mlsanityData to 7 Oct 2026

Control Barriers in Bayesian Learning of System Dynamics

arXiv 2012.14964 ↗First posted 29 Dec 2020eess.SY cs.RO cs.SYcited by 17

Not on the map. Why?

Abstract (arXiv)

This paper focuses on learning a model of system dynamics online while satisfying safety constraints. Our objective is to avoid offline system identification or hand-specified models and allow a system to safely and autonomously estimate and adapt its own model during operation. Given streaming observations of the system state, we use Bayesian learning to obtain a distribution over the system dynamics. Specifically, we propose a new matrix variate Gaussian process (MVGP) regression approach with an efficient covariance factorization to learn the drift and input gain terms of a nonlinear control-affine system. The MVGP distribution is then used to optimize the system behavior and ensure safety with high probability, by specifying control Lyapunov function (CLF) and control barrier function (CBF) chance constraints. We show that a safe control policy can be synthesized for systems with arbitrary relative degree and probabilistic CLF-CBF constraints by solving a second order cone program (SOCP). Finally, we extend our design to a self-triggering formulation, adaptively determining the time at which a new control input needs to be applied in order to guarantee safety.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). First posted on arXiv 29 Dec 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 3; 2022: 3; 2023: 4; 2024: 4; 2025: 3.

17 papers.

Sort:

  1. 2021Safe Reinforcement Learning Using Robust Control Barrier Functionscited by 44
  2. 2023In-Distribution Barrier Functions: Self-Supervised Policy Filters that Avoid Out-of-Distribution Statescited by 15
  3. 2021Pointwise Feasibility of Gaussian Process-based Safety-Critical Control under Model Uncertaintycited by 13
  4. 2022Conformal Methods for Quantifying Uncertainty in Spatiotemporal Data: A Surveycited by 11
  5. 2023Can Learning Deteriorate Control? Analyzing Computational Delays in Gaussian Process-Based Event-Triggered Online Learningcited by 8
  6. 2024Safety Filters for Black-Box Dynamical Systems by Learning Discriminating Hyperplanescited by 8
  7. 2024DADEE: Well-calibrated uncertainty quantification in neural networks for barriers-based robot safetycited by 3
  8. 2022Recursively Feasible Probabilistic Safe Online Learning with Control Barrier Functionscited by 2
  9. 2025Distance-Aware Error for Spline Networks: A Bottom-Up Approach to Uncertaintycited by 2
  10. 2021Safety-Critical Learning of Robot Control with Temporal Logic Specificationscited by 1
  11. 2023Model-Assisted Probabilistic Safe Adaptive Control With Meta-Bayesian Learningcited by 1
  12. 2024Real-Time Adaptive Safety-Critical Control with Gaussian Processes in High-Order Uncertain Modelscited by 1
5 more
  1. 2025Barrier Certificates for Unknown Systems with Latent States and Polynomial Dynamics using Bayesian Inferencecited by 1
  2. 2022Geometry of Radial Basis Neural Networks for Safety Biased Approximation of Unsafe Regionscited by 0
  3. 2023Episodic Gaussian Process-Based Learning Control with Vanishing Tracking Errorscited by 0
  4. 2024Bayesian meta learning for trustworthy uncertainty quantificationcited by 0
  5. 2025Worst-Case Distance-Aware Error Bounds for Neural Networkscited by 0