mlsanityData to 14 Oct 2026

Learning Safety Filters for Unknown Discrete-Time Linear Systems

arXiv 2111.00631 ↗First posted 1 Nov 2021cs.LG cs.SY eess.SYcited by 0

Not on the map. Why?

Abstract (arXiv)

A learning-based safety filter is developed for discrete-time linear time-invariant systems with unknown models subject to Gaussian noises with unknown covariance. Safety is characterized using polytopic constraints on the states and control inputs. The empirically learned model and process noise covariance with their confidence bounds are used to construct a robust optimization problem for minimally modifying nominal control actions to ensure safety with high probability. The optimization problem relies on tightening the original safety constraints. The magnitude of the tightening is larger at the beginning since there is little information to construct reliable models, but shrinks with time as more data becomes available.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 12 of its 29 references that are in the map. First posted on arXiv 1 Nov 2021.

Builds on

12 of 29 references.

References · 12

  1. 2019End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Taskscited by 289
  2. 2017A General Safety Framework for Learning-Based Control in Uncertain Robotic Systemscited by 163
  3. 2019Learning for Safety-Critical Control with Control Barrier Functionscited by 69
  4. 2020Reinforcement Learning for Safety-Critical Control under Model Uncertainty, using Control Lyapunov Functions and Control Barrier Functionscited by 68
  5. 2018Linear model predictive safety certification for learning-based controlcited by 37
  6. 2018Safely Learning to Control the Constrained Linear Quadratic Regulatorcited by 33
  7. 2020Safe Multi-Agent Interaction through Robust Control Barrier Functions with Learned Uncertaintiescited by 20
  8. 2020Control Barrier Functions for Unknown Nonlinear Systems using Gaussian Processescited by 20
  9. 2021Safe Adaptive Learning-based Control for Constrained Linear Quadratic Regulators with Regret Guaranteescited by 11
  10. 2020Bayesian Safe Learning and Control with Sum-of-Squares Analysis and Polynomial Kernelscited by 7
  11. 2021Adaptive Model Predictive Safety Certification for Learning-based Control -- Extended Versioncited by 2
  12. 2019Safe Learning-Based Control of Stochastic Jump Linear Systems: a Distributionally Robust Approachcited by 1

Built on by

Not cited yet.