Online Adaptive Policy Learning Algorithm for H State Feedback Control of Unknown Affine Nonlinear Discrete-Time Systems

The problem of H ∞ state feedback control of affine nonlinear discrete-time systems with unknown dynamics is investigated in this paper. An online adaptive policy learning algorithm (APLA) based on adaptive dynamic programming (ADP) is proposed for learning in real-time the solution to the Hamilton-...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE transactions on cybernetics Ročník 44; číslo 12; s. 2706 - 2718
Hlavní autori: Zhang, Huaguang, Qin, Chunbin, Jiang, Bin, Luo, Yanhong
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: United States IEEE 01.12.2014
Predmet:
Adaptive dynamic programming
Adaptive systems
Algorithms
Artificial Intelligence
Computer Simulation
Discrete-time systems
Dynamic programming
Feedback
H infinity control
H∞ control
Models, Theoretical
Neural networks
nonlinear discrete-time system
Nonlinear Dynamics
Pattern Recognition, Automated - methods
zero-sum game
(H_{\infty }\) control
nonlinear discrete-time system
Adaptive dynamic programming
zero-sum game
neural networks
ISSN:2168-2267, 2168-2275, 2168-2275
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:The problem of H ∞ state feedback control of affine nonlinear discrete-time systems with unknown dynamics is investigated in this paper. An online adaptive policy learning algorithm (APLA) based on adaptive dynamic programming (ADP) is proposed for learning in real-time the solution to the Hamilton-Jacobi-Isaacs (HJI) equation, which appears in the H ∞ control problem. In the proposed algorithm, three neural networks (NNs) are utilized to find suitable approximations of the optimal value function and the saddle point feedback control and disturbance policies. Novel weight updating laws are given to tune the critic, actor, and disturbance NNs simultaneously by using data generated in real-time along the system trajectories. Considering NN approximation errors, we provide the stability analysis of the proposed algorithm with Lyapunov approach. Moreover, the need of the system input dynamics for the proposed algorithm is relaxed by using a NN identification scheme. Finally, simulation examples show the effectiveness of the proposed algorithm.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:2168-2267
2168-2275
2168-2275
DOI:10.1109/TCYB.2014.2313915