Bayesian Learning-Based Adaptive Control for Safety Critical Systems

被引:0
|
作者
Fan, David D. [1 ,3 ]
Nguyen, Jennifer [2 ]
Thakker, Rohan [3 ]
Alatur, Nikhilesh [3 ]
Agha-mohammadi, Ali-akbar [3 ]
Theodorou, Evangelos A. [1 ]
机构
[1] Georgia Inst Technol, Inst Robot & Intelligent Machines, Atlanta, GA 30332 USA
[2] West Virginia Univ, Dept Mech & Aerosp Engn, Morgantown, WV 26506 USA
[3] CALTECH, Jet Prop Lab, Pasadena, CA 91125 USA
基金
美国国家航空航天局;
关键词
Robust/Adaptive Control of Robotic Systems; Robot Safety; Probability and Statistical Methods; Bayesian Adaptive Control; Deep Learning; Mars Rover; MODEL-PREDICTIVE CONTROL;
D O I
10.1109/icra40945.2020.9196709
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Deep learning has enjoyed much recent success, and applying state-of-the-art model learning methods to controls is an exciting prospect. However, there is a strong reluctance to use these methods on safety-critical systems, which have constraints on safety, stability, and real-time performance. We propose a framework which satisfies these constraints while allowing the use of deep neural networks for learning model uncertainties. Central to our method is the use of Bayesian model learning, which provides an avenue for maintaining appropriate degrees of caution in the face of the unknown. In the proposed approach, we develop an adaptive control framework leveraging the theory of stochastic CLFs (Control Lyapunov Functions) and stochastic CBFs (Control Barrier Functions) along with tractable Bayesian model learning via Gaussian Processes or Bayesian neural networks. Under reasonable assumptions, we guarantee stability and safety while adapting to unknown dynamics with probability 1. We demonstrate this architecture for high-speed terrestrial mobility targeting potential applications in safety-critical high-speed Mars rover missions.
引用
收藏
页码:4093 / 4099
页数:7
相关论文
共 50 条
  • [1] Security and Safety-Critical Learning-Based Collaborative Control for Multiagent Systems
    Yan, Bing
    Shi, Peng
    Lim, Chee Peng
    Sun, Yuan
    Agarwal, Ramesh K.
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2024, : 1 - 12
  • [2] Learning-based Adaptive Control for Nonlinear Systems
    Benosman, Mouhacine
    [J]. 2014 EUROPEAN CONTROL CONFERENCE (ECC), 2014, : 920 - 925
  • [3] Reinforcement Learning-Based Decentralized Safety Control for Constrained Interconnected Nonlinear Safety-Critical Systems
    Qin, Chunbin
    Wu, Yinliang
    Zhang, Jishi
    Zhu, Tianzeng
    [J]. ENTROPY, 2023, 25 (08)
  • [4] Adaptive Model Predictive Safety Certification for Learning-based Control
    Didier, Alexandre
    Wabersich, Kim P.
    Zeilinger, Melanie N.
    [J]. 2021 60TH IEEE CONFERENCE ON DECISION AND CONTROL (CDC), 2021, : 809 - 815
  • [5] Safety Filtering for Reinforcement Learning-based Adaptive Cruise Control
    Hailemichael, Habtamu
    Ayalew, Beshah
    Kerbel, Lindsey
    Ivanco, Andrej
    Loiselle, Keith
    [J]. IFAC PAPERSONLINE, 2022, 55 (24): : 149 - 154
  • [6] Learning-Based Safety-Stability-Driven Control for Safety-Critical Systems under Model Uncertainties
    Zheng, Lei
    Yang, Rui
    Pan, Jiesen
    Cheng, Hui
    Hu, Haifeng
    [J]. 2020 12TH INTERNATIONAL CONFERENCE ON WIRELESS COMMUNICATIONS AND SIGNAL PROCESSING (WCSP), 2020, : 1112 - 1118
  • [7] Learning-based iterative modular adaptive control for nonlinear systems
    Benosman, Mouhacine
    Farahmand, Amir-Massoud
    Xia, Meng
    [J]. INTERNATIONAL JOURNAL OF ADAPTIVE CONTROL AND SIGNAL PROCESSING, 2019, 33 (02) : 335 - 355
  • [8] Adaptive learning-based recoil control for deepwater drilling riser systems
    Zhang, Yun
    Zhang, Bao-Lin
    Han, Qing-Long
    Zhang, Xian-Ming
    Liu, Ximei
    Zhang, Bin
    [J]. OCEAN ENGINEERING, 2023, 287
  • [9] Learning-Based Adaptive Control for Stochastic Linear Systems With Input Constraints
    Siriya, Seth
    Zhu, Jingge
    Nesic, Dragan
    Pu, Ye
    [J]. IEEE CONTROL SYSTEMS LETTERS, 2023, 7 : 1273 - 1278
  • [10] Reinforcement learning-based adaptive production control of pull manufacturing systems
    Xanthopoulos, A. S.
    Chnitidis, G.
    Koulouriotis, D. E.
    [J]. JOURNAL OF INDUSTRIAL AND PRODUCTION ENGINEERING, 2019, 36 (05) : 313 - 323