V-OCBF: Learning Safety Filters from Offline Data via Value-Guided Offline Control Barrier Functions

• URL: http://arxiv.org/abs/2512.10822v1
• Date: Thu, 11 Dec 2025 17:14:37 GMT
• Title: V-OCBF: Learning Safety Filters from Offline Data via Value-Guided Offline Control Barrier Functions
• Authors: Mumuksh Tayal, Manan Tayal, Aditya Singh, Shishir Kolathaya, Ravi Prakash,
• Abstract summary: We introduce Value-Guided Offline Control Barrier Functions (V-OCBF)<n>It learns a neural CBF entirely from offline demonstrations.<n>It yields substantially fewer safety violations than baseline methods.
• Score: 8.042484673796137
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Ensuring safety in autonomous systems requires controllers that satisfy hard, state-wise constraints without relying on online interaction. While existing Safe Offline RL methods typically enforce soft expected-cost constraints, they do not guarantee forward invariance. Conversely, Control Barrier Functions (CBFs) provide rigorous safety guarantees but usually depend on expert-designed barrier functions or full knowledge of the system dynamics. We introduce Value-Guided Offline Control Barrier Functions (V-OCBF), a framework that learns a neural CBF entirely from offline demonstrations. Unlike prior approaches, V-OCBF does not assume access to the dynamics model; instead, it derives a recursive finite-difference barrier update, enabling model-free learning of a barrier that propagates safety information over time. Moreover, V-OCBF incorporates an expectile-based objective that avoids querying the barrier on out-of-distribution actions and restricts updates to the dataset-supported action set. The learned barrier is then used with a Quadratic Program (QP) formulation to synthesize real-time safe control. Across multiple case studies, V-OCBF yields substantially fewer safety violations than baseline methods while maintaining strong task performance, highlighting its scalability for offline synthesis of safety-critical controllers without online interaction or hand-engineered barriers.

Related papers

• BarrierSteer: LLM Safety via Learning Barrier Steering [83.12893815611052]
  BarrierSteer is a novel framework that formalizes safety by embedding learned non-linear safety constraints directly into the model's latent representation space.<n>We show that BarrierSteer substantially reduces adversarial success rates, decreases unsafe generations, and outperforms existing methods.
  arXiv  Detail & Related papers  (2026-02-23T18:19:46Z)
• Learning Neural Control Barrier Functions from Expert Demonstrations using Inverse Constraint Learning [1.7235805533661985]
  We train a constraint function that classifies the states of the system under consideration to safe, i.e., belong to a controlled forward invariant set.<n>We then use that function to label a new set of simulated trajectories to train our neural CBF.<n>We empirically evaluate our approach in four different environments, demonstrating that it outperforms existing baselines.
  arXiv  Detail & Related papers  (2025-10-24T15:20:34Z)
• Reachability Barrier Networks: Learning Hamilton-Jacobi Solutions for Smooth and Flexible Control Barrier Functions [5.846607930201535]
  Control barrier functions (CBFs) are a popular method for appending safety guarantees to a general control framework.<n>We use physics-informed neural networks (PINNs) to generate smooth approximations of CBFs by computing Hamilton-Jacobi optimal control solutions.<n>We demonstrate that RBNs are highly accurate in low dimensions, and safer than the standard neural CBF approach in high dimensions.
  arXiv  Detail & Related papers  (2025-05-16T23:30:13Z)
• Pareto Control Barrier Function for Inner Safe Set Maximization Under Input Constraints [50.920465513162334]
  We introduce the PCBF algorithm to maximize the inner safe set of dynamical systems under input constraints.<n>We validate its effectiveness through comparison with Hamilton-Jacobi reachability for an inverted pendulum and through simulations on a 12-dimensional quadrotor system.<n>Results show that the PCBF consistently outperforms existing methods, yielding larger safe sets and ensuring safety under input constraints.
  arXiv  Detail & Related papers  (2024-10-05T18:45:19Z)
• Learning Performance-Oriented Control Barrier Functions Under Complex Safety Constraints and Limited Actuation [5.62479170374811]
  Control Barrier Functions (CBFs) provide an elegant framework for constraining nonlinear control system dynamics. We introduce a novel self-supervised learning framework to comprehensively address these challenges. We validate our approach on a 2D double integrator (DI) system and a 7D fixed-wing aircraft system.
  arXiv  Detail & Related papers  (2024-01-11T02:51:49Z)
• 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)
• Recursively Feasible Probabilistic Safe Online Learning with Control Barrier Functions [60.26921219698514]
  We introduce a model-uncertainty-aware reformulation of CBF-based safety-critical controllers. We then present the pointwise feasibility conditions of the resulting safety controller. We use these conditions to devise an event-triggered online data collection strategy.
  arXiv  Detail & Related papers  (2022-08-23T05:02:09Z)
• BarrierNet: A Safety-Guaranteed Layer for Neural Networks [50.86816322277293]
  BarrierNet allows the safety constraints of a neural controller be adaptable to changing environments. We evaluate them on a series of control problems such as traffic merging and robot navigations in 2D and 3D space.
  arXiv  Detail & Related papers  (2021-11-22T15:38:11Z)
• 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.