mlsanityData to 7 Oct 2026

Conformal Reachability for Safe Control in Unknown Environments

arXiv 2602.03799 ↗First posted 3 Feb 2026cs.RO cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Designing provably safe control is a core problem in trustworthy autonomy. However, most prior work in this regard assumes either that the system dynamics are known or deterministic, or that the state and action space are finite, significantly limiting application scope. We address this limitation by developing a probabilistic verification framework for unknown dynamical systems which combines conformal prediction with reachability analysis. In particular, we use conformal prediction to obtain valid uncertainty intervals for the unknown dynamics at each time step, with reachability then verifying whether safety is maintained within the conformal uncertainty bounds. Next, we develop an algorithmic approach for training control policies that optimize nominal reward while also maximizing the planning horizon with sound probabilistic safety guarantees. We evaluate the proposed approach in seven safe control settings spanning four domains -- cartpole, lane following, drone control, and safe navigation -- for both affine and nonlinear safety specifications. Our experiments show that the policies we learn achieve the strongest provable safety guarantees while still maintaining high average reward.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 34 of its 54 references that are in the map. First posted on arXiv 3 Feb 2026.

Builds on

34 of 54 references.

References · 34

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2017Constrained Policy Optimizationcited by 928
  3. 2021A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantificationcited by 777
  4. 2018Reward Constrained Policy Optimizationcited by 397
  5. 2019Control Barrier Functions: Theory and Applicationscited by 332
  6. 2020Responsive Safety in Reinforcement Learning by PID Lagrangian Methodscited by 302
  7. 2018A Lyapunov-based Approach to Safe Reinforcement Learningcited by 278
  8. 2016Control Barrier Function Based Quadratic Programs for Safety Critical Systemscited by 261
  9. 2019End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Taskscited by 256
  10. 2020Fast and Complete: Enabling Complete Neural Network Verification with Rapid and Massively Parallel Incomplete Verifierscited by 183
  11. 2023Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmarkcited by 135
  12. 2020CRPO: A New Approach for Safe Reinforcement Learning with Convergence Guaranteecited by 128
22 more
  1. 2021Safe Nonlinear Control Using Robust Neural Lyapunov-Barrier Functionscited by 91
  2. 2018Verisig: verifying safety properties of hybrid systems with neural network controllerscited by 83
  3. 2023OmniSafe: An Infrastructure for Accelerating Safe Reinforcement Learning Researchcited by 76
  4. 2021Lyapunov-stable neural-network controlcited by 66
  5. 2024Neural Network Verification with Branch-and-Bound for General Nonlinearitiescited by 47
  6. 2022Neural Lyapunov Control of Unknown Nonlinear Systems with Stability Guaranteescited by 39
  7. 2023Conformal Prediction Regions for Time Series using Linear Complementarity Programmingcited by 33
  8. 2021Feasible Actor-Critic: Constrained Reinforcement Learning for Ensuring Statewise Safetycited by 30
  9. 2023OmniDrones: An Efficient and Flexible Platform for Reinforcement Learning in Drone Controlcited by 28
  10. 2022Model-based Safe Deep Reinforcement Learning via a Constrained Proximal Policy Optimization Algorithmcited by 27
  11. 2024Formal Verification and Control with Conformal Predictioncited by 26
  12. 2022Efficient and Differentiable Conformal Prediction with General Function Classescited by 25
  13. 2022Provably Safe Reinforcement Learning via Action Projection using Reachability Analysis and Polynomial Zonotopescited by 23
  14. 2023Multi-Agent Reachability Calibration with Conformal Predictioncited by 23
  15. 2022Safe Reinforcement Learning Using Black-Box Reachability Analysiscited by 22
  16. 2022Safe Model-Based Reinforcement Learning with an Uncertainty-Aware Reachability Certificatecited by 16
  17. 2017DRYVR:Data-driven verification and compositional reasoning for automotive systemscited by 14
  18. 2020Safety Verification of Unknown Dynamical Systems via Gaussian Process Regressioncited by 9
  19. 2024Verified Safe Reinforcement Learning for Neural Network Dynamic Modelscited by 7
  20. 2024SEEV: Synthesis with Efficient Exact Verification for ReLU Neural Barrier Functionscited by 7
  21. 2025Safety Evaluation of Motion Plans Using Trajectory Predictors as Forward Reachable Set Estimatorscited by 3
  22. 2025Learning Vision-Based Neural Network Controllers with Semi-Probabilistic Safety Guaranteescited by 1

Built on by

Not cited yet.