2007. p. 419-442 (Studies in Computational Intelligence; Vol. 35).

Research output: Chapter in Book/Report/Conference proceedingChapter

TY - CHAP

T1 - Performance improvement for formation-keeping control using a neural network HJI approach

AU - Yang, Erfu

AU - Gu, Dongbing

AU - Hu, Huosheng

PY - 2007

Y1 - 2007

N2 - This article deals with the performance improvement issues for nonlinear formation-keeping control systems by using a neural network HamiltonJacobi-Isaacs (HJI) approach. The associated HJI equation is successively solved by approximating its value function with a neural network and the successive Galerkin approximation (SGA) method. The neural network is also used to approximate the control laws achieved by successive policy iterations rather than data-based training. As a case study, we present the application of this approach to the nonlinear optimal (nearly) and robust formation control of multiple autonomous underwater robotic vehicles (AURVs). A nonlinear change of coordinates and feedback is made such that the SGA algorithm developed for time-invariant nonlinear systems can be implemented to the formation control system under consideration in this article. The formation-keeping performance is significantly improved by solving the associated HJI equation with the SGA algorithm. The synthesized formation-keeping controller, which is expressed by a neural network, also has nearly optimal and robust properties in comparison with the original control law designed by taking advantage of Lyapunov’s direct method. Simulation results are presented to demonstrate the improved formation-keeping performance of a leader-follower formation of AURVs in nonholonomic chained form.

AB - This article deals with the performance improvement issues for nonlinear formation-keeping control systems by using a neural network HamiltonJacobi-Isaacs (HJI) approach. The associated HJI equation is successively solved by approximating its value function with a neural network and the successive Galerkin approximation (SGA) method. The neural network is also used to approximate the control laws achieved by successive policy iterations rather than data-based training. As a case study, we present the application of this approach to the nonlinear optimal (nearly) and robust formation control of multiple autonomous underwater robotic vehicles (AURVs). A nonlinear change of coordinates and feedback is made such that the SGA algorithm developed for time-invariant nonlinear systems can be implemented to the formation control system under consideration in this article. The formation-keeping performance is significantly improved by solving the associated HJI equation with the SGA algorithm. The synthesized formation-keeping controller, which is expressed by a neural network, also has nearly optimal and robust properties in comparison with the original control law designed by taking advantage of Lyapunov’s direct method. Simulation results are presented to demonstrate the improved formation-keeping performance of a leader-follower formation of AURVs in nonholonomic chained form.

KW - computational engineering

KW - artificial intelligence

KW - performance improvement

UR - http://www.scopus.com/inward/record.url?scp=33751004700&partnerID=8YFLogxK

U2 - 10.1007/978-3-540-36122-0_17

DO - 10.1007/978-3-540-36122-0_17

M3 - Chapter

SN - 978-3-540-36121-3

T3 - Studies in Computational Intelligence

SP - 419

EP - 442

BT - Trends in Neural Computation

A2 - Chen, Ke

A2 - Wang, Lipo

ER -

Yang E, Gu D, Hu H. Performance improvement for formation-keeping control using a neural network HJI approach. In Chen K, Wang L, editors, Trends in Neural Computation. 2007. p. 419-442. (Studies in Computational Intelligence). https://doi.org/10.1007/978-3-540-36122-0_17