Reinforcement Learning-Based Decentralized Safety Control for Constrained Interconnected Nonlinear Safety-Critical Systems
This paper addresses the problem of decentralized safety control (DSC) of constrained interconnected nonlinear safety-critical systems under reinforcement learning strategies, where asymmetric input constraints and security constraints are considered. To begin with, improved performance functions as...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-08-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1099-4300/25/8/1158 |
| _version_ | 1797584822253649920 |
|---|---|
| author | Chunbin Qin Yinliang Wu Jishi Zhang Tianzeng Zhu |
| author_facet | Chunbin Qin Yinliang Wu Jishi Zhang Tianzeng Zhu |
| author_sort | Chunbin Qin |
| collection | DOAJ |
| description | This paper addresses the problem of decentralized safety control (DSC) of constrained interconnected nonlinear safety-critical systems under reinforcement learning strategies, where asymmetric input constraints and security constraints are considered. To begin with, improved performance functions associated with the actuator estimates for each auxiliary subsystem are constructed. Then, the decentralized control problem with security constraints and asymmetric input constraints is transformed into an equivalent decentralized control problem with asymmetric input constraints using the barrier function. This approach ensures that safety-critical systems operate and learn optimal DSC policies within their safe global domains. Then, the optimal control strategy is shown to ensure that the entire system is uniformly ultimately bounded (UUB). In addition, all signals in the closed-loop auxiliary subsystem, based on Lyapunov theory, are uniformly ultimately bounded, and the effectiveness of the designed method is verified by practical simulation. |
| first_indexed | 2024-03-10T23:58:09Z |
| format | Article |
| id | doaj.art-432ab25079134737a22c80c20b20b041 |
| institution | Directory Open Access Journal |
| issn | 1099-4300 |
| language | English |
| last_indexed | 2024-03-10T23:58:09Z |
| publishDate | 2023-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Entropy |
| spelling | doaj.art-432ab25079134737a22c80c20b20b0412023-11-19T00:59:22ZengMDPI AGEntropy1099-43002023-08-01258115810.3390/e25081158Reinforcement Learning-Based Decentralized Safety Control for Constrained Interconnected Nonlinear Safety-Critical SystemsChunbin Qin0Yinliang Wu1Jishi Zhang2Tianzeng Zhu3School of Artificial Intelligence, Henan University, Zhengzhou 450046, ChinaSchool of Artificial Intelligence, Henan University, Zhengzhou 450046, ChinaSchool of Software, Henan University, Kaifeng 475000, ChinaSchool of Artificial Intelligence, Henan University, Zhengzhou 450046, ChinaThis paper addresses the problem of decentralized safety control (DSC) of constrained interconnected nonlinear safety-critical systems under reinforcement learning strategies, where asymmetric input constraints and security constraints are considered. To begin with, improved performance functions associated with the actuator estimates for each auxiliary subsystem are constructed. Then, the decentralized control problem with security constraints and asymmetric input constraints is transformed into an equivalent decentralized control problem with asymmetric input constraints using the barrier function. This approach ensures that safety-critical systems operate and learn optimal DSC policies within their safe global domains. Then, the optimal control strategy is shown to ensure that the entire system is uniformly ultimately bounded (UUB). In addition, all signals in the closed-loop auxiliary subsystem, based on Lyapunov theory, are uniformly ultimately bounded, and the effectiveness of the designed method is verified by practical simulation.https://www.mdpi.com/1099-4300/25/8/1158interconnected nonlinear safety-critical systemsbarrier functionasymmetric input constraintssafety constraintsdecentralized control |
| spellingShingle | Chunbin Qin Yinliang Wu Jishi Zhang Tianzeng Zhu Reinforcement Learning-Based Decentralized Safety Control for Constrained Interconnected Nonlinear Safety-Critical Systems Entropy interconnected nonlinear safety-critical systems barrier function asymmetric input constraints safety constraints decentralized control |
| title | Reinforcement Learning-Based Decentralized Safety Control for Constrained Interconnected Nonlinear Safety-Critical Systems |
| title_full | Reinforcement Learning-Based Decentralized Safety Control for Constrained Interconnected Nonlinear Safety-Critical Systems |
| title_fullStr | Reinforcement Learning-Based Decentralized Safety Control for Constrained Interconnected Nonlinear Safety-Critical Systems |
| title_full_unstemmed | Reinforcement Learning-Based Decentralized Safety Control for Constrained Interconnected Nonlinear Safety-Critical Systems |
| title_short | Reinforcement Learning-Based Decentralized Safety Control for Constrained Interconnected Nonlinear Safety-Critical Systems |
| title_sort | reinforcement learning based decentralized safety control for constrained interconnected nonlinear safety critical systems |
| topic | interconnected nonlinear safety-critical systems barrier function asymmetric input constraints safety constraints decentralized control |
| url | https://www.mdpi.com/1099-4300/25/8/1158 |
| work_keys_str_mv | AT chunbinqin reinforcementlearningbaseddecentralizedsafetycontrolforconstrainedinterconnectednonlinearsafetycriticalsystems AT yinliangwu reinforcementlearningbaseddecentralizedsafetycontrolforconstrainedinterconnectednonlinearsafetycriticalsystems AT jishizhang reinforcementlearningbaseddecentralizedsafetycontrolforconstrainedinterconnectednonlinearsafetycriticalsystems AT tianzengzhu reinforcementlearningbaseddecentralizedsafetycontrolforconstrainedinterconnectednonlinearsafetycriticalsystems |