Direct adaptive control using single network adaptive critic

Swagat Kumar; Radhakant Padhi; Laxmidhar Behera

doi:10.1109/SYSOSE.2007.4304249

Direct adaptive control using single network adaptive critic

Swagat Kumar, Radhakant Padhi, Laxmidhar Behera

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Chapter › peer-review

9 Citations (Scopus)

Abstract

An optimal control law for a general nonlinear system can be obtained by solving Hamilton-Jacobi-Bellman equation. However, it is difficult to obtain an analytical solution of this equation. In this paper, we propose a direct adaptive control method for affine systems where the optimal value function is approximated using a critic network and the weight update law is derived so as to satisfy the HJB equation. This provides an alternative method to solve the HJB equation in real-time and thus paves the way for introducing some notion of optimality to direct adaptive control paradigm. The efficacy of the scheme is demonstrated for a linearized mass-spring-damper system and its performance is compared with that of LQR. ©2007 IEEE.

Original language	English
Title of host publication	2007 IEEE International Conference on System of Systems Engineering, SOSE
DOIs	https://doi.org/10.1109/SYSOSE.2007.4304249
Publication status	Published - 2007
Event	2007 IEEE International Conference on System of Systems Engineering - San Antonio, Texas, United States Duration: 16 Apr 2007 → 18 Apr 2007

Publication series

Name	2007 IEEE International Conference on System of Systems Engineering, SOSE

Conference

Conference	2007 IEEE International Conference on System of Systems Engineering
Country/Territory	United States
City	San Antonio, Texas
Period	16/04/07 → 18/04/07

Access to Document

10.1109/SYSOSE.2007.4304249

Cite this

@inbook{69eb6644e095475e93799cdfa90d0874,

title = "Direct adaptive control using single network adaptive critic",

abstract = "An optimal control law for a general nonlinear system can be obtained by solving Hamilton-Jacobi-Bellman equation. However, it is difficult to obtain an analytical solution of this equation. In this paper, we propose a direct adaptive control method for affine systems where the optimal value function is approximated using a critic network and the weight update law is derived so as to satisfy the HJB equation. This provides an alternative method to solve the HJB equation in real-time and thus paves the way for introducing some notion of optimality to direct adaptive control paradigm. The efficacy of the scheme is demonstrated for a linearized mass-spring-damper system and its performance is compared with that of LQR. {\textcopyright}2007 IEEE.",

author = "Swagat Kumar and Radhakant Padhi and Laxmidhar Behera",

year = "2007",

doi = "10.1109/SYSOSE.2007.4304249",

language = "English",

isbn = "1424411602",

series = "2007 IEEE International Conference on System of Systems Engineering, SOSE",

booktitle = "2007 IEEE International Conference on System of Systems Engineering, SOSE",

note = " 2007 IEEE International Conference on System of Systems Engineering ; Conference date: 16-04-2007 Through 18-04-2007",

}

Kumar, S, Padhi, R & Behera, L 2007, Direct adaptive control using single network adaptive critic. in 2007 IEEE International Conference on System of Systems Engineering, SOSE. 2007 IEEE International Conference on System of Systems Engineering, SOSE, 2007 IEEE International Conference on System of Systems Engineering, San Antonio, Texas, United States, 16/04/07. https://doi.org/10.1109/SYSOSE.2007.4304249

TY - CHAP

T1 - Direct adaptive control using single network adaptive critic

AU - Kumar, Swagat

AU - Padhi, Radhakant

AU - Behera, Laxmidhar

PY - 2007

Y1 - 2007

N2 - An optimal control law for a general nonlinear system can be obtained by solving Hamilton-Jacobi-Bellman equation. However, it is difficult to obtain an analytical solution of this equation. In this paper, we propose a direct adaptive control method for affine systems where the optimal value function is approximated using a critic network and the weight update law is derived so as to satisfy the HJB equation. This provides an alternative method to solve the HJB equation in real-time and thus paves the way for introducing some notion of optimality to direct adaptive control paradigm. The efficacy of the scheme is demonstrated for a linearized mass-spring-damper system and its performance is compared with that of LQR. ©2007 IEEE.

AB - An optimal control law for a general nonlinear system can be obtained by solving Hamilton-Jacobi-Bellman equation. However, it is difficult to obtain an analytical solution of this equation. In this paper, we propose a direct adaptive control method for affine systems where the optimal value function is approximated using a critic network and the weight update law is derived so as to satisfy the HJB equation. This provides an alternative method to solve the HJB equation in real-time and thus paves the way for introducing some notion of optimality to direct adaptive control paradigm. The efficacy of the scheme is demonstrated for a linearized mass-spring-damper system and its performance is compared with that of LQR. ©2007 IEEE.

UR - http://www.mendeley.com/research/direct-adaptive-control-using-single-network-adaptive-critic

U2 - 10.1109/SYSOSE.2007.4304249

DO - 10.1109/SYSOSE.2007.4304249

M3 - Chapter

SN - 1424411602

T3 - 2007 IEEE International Conference on System of Systems Engineering, SOSE

BT - 2007 IEEE International Conference on System of Systems Engineering, SOSE

T2 - 2007 IEEE International Conference on System of Systems Engineering

Y2 - 16 April 2007 through 18 April 2007

ER -

Direct adaptive control using single network adaptive critic

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this