mlsanityData to 14 Oct 2026

Designing Control Barrier Function via Probabilistic Enumeration for Safe Reinforcement Learning Navigation

arXiv 2504.21643 ↗First posted 30 Apr 2025cs.AI cs.ROcited by 3

On the map: Deep reinforcement learning methods → Safe and constrained RL

Abstract (arXiv)

Achieving safe autonomous navigation systems is critical for deploying robots in dynamic and uncertain real-world environments. In this paper, we propose a hierarchical control framework leveraging neural network verification techniques to design control barrier functions (CBFs) and policy correction mechanisms that ensure safe reinforcement learning navigation policies. Our approach relies on probabilistic enumeration to identify unsafe regions of operation, which are then used to construct a safe CBF-based control layer applicable to arbitrary policies. We validate our framework both in simulation and on a real robot, using a standard mobile robot benchmark and a highly dynamic aquatic environmental monitoring task. These experiments demonstrate the ability of the proposed solution to correct unsafe actions while preserving efficient navigation behavior. Our results show the promise of developing hierarchical verification-based systems to enable safe and robust navigation behaviors in complex scenarios.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in Safe and constrained RL, one of 15 directions in Deep reinforcement learning methods. Builds on 20 of its 33 references that are in the map. First posted on arXiv 30 Apr 2025.

Builds on

20 of 33 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024A Dynamic Safety Shield for Safe and Efficient Reinforcement Learning of Navigation Tasks5 Dec

Other references · 19

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2013Intriguing properties of neural networkscited by 5,155
  3. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  4. 2020Responsive Safety in Reinforcement Learning by PID Lagrangian Methodscited by 316
  5. 2016Control Barrier Function Based Quadratic Programs for Safety Critical Systemscited by 287
  6. 2019Algorithms for Verifying Deep Neural Networkscited by 221
  7. 2023Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmarkcited by 143
  8. 2023OmniSafe: An Infrastructure for Accelerating Safe Reinforcement Learning Researchcited by 80
  9. 2022Penalized Proximal Policy Optimization for Safe Reinforcement Learningcited by 68
  10. 2023How to Train Your Neural Control Barrier Function: Learning Safety Filters for Complex Input-Constrained Systemscited by 44
  11. 2022Verifying Learning-Based Robotic Navigation Systemscited by 33
  12. 2022Safe Control Under Input Limits with Neural Control Barrier Functionscited by 29
7 more
  1. 2023The #DNN-Verification Problem: Counting Unsafe Inputs for Deep Neural Networkscited by 19
  2. 2023Enumerating Safe Regions in Deep Neural Networks with Provable Probabilistic Guaranteescited by 19
  3. 2024Verification of Neural Control Barrier Functions with Symbolic Derivative Bounds Propagationcited by 12
  4. 2023Safe Deep Reinforcement Learning by Verifying Task-Level Propertiescited by 9
  5. 2024Neural Control Barrier Functions for Safe Navigationcited by 9
  6. 2023Online Safety Property Collection and Refinement for Safe Deep Reinforcement Learning in Mapless Navigationcited by 7
  7. 2024Improving Policy Optimization via varepsilon-Retraincited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Zero-Shot, Safe and Time-Efficient UAV Navigation via Potential-Based Reward Shaping, Control Lyapunov and Barrier Functionscited by 0
  2. 2026Probabilistic Verification of Recurrent Neural Networks for Single and Multi-Agent Reinforcement Learningcited by 0
  3. 2026A Survey on the Verification of Reinforcement Learning Policiescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Safety-Constrained Reinforcement Learning with Post-Training Reachability Verification for Robot Navigation
  2. 2025Certificated Actor-Critic: Hierarchical Reinforcement Learning with Control Barrier Functions for Safe Navigation
  3. 2026CAPSULE: Control-Theoretic Action Perturbations for Safe Uncertainty-Aware Reinforcement Learning
  4. 2024Learning Control Barrier Functions and their application in Reinforcement Learning: A Survey
  5. 2026DODGER: Safety-Guided Reinforcement Learning for Robot Navigation Among Dynamic Obstacles
  6. 2025Soft Actor-Critic-based Control Barrier Adaptation for Robust Autonomous Navigation in Unknown Environments
  7. 2024Handling Long-Term Safety and Uncertainty in Safe Reinforcement Learning
  8. 2025Hierarchical Reinforcement Learning for Safe Mapless Navigation with Congestion Estimation