mlsanityData to 14 Oct 2026

The Safety Filter: A Unified View of Safety-Critical Control in Autonomous Systems

arXiv 2309.05837 ↗First posted 11 Sep 2023eess.SY cs.LG cs.ROcited by 88

Not on the map. Why?

Cited by 22 in Deep reinforcement learning methods, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Recent years have seen significant progress in the realm of robot autonomy, accompanied by the expanding reach of robotic technologies. However, the emergence of new deployment domains brings unprecedented challenges in ensuring safe operation of these systems, which remains as crucial as ever. While traditional model-based safe control methods struggle with generalizability and scalability, emerging data-driven approaches tend to lack well-understood guarantees, which can result in unpredictable catastrophic failures. Successful deployment of the next generation of autonomous robots will require integrating the strengths of both paradigms. This article provides a review of safety filter approaches, highlighting important connections between existing techniques and proposing a unified technical framework to understand, compare, and combine them. The new unified view exposes a shared modular structure across a range of seemingly disparate safety filter classes and naturally suggests directions for future progress towards more scalable synthesis, robust monitoring, and efficient intervention.

Key facts. Cited by 88 papers in the map (data through 14 Oct 2026). Builds on 65 of its 120 references that are in the map. First posted on arXiv 11 Sep 2023.

Builds on

65 of 120 references.

References · 65

  1. 2018Efficient Neural Network Robustness Certification with General Activation Functionscited by 445
  2. 2019Control Barrier Functions: Theory and Applicationscited by 372
  3. 2021Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learningcited by 371
  4. 2017Safe Model-based Reinforcement Learning with Stability Guaranteescited by 366
  5. 2016Control Barrier Function Based Quadratic Programs for Safety Critical Systemscited by 287
  6. 2017Hamilton-Jacobi Reachability: A Brief Overview and Recent Advancescited by 201
  7. 2020Recovery RL: Safe Reinforcement Learning with Learned Recovery Zonescited by 175
  8. 2017A General Safety Framework for Learning-Based Control in Uncertain Robotic Systemscited by 163
  9. 2022Safe Control with Learned Certificates: A Survey of Neural Lyapunov, Barrier, and Contraction methodscited by 151
  10. 2018A predictive safety filter for learning-based control of constrained nonlinear dynamical systemscited by 118
  11. 2020Learning to be Safe: Deep RL with a Safety Criticcited by 116
  12. 2020Conservative Safety Critics for Explorationcited by 113
38 more
  1. 2021Safe Nonlinear Control Using Robust Neural Lyapunov-Barrier Functionscited by 94
  2. 2020Learning Control Barrier Functions from Expert Demonstrationscited by 92
  3. 2020DeepReach: A Deep Learning Approach to High-Dimensional Reachabilitycited by 91
  4. 2021Robust Control Barrier-Value Functions for Safety-Critical Controlcited by 51
  5. 2021Safety and Liveness Guarantees through Reach-Avoid Reinforcement Learningcited by 49
  6. 2021On Exposing the Challenging Long Tail in Future Prediction of Traffic Actorscited by 48
