Adaptive Neural Stochastic Control With Lipschitz Constant Optimization

被引:0
作者
Geng, Lian [1 ]
Qu, Qingyu [1 ]
Ran, Maopeng
Liu, Kexin [2 ]
Lu, Jinhu [2 ]
机构
[1] Beihang Univ, Sch Automat Sci & Elect Engn, Beijing 100191, Peoples R China
[2] Beihang Univ, Sch Automat Sci & Elect Engn, Natl Key Lab Multiperch Vehicle Power Driving Syst, Beijing 100094, Peoples R China
关键词
Measurement; Uncertainty; Optimization; Uncertain systems; Artificial neural networks; Stochastic processes; Adaptive control; Contraction theory; adaptive control; neural network; Lipschitz constant optimization; LEARNING-BASED CONTROL; CONTRACTION METRICS; NETWORKS; CONVEX;
D O I
10.1109/TCSI.2024.3386506
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
An adaptive neural stochastic contraction metric with Lipschitz constant optimization (aNSCM-Lip) is proposed for It stochastic systems with unmatched parameter uncertainties. The adaptive law is designed via the certainty equivalence principle with incremental stability guarantee, which is specified by the neural stochastic contraction metric (NSCM). Then, we develop a neural network (NN) based on Lipschitz constant estimation and optimization. Lipschitz optimization and weights training are formulated as optimization problems utilizing the alternating direction method of multipliers (ADMM), which ensures the Lipschitz continuity of the network metric and its derivative. The learning-based controller with a Lipschitz constant optimized network provides stability certificates for the closed-loop system. DC-DC buck vector and single-joint manipulator examples are given to demonstrate the effectiveness and superiority of the proposed control strategy.
引用
收藏
页码:3294 / 3306
页数:13
相关论文
共 35 条
[1]   Observer-Based Backstepping Sliding Mode Control Design for Microgrids Feeding a Constant Power Load [J].
Alipour, Mohammad ;
Zarei, Jafar ;
Razavi-Far, Roozbeh ;
Saif, Mehrdad ;
Mijatovic, Nenad ;
Dragicevic, Tomislav .
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2023, 70 (01) :465-473
[2]   Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning [J].
Brunke, Lukas ;
Greeff, Melissa ;
Hall, Adam W. ;
Yuan, Zhaocong ;
Zhou, Siqi ;
Panerati, Jacopo ;
Schoellig, Angela P. .
ANNUAL REVIEW OF CONTROL ROBOTICS AND AUTONOMOUS SYSTEMS, 2022, 5 :411-444
[3]   A Novel Adaptive Control Scheme for Automotive Electronic Throttle Based on Extremum Seeking [J].
Chen, Lin ;
Wang, Yilin ;
Zhao, Jing ;
Ding, Shihong ;
Gao, Jinwu ;
Chen, Hong .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 2023, 70 (06) :2599-2611
[4]   Observer Design for Stochastic Nonlinear Systems via Contraction-Based Incremental Stability [J].
Dani, Ashwin P. ;
Chung, Soon-Jo ;
Hutchinson, Seth .
IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2015, 60 (03) :700-714
[5]   H∞ Codesign for Uncertain Nonlinear Control Systems Based on Policy Iteration Method [J].
Fan, Quan-Yong ;
Wang, Dongsheng ;
Xu, Bin .
IEEE TRANSACTIONS ON CYBERNETICS, 2022, 52 (10) :10101-10110
[6]  
Fazlyab M., 2019, ARXIV
[7]  
Fazlyab M, 2019, ADV NEUR IN, V32
[8]   An Introduction to Neural Network Analysis via Semidefinite Programming [J].
Fazlyab, Mahyar ;
Morari, Manfred ;
Pappas, George J. .
2021 60TH IEEE CONFERENCE ON DECISION AND CONTROL (CDC), 2021, :6341-6350
[9]   Safety Verification and Robustness Analysis of Neural Networks via Quadratic Constraints and Semidefinite Programming [J].
Fazlyab, Mahyar ;
Morari, Manfred ;
Pappas, George J. .
IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2022, 67 (01) :1-15
[10]   Optimal Parameter Selection for the Alternating Direction Method of Multipliers (ADMM): Quadratic Problems [J].
Ghadimi, Euhanna ;
Teixeira, Andre ;
Shames, Iman ;
Johansson, Mikael .
IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2015, 60 (03) :644-658