Neural network‐based optimal tracking control for partially unknown discrete‐time non‐linear systems using reinforcement learning
Abstract Otimal tracking control of discrete‐time non‐linear systems is investigated in this paper. The system drift dynamics is unknown in this investigation. Firstly, in the light of the discrete‐time non‐linear systems and reference signal, an augmented system is constructed. Optimal tracking con...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-01-01
|
| Series: | IET Control Theory & Applications |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/cth2.12037 |
| _version_ | 1811223316057292800 |
|---|---|
| author | Jingang Zhao Prateek Vishal |
| author_facet | Jingang Zhao Prateek Vishal |
| author_sort | Jingang Zhao |
| collection | DOAJ |
| description | Abstract Otimal tracking control of discrete‐time non‐linear systems is investigated in this paper. The system drift dynamics is unknown in this investigation. Firstly, in the light of the discrete‐time non‐linear systems and reference signal, an augmented system is constructed. Optimal tracking control problem of original non‐linear systems is thus transformed into solving optimal regulation problem of the augmented systems. The solution to optimal regulation problem can be found by solving its Hamilton–Jacobi–Bellman (HJB) equation. To solve the HJB equation, a new critic‐actor neural network (NN) structure‐based online reinforcement learning (RL) scheme is proposed to learn the solution of HJB equation while the corresponding optimal control input that minimizes the HJB equation is calculated in a forward‐in‐time manner without requiring any value, policy iterations and the system drift dynamics. The Uniformly Ultimately Boundedness (UUB) of NN weight errors and closed‐loop augmented system states are provided via the Lyapunov theory. Finally, simulation results are given to validate the proposed scheme. |
| first_indexed | 2024-04-12T08:30:49Z |
| format | Article |
| id | doaj.art-5b2c988bcb1e48d286692b241c39262e |
| institution | Directory Open Access Journal |
| issn | 1751-8644 1751-8652 |
| language | English |
| last_indexed | 2024-04-12T08:30:49Z |
| publishDate | 2021-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Control Theory & Applications |
| spelling | doaj.art-5b2c988bcb1e48d286692b241c39262e2022-12-22T03:40:13ZengWileyIET Control Theory & Applications1751-86441751-86522021-01-0115226027110.1049/cth2.12037Neural network‐based optimal tracking control for partially unknown discrete‐time non‐linear systems using reinforcement learningJingang Zhao0Prateek Vishal1College of Information and Control Engineering Weifang University 5147 Dongfeng East Street Weifang Shandong 261061 ChinaCollege of Engineering The Ohio State University Columbus OhioAbstract Otimal tracking control of discrete‐time non‐linear systems is investigated in this paper. The system drift dynamics is unknown in this investigation. Firstly, in the light of the discrete‐time non‐linear systems and reference signal, an augmented system is constructed. Optimal tracking control problem of original non‐linear systems is thus transformed into solving optimal regulation problem of the augmented systems. The solution to optimal regulation problem can be found by solving its Hamilton–Jacobi–Bellman (HJB) equation. To solve the HJB equation, a new critic‐actor neural network (NN) structure‐based online reinforcement learning (RL) scheme is proposed to learn the solution of HJB equation while the corresponding optimal control input that minimizes the HJB equation is calculated in a forward‐in‐time manner without requiring any value, policy iterations and the system drift dynamics. The Uniformly Ultimately Boundedness (UUB) of NN weight errors and closed‐loop augmented system states are provided via the Lyapunov theory. Finally, simulation results are given to validate the proposed scheme.https://doi.org/10.1049/cth2.12037Optimisation techniquesInterpolation and function approximation (numerical analysis)Linear control systemsControl system analysis and synthesis methodsStability in control theoryOptimal control |
| spellingShingle | Jingang Zhao Prateek Vishal Neural network‐based optimal tracking control for partially unknown discrete‐time non‐linear systems using reinforcement learning IET Control Theory & Applications Optimisation techniques Interpolation and function approximation (numerical analysis) Linear control systems Control system analysis and synthesis methods Stability in control theory Optimal control |
| title | Neural network‐based optimal tracking control for partially unknown discrete‐time non‐linear systems using reinforcement learning |
| title_full | Neural network‐based optimal tracking control for partially unknown discrete‐time non‐linear systems using reinforcement learning |
| title_fullStr | Neural network‐based optimal tracking control for partially unknown discrete‐time non‐linear systems using reinforcement learning |
| title_full_unstemmed | Neural network‐based optimal tracking control for partially unknown discrete‐time non‐linear systems using reinforcement learning |
| title_short | Neural network‐based optimal tracking control for partially unknown discrete‐time non‐linear systems using reinforcement learning |
| title_sort | neural network based optimal tracking control for partially unknown discrete time non linear systems using reinforcement learning |
| topic | Optimisation techniques Interpolation and function approximation (numerical analysis) Linear control systems Control system analysis and synthesis methods Stability in control theory Optimal control |
| url | https://doi.org/10.1049/cth2.12037 |
| work_keys_str_mv | AT jingangzhao neuralnetworkbasedoptimaltrackingcontrolforpartiallyunknowndiscretetimenonlinearsystemsusingreinforcementlearning AT prateekvishal neuralnetworkbasedoptimaltrackingcontrolforpartiallyunknowndiscretetimenonlinearsystemsusingreinforcementlearning |