  7. 2019Robust Model Predictive Shielding for Safe Reinforcement Learning with Stochastic Dynamicscited by 47
  8. 2014Reach-Avoid Problems with Time-Varying Dynamics, Targets and Constraintscited by 44
  9. 2020Reach-SDP: Reachability Analysis of Closed-Loop Systems with Neural Network Controllers via Semidefinite Programmingcited by 43
  10. 2021Reachability Analysis of Neural Feedback Loopscited by 41
  11. 2016Learning Model Predictive Control for iterative tasks. A Data-Driven Control Frameworkcited by 39
  12. 2018Linear model predictive safety certification for learning-based controlcited by 37
  13. 2020Guaranteeing Safety of Learned Perception Modules via Measurement-Robust Control Barrier Functionscited by 33
  14. 2018Probabilistically Safe Robot Planning with Confidence-Based Human Predictionscited by 28
  15. 2022ISAACS: Iterative Soft Adversarial Actor-Critic for Safetycited by 28
  16. 2022Sim-to-Lab-to-Real: Safe Reinforcement Learning with Shielding and Generalization Guaranteescited by 27
  17. 2020On Infusing Reachability-Based Safety Assurance within Planning Frameworks for Human-Robot Vehicle Interactionscited by 25
  18. 2020Learning Hybrid Control Barrier Functions from Datacited by 24
  19. 2023Solving Stabilize-Avoid Optimal Control via Epigraph Form and Deep Reinforcement Learningcited by 24
  20. 2021Safe Occlusion-aware Autonomous Driving via Game-Theoretic Active Perceptioncited by 23
  21. 2019Probabilistic model predictive safety certification for learning-based controlcited by 22
  22. 2021Safety Assurances for Human-Robot Interaction via Confidence-aware Game-theoretic Human Modelscited by 21
  23. 2016Decomposition of Reachable Sets and Tubes for a Class of Nonlinear Systemscited by 18
  24. 2018Permissive Barrier Certificates for Safe Stabilization Using Sum-of-squarescited by 15
  25. 2021FaSTrack: a Modular Framework for Real-Time Motion Planning and Guaranteed Safe Trackingcited by 15
  26. 2022Refining Control Barrier Functions through Hamilton-Jacobi Reachabilitycited by 15
  27. 2022Online Update of Safety Assurances Using Confidence-Based Predictionscited by 15
  28. 2021Learning Robust Hybrid Control Barrier Functions for Uncertain Systemscited by 14
  29. 2021Backup Control Barrier Functions: Formulation and Comparative Studycited by 12
  30. 2021SHARP: Shielding-Aware Robust Planning for Safe and Efficient Human-Robot Interactioncited by 12
  31. 2022Parameter-Conditioned Reachable Sets for Updating Safety Assurances Onlinecited by 12
  32. 2018Bridging the Gap Between Safety and Real-Time Performance in Receding-Horizon Trajectory Design for Mobile Robotscited by 11
  33. 2020Improving Automated Driving through POMDP Planning with Human Internal Statescited by 11
  34. 2021Probabilistic Safety-Assured Adaptive Merging Control for Autonomous Vehiclescited by 11
  35. 2022Generating Formal Safety Assurances for High-Dimensional Reachabilitycited by 11
  36. 2018A Classification-based Approach for Approximate Reachabilitycited by 10
  37. 2022Active Uncertainty Reduction for Human-Robot Interaction: An Implicit Dual Control Approachcited by 10
  38. 2019Reachability-Based Safety Guarantees using Efficient Initializationscited by 9

