Safe learning-based control via function-based uncertainty quantification

• URL: http://arxiv.org/abs/2604.01173v1
• Date: Wed, 01 Apr 2026 17:23:30 GMT
• Title: Safe learning-based control via function-based uncertainty quantification
• Abstract summary: Uncertainty quantification is essential when deploying learning-based control methods in safety-critical systems.<n>We model the unknown function as a random function from which independent and identically distributed realizations can be generated.<n>We integrate these uncertainty tubes into a safe Bayesian optimization algorithm, which we then use to safely tune control parameters on a real Furuta pendulum.
• Score: 12.101454217337931
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Uncertainty quantification is essential when deploying learning-based control methods in safety-critical systems. This is commonly realized by constructing uncertainty tubes that enclose the unknown function of interest, e.g., the reward and constraint functions or the underlying dynamics model, with high probability. However, existing approaches for uncertainty quantification typically rely on restrictive assumptions on the unknown function, such as known bounds on functional norms or Lipschitz constants, and struggle with discontinuities. In this paper, we model the unknown function as a random function from which independent and identically distributed realizations can be generated, and construct uncertainty tubes via the scenario approach that hold with high probability and rely solely on the sampled realizations. We integrate these uncertainty tubes into a safe Bayesian optimization algorithm, which we then use to safely tune control parameters on a real Furuta pendulum.

Related papers

• Safe Exploration for Nonlinear Processes Using Online Gaussian Process Learning [7.223664911847993]
  This paper proposes a safe data-driven control framework for nonlinear systems with partially known dynamics.<n>Unmodeled nonlinear dynamics are captured by a Gaussian process residual learned in real time.<n> Numerical results validate the approach, demonstrating safe and informative exploration under model uncertainty.
  arXiv  Detail & Related papers  (2026-05-10T21:33:37Z)
• Optimal uncertainty bounds for multivariate kernel regression under bounded noise: A Gaussian process-based dual function [3.2093811507874768]
  Non-conservative uncertainty bounds are essential for making reliable predictions about latent functions from noisy data.<n>This paper presents a tight, distribution-free bound for multi-output kernel-based estimates.
  arXiv  Detail & Related papers  (2026-03-17T13:06:54Z)
• Statistical Contraction for Chance-Constrained Trajectory Optimization of Non-Gaussian Stochastic Systems [0.0]
  Our framework employs conformal inference to generate confidence sets for the closed-loop dynamics around arbitrary reference trajectories.<n>Via appropriate constraint tightening, chance constraints can be reformulated into tractable, statistically valid deterministic constraints on the reference trajectories.<n>This enables a formal pathway to leverage and validate learning-based motion planners and controllers, such as those with neural contraction metrics, in safety-critical real-world applications.
  arXiv  Detail & Related papers  (2026-03-07T08:01:20Z)
• Information-Theoretic Safe Bayesian Optimization [59.758009422067005]
  We consider a sequential decision making task, where the goal is to optimize an unknown function without evaluating parameters that violate an unknown (safety) constraint. Most current methods rely on a discretization of the domain and cannot be directly extended to the continuous case. We propose an information-theoretic safe exploration criterion that directly exploits the GP posterior to identify the most informative safe parameters to evaluate.
  arXiv  Detail & Related papers  (2024-02-23T14:31:10Z)
• Model-Based Uncertainty in Value Functions [89.31922008981735]
  We focus on characterizing the variance over values induced by a distribution over MDPs. Previous work upper bounds the posterior variance over values by solving a so-called uncertainty Bellman equation. We propose a new uncertainty Bellman equation whose solution converges to the true posterior variance over values.
  arXiv  Detail & Related papers  (2023-02-24T09:18:27Z)
• Information-Theoretic Safe Exploration with Gaussian Processes [89.31922008981735]
  We consider a sequential decision making task where we are not allowed to evaluate parameters that violate an unknown (safety) constraint. Most current methods rely on a discretization of the domain and cannot be directly extended to the continuous case. We propose an information-theoretic safe exploration criterion that directly exploits the GP posterior to identify the most informative safe parameters to evaluate.
  arXiv  Detail & Related papers  (2022-12-09T15:23:58Z)
• Probabilities Are Not Enough: Formal Controller Synthesis for Stochastic Dynamical Models with Epistemic Uncertainty [68.00748155945047]
  Capturing uncertainty in models of complex dynamical systems is crucial to designing safe controllers. Several approaches use formal abstractions to synthesize policies that satisfy temporal specifications related to safety and reachability. Our contribution is a novel abstraction-based controller method for continuous-state models with noise, uncertain parameters, and external disturbances.
  arXiv  Detail & Related papers  (2022-10-12T07:57:03Z)
• Deep Ensemble as a Gaussian Process Approximate Posterior [32.617549688656354]
  Deep Ensemble (DE) is an effective alternative to Bayesian neural networks for uncertainty quantification in deep learning. We propose a refinement of DE where the functional inconsistency is explicitly characterized and tuned w.r.t. the training data and certain priori beliefs. Our approach consumes only marginally added training cost than the standard DE, but achieves better uncertainty quantification than DE and its variants across diverse scenarios.
  arXiv  Detail & Related papers  (2022-04-30T05:25:44Z)
• Probabilistic robust linear quadratic regulators with Gaussian processes [73.0364959221845]
  Probabilistic models such as Gaussian processes (GPs) are powerful tools to learn unknown dynamical systems from data for subsequent use in control design. We present a novel controller synthesis for linearized GP dynamics that yields robust controllers with respect to a probabilistic stability margin.
  arXiv  Detail & Related papers  (2021-05-17T08:36:18Z)
• Deep Learning based Uncertainty Decomposition for Real-time Control [9.067368638784355]
  We propose a novel method for detecting the absence of training data using deep learning. We show its advantages over existing approaches on synthetic and real-world datasets. We further demonstrate the practicality of this uncertainty estimate in deploying online data-efficient control on a simulated quadcopter.
  arXiv  Detail & Related papers  (2020-10-06T10:46:27Z)
• Learning Control Barrier Functions from Expert Demonstrations [69.23675822701357]
  We propose a learning based approach to safe controller synthesis based on control barrier functions (CBFs) We analyze an optimization-based approach to learning a CBF that enjoys provable safety guarantees under suitable Lipschitz assumptions on the underlying dynamical system. To the best of our knowledge, these are the first results that learn provably safe control barrier functions from data.
  arXiv  Detail & Related papers  (2020-04-07T12:29:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.