Robust Conformal CBF and CLF Controllers via Iterative Policy Updates

• URL: http://arxiv.org/abs/2606.15366v1
• Date: Sat, 13 Jun 2026 16:03:22 GMT
• Title: Robust Conformal CBF and CLF Controllers via Iterative Policy Updates
• Abstract summary: Conformal prediction (CP) has been used to obtain probabilistic bounds on the error between a learned dynamics model and the true but unknown system.<n>Such CP bounds can then be embedded into robust control Lyapunov function (CLF) and control barrier function (CBF) frameworks.<n>However, such an approach does not retain stability/safety guarantees because of the distribution shift between the closed-loop trajectory distribution.<n>We propose an episodic framework that iteratively updates the robust CLF/CBF policy while maintaining stability/safety guarantees.
• Score: 10.455279488679523
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Conformal prediction (CP) has been used to obtain probabilistic bounds on the error between a learned dynamics model and the true but unknown system. Such CP bounds can then be embedded into robust control Lyapunov function (CLF) and control barrier function (CBF) frameworks. However, such an approach does not retain stability/safety guarantees because of the distribution shift between the closed-loop trajectory distribution under the deployed CLF/CBF policy and the trajectory distribution from which the CP bound and its guarantees were derived. To address this issue, we propose an episodic framework that iteratively updates the robust conformal CLF/CBF policy while maintaining stability/safety guarantees across episodes. We achieve this by (1) using adversarially robust conformal prediction, and (2) quantifying a distribution shift budget that allows us to control how much the model error can increase across policy updates. This distribution shift budget is derived via a closed-loop trajectory sensitivity analysis, yielding an implicit and an explicit update rule for the CP bound. We analyze convergence of our algorithm, which we demonstrate on three case studies. To the best of our knowledge, these are the first results that provide stability/safety guarantees for robust conformal CBF/CLF policies.

Related papers

• Predicted-Flow Control Barrier Functions for Real-Time Safe Optimal Control [0.0]
  Control barrier functions (CBFs) provide real-time safety guarantees through pointwise conditions on the state.<n>This article introduces predicted-flow control barrier functions (P-CBFs)<n>For safety, a P-CBF can certify that the predicted flow is in a safe set over the entire prediction horizon.
  arXiv  Detail & Related papers  (2026-05-29T19:27:24Z)
• Ratio-Variance Regularized Policy Optimization [64.95520246570446]
  We show that explicitly constraining the policy ratio variance provides a principled local approximation to trust-region constraints.<n>We introduce $bf R2bf VPO$ (Ratio-Variance Regularized Policy Optimization), which implements this constraint via a primal-dual optimization framework.
  arXiv  Detail & Related papers  (2026-05-26T09:53:42Z)
• MPC as a Copilot: A Predictive Filter Framework with Safety and Stability Guarantees [6.019901994880397]
  This paper introduces the Predictive Safety-Stability Filter (PS2F), a unified predictive filter framework that guarantees constraint satisfaction and stability within a single architecture.<n>The PS2F framework comprises two cascaded optimal control problems: a nominal model predictive control (MPC) layer that serves solely as a copilot, and a secondary filtering layer that adjusts external command to remain within a provably safe and stable region.
  arXiv  Detail & Related papers  (2026-03-29T22:17:39Z)
• BandPO: Bridging Trust Regions and Ratio Clipping via Probability-Aware Bounds for LLM Reinforcement Learning [49.25750348525603]
  BandPO replaces canonical clipping with Band, a unified theoretical operator that projects trust regions into dynamic, probability-aware clipping intervals.<n>We show that BandPO consistently outperforms canonical clipping and Clip-Higher, while robustly mitigating entropy collapse.
  arXiv  Detail & Related papers  (2026-03-05T08:03:05Z)
• Entropy Ratio Clipping as a Soft Global Constraint for Stable Reinforcement Learning [49.92803982100042]
  We propose using the entropy ratio between the current and previous policies as a new global metric.<n>We introduce an textbfEntropy Ratio (ERC) mechanism that imposes bidirectional constraints on the entropy ratio.<n>This stabilizes policy updates at the global distribution level and compensates for the inability of PPO-clip to regulate probability shifts of un-sampled actions.
  arXiv  Detail & Related papers  (2025-12-05T10:26:32Z)
• Conformal Prediction in The Loop: A Feedback-Based Uncertainty Model for Trajectory Optimization [3.761729592527251]
  Conformal Prediction (CP) is a powerful statistical machine learning tool to construct uncertainty sets with coverage guarantees.<n>We propose a novel Feedback-Based CP (Fb-CP) framework for shrinking-horizon TO with a joint risk constraint.
  arXiv  Detail & Related papers  (2025-10-18T07:11:23Z)
• Wasserstein Distributionally Robust Control Barrier Function using Conditional Value-at-Risk with Differentiable Convex Programming [4.825619788907192]
  Control Barrier functions (CBFs) have attracted extensive attention for designing safe controllers for real-world safety-critical systems. We present distributional robust CBF to achieve resilience under distributional shift. We also provide an approximate variant of DR-CBF for higher-order systems.
  arXiv  Detail & Related papers  (2023-09-15T18:45:09Z)
• Safe Neural Control for Non-Affine Control Systems with Differentiable Control Barrier Functions [58.19198103790931]
  This paper addresses the problem of safety-critical control for non-affine control systems. It has been shown that optimizing quadratic costs subject to state and control constraints can be sub-optimally reduced to a sequence of quadratic programs (QPs) by using Control Barrier Functions (CBFs) We incorporate higher-order CBFs into neural ordinary differential equation-based learning models as differentiable CBFs to guarantee safety for non-affine control systems.
  arXiv  Detail & Related papers  (2023-09-06T05:35:48Z)
• Pointwise Feasibility of Gaussian Process-based Safety-Critical Control under Model Uncertainty [77.18483084440182]
  Control Barrier Functions (CBFs) and Control Lyapunov Functions (CLFs) are popular tools for enforcing safety and stability of a controlled system, respectively. We present a Gaussian Process (GP)-based approach to tackle the problem of model uncertainty in safety-critical controllers that use CBFs and CLFs.
  arXiv  Detail & Related papers  (2021-06-13T23:08:49Z)
• Reinforcement Learning for Safety-Critical Control under Model Uncertainty, using Control Lyapunov Functions and Control Barrier Functions [96.63967125746747]
  Reinforcement learning framework learns the model uncertainty present in the CBF and CLF constraints. RL-CBF-CLF-QP addresses the problem of model uncertainty in the safety constraints.
  arXiv  Detail & Related papers  (2020-04-16T10:51:33Z)

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.