50 most cited of 65 All 65 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 17; 2025: 30; 2026: 37.

88 papers.

Sort:

By area:

  1. 2023Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysiscited by 103
  2. 2023Conformal Decision Theory: Safe Autonomous Decisions from Imperfect Predictionscited by 50
  3. 2025Generalizing Safety Beyond Collision-Avoidance via Latent-Space Reachability Analysiscited by 45
  4. 2023Model-Based Runtime Monitoring with Interactive Imitation Learningcited by 38
  5. 2024Multi-Task Interactive Robot Fleet Learning with Visual World Modelscited by 36
  6. 2025Uncertainty-aware Latent Safety Filters for Avoiding Out-of-Distribution Failurescited by 33
  7. 2025Offline Goal-conditioned Reinforcement Learning with Quasimetric Representationscited by 24
  8. 2024Safety Filtering While Training: Improving the Performance and Sample Efficiency of Reinforcement Learning Agentscited by 17
  9. 2024Gameplay Filters: Robust Zero-Shot Safety through Adversarial Imaginationcited by 16
  10. 2024Hamilton-Jacobi Reachability in Reinforcement Learning: A Surveycited by 16
  11. 2024SAFE-GIL: SAFEty Guided Imitation Learning for Robotic Systemscited by 14
  12. 2025A Physics-Informed Machine Learning Framework for Safe and Optimal Control of Autonomous Systemscited by 12
38 more
  1. 2025SafeFlowMatcher: Safe and Fast Planning using Flow Matching with Control Barrier Functionscited by 12
  2. 2025Real-Time Out-of-Distribution Failure Prevention via Multi-Modal Reasoningcited by 10
  3. 2025Discrete GCBF Proximal Policy Optimization for Multi-agent Safe Optimal Controlcited by 8
  4. 2024Human-AI Safety: A Descendant of Generative AI and Control Systems Safetycited by 7
  5. 2024MAGICS: Adversarial RL with Minimax Actors Guided by Implicit Critic Stackelberg for Convergent Neural Synthesis of Robot Safetycited by 7
  6. 2025AnySafe: Adapting Latent Safety Filters at Runtime via Safety Constraint Parameterization in the Latent Spacecited by 7
  7. 2024Blending Data-Driven Priors in Dynamic Gamescited by 6
  8. 2024Safe Multi-Agent Reinforcement Learning with Convergence to Generalized Nash Equilibriumcited by 6
  9. 2025SafeMimic: Towards Safe and Autonomous Human-to-Robot Imitation for Mobile Manipulationcited by 6
  10. 2024RAIL: Reachability-Aided Imitation Learning for Safe Policy Executioncited by 5
  11. 2025Learning Conservative Neural Control Barrier Functions from Offline Datacited by 5
  12. 2025From Demonstrations to Safe Deployment: Path-Consistent Safety Filtering for Diffusion Policiescited by 5
  13. 2026Synthesis and Deployment of Maximal Robust Control Barrier Functions through Adversarial Reinforcement Learningcited by 5
  14. 2023Value Approximation for Two-Player General-Sum Differential Games with State Constraintscited by 3
  15. 2024Learning Maximal Safe Sets Using Hypernetworks for MPC-based Local Trajectory Planning in Unknown Environmentscited by 3
  16. 2025Reachability Barrier Networks: Learning Hamilton-Jacobi Solutions for Smooth and Flexible Control Barrier Functionscited by 3
  17. 2025Generative AI for Autonomous Driving: A Reviewcited by 3
  18. 2025Provably Optimal Reinforcement Learning under Safety Filteringcited by 3
  19. 2024RuleFuser: An Evidential Bayes Approach for Rule Injection in Imitation Learned Planners and Predictors for Robustness under Distribution Shiftscited by 2
  20. 2025A Survey of Reinforcement Learning-Based Motion Planning for Autonomous Driving: Lessons Learned from a Driving Task Perspectivecited by 2
  21. 2025ORN-CBF: Learning Observation-conditioned Residual Neural Control Barrier Functions via Hypernetworkscited by 2
  22. 2025Out-of-Distribution Detection for Safety Assurance of AI and Autonomous Systemscited by 2
  23. 2025Scalable Verification of Neural Control Barrier Functions Using Linear Bound Propagationcited by 2
  24. 2025ResponsibleRobotBench: Benchmarking Responsible Robot Manipulation using Multi-modal Large Language Modelscited by 2
  25. 2026Shields to Guarantee Probabilistic Safety in MDPscited by 2
  26. 2024Who Plays First? Optimizing the Order of Play in Stackelberg Games with Many Robotscited by 1
  27. 2024Deep Reinforcement Learning for Reach-Avoid-Stay Problemscited by 1
  28. 2024Safe PDE Boundary Control with Neural Operatorscited by 1
  29. 2025SPoRt -- Safe Policy Ratio: Certified Training and Deployment of Task Policies in Model-Free RLcited by 1
  30. 2025Follow the STARs: Dynamic ω-Regular Shielding of Learned Policiescited by 1
  31. 2025Safety-Aware Imitation Learning via MPC-Guided Disturbance Injectioncited by 1
  32. 2025From Refusal to Recovery: A Control-Theoretic Approach to Generative AI Guardrailscited by 1
  33. 2025Learning Neural Control Barrier Functions from Expert Demonstrations using Inverse Constraint Learningcited by 1
  34. 2025Predictive Safety Shield for Dyna-Q Reinforcement Learningcited by 1
  35. 2026Learning Contextual Runtime Monitors for Safe AI-Based Autonomycited by 1
  36. 2026CN-CBF: Composite Neural Control Barrier Function for Robot Navigation in Dynamic Environmentscited by 1
  37. 2026Toward Generalist Neural Motion Planners for Robotic Manipulators: Challenges and Opportunitiescited by 1
  38. 2026Value Functions for Temporal Logic: Optimal Policies and Safety Filterscited by 1

50 most cited of 88 All 88 (JSON)