mlsanityData to 14 Oct 2026

A predictive safety filter for learning-based control of constrained nonlinear dynamical systems

arXiv 1812.05506 ↗First posted 13 Dec 2018eess.SY cs.LG cs.SYcited by 118

Not on the map. Why?

Cited by 38 in Deep reinforcement learning methods, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

The transfer of reinforcement learning (RL) techniques into real-world applications is challenged by safety requirements in the presence of physical limitations. Most RL methods, in particular the most popular algorithms, do not support explicit consideration of state and input constraints. In this paper, we address this problem for nonlinear systems with continuous state and input spaces by introducing a predictive safety filter, which is able to turn a constrained dynamical system into an unconstrained safe system and to which any RL algorithm can be applied `out-of-the-box'. The predictive safety filter receives the proposed control input and decides, based on the current system state, if it can be safely applied to the real system, or if it has to be modified otherwise. Safety is thereby established by a continuously updated safety policy, which is based on a model predictive control formulation using a data-driven system model and considering state and input dependent uncertainties.

Key facts. Cited by 118 papers in the map (data through 14 Oct 2026). First posted on arXiv 13 Dec 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 7; 2022: 11; 2023: 14; 2024: 17; 2025: 19; 2026: 50.

118 papers.

Sort:

By area:

  1. 2021Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learningcited by 371
  2. 2023The Safety Filter: A Unified View of Safety-Critical Control in Autonomous Systemscited by 88
  3. 2022Constrained Policy Optimization via Bayesian World Modelscited by 57
  4. 2023SafeDreamer: Safe Reinforcement Learning with World Modelscited by 54
  5. 2022Provably Safe Reinforcement Learning: Conceptual Analysis, Survey, and Benchmarkingcited by 34
  6. 2023Physics-Informed Machine Learning for Modeling and Control of Dynamical Systemscited by 28
  7. 2022Provably Safe Reinforcement Learning via Action Projection using Reachability Analysis and Polynomial Zonotopescited by 26
  8. 2025Synthesis of Model Predictive Control and Reinforcement Learning: Survey and Classificationcited by 26
  9. 2024ActSafe: Active Exploration with Safety Constraints for Reinforcement Learningcited by 23
  10. 2021Safe Reinforcement Learning with Chance-constrained Model Predictive Controlcited by 20
  11. 2022GoSafeOpt: Scalable Safe Exploration for Global Optimization of Dynamical Systemscited by 17
  12. 2024Safety Filtering While Training: Improving the Performance and Sample Efficiency of Reinforcement Learning Agentscited by 17
38 more
  1. 2025CBF-RL: Safety Filtering Reinforcement Learning in Training with Control Barrier Functionscited by 17
  2. 2024Gameplay Filters: Robust Zero-Shot Safety through Adversarial Imaginationcited by 16
  3. 2023Active Uncertainty Reduction for Safe and Efficient Interaction Planning: A Shielding-Aware Dual Control Approachcited by 15
  4. 2021Risk-averse autonomous systems: A brief history and recent developments from the perspective of optimal controlcited by 12
  5. 2021SHARP: Shielding-Aware Robust Planning for Safe and Efficient Human-Robot Interactioncited by 12
  6. 2024Safety Filters for Black-Box Dynamical Systems by Learning Discriminating Hyperplanescited by 12
  7. 2025SafeFlowMatcher: Safe and Fast Planning using Flow Matching with Control Barrier Functionscited by 12
  8. 2021Safe Chance Constrained Reinforcement Learning for Batch Process Controlcited by 11
  9. 2022Log Barriers for Safe Black-box Optimization with Application to Safe Reinforcement Learningcited by 11
  10. 2026Failure-Aware RL: Reliable Offline-to-Online Reinforcement Learning with Self-Recovery for Real-World Manipulationcited by 11
  11. 2022End-to-End Imitation Learning with Safety Guarantees using Control Barrier Functionscited by 10
  12. 2023Approximate non-linear model predictive control with safety-augmented neural networkscited by 9
  13. 2026Embodied Foundation Models at the Edge: A Survey of Deployment Constraints and Mitigation Strategiescited by 9
  14. 2022Contingency-constrained economic dispatch with safe reinforcement learningcited by 8
  15. 2023Shielded Reinforcement Learning for Hybrid Systemscited by 8
  16. 2024Safe Guaranteed Exploration for Non-linear Systemscited by 8
  17. 2024Learning to Boost the Performance of Stable Nonlinear Systemscited by 7
  18. 2025A view on learning robust goal-conditioned value functions: Interplay between RL and MPCcited by 7
  19. 2023Adaptive Stochastic Nonlinear Model Predictive Control with Look-ahead Deep Reinforcement Learning for Autonomous Vehicle Motion Controlcited by 6
  20. 2024The Duality of Generative AI and Reinforcement Learning in Robotics: A Reviewcited by 6
  21. 2026Safe Exploration via Policy Priorscited by 6
  22. 2021Provably Correct Training of Neural Network Controllers Using Reachability Analysiscited by 5
  23. 2022Safe Reinforcement Learning using Data-Driven Predictive Controlcited by 5
  24. 2024A Dynamic Safety Shield for Safe and Efficient Reinforcement Learning of Navigation Taskscited by 5
  25. 2025SIGN: Safety-Aware Image-Goal Navigation for Autonomous Drones via Reinforcement Learningcited by 5
  26. 2025Safe Reinforcement Learning using Action Projection: Safeguard the Policy or the Environment?cited by 5
  27. 2025From Demonstrations to Safe Deployment: Path-Consistent Safety Filtering for Diffusion Policiescited by 5
  28. 2023Learning-Aided Warmstart of Model Predictive Control in Uncertain Fast-Changing Trafficcited by 4
  29. 2024Reinforcement Learning with Ensemble Model Predictive Safety Certificationcited by 4
  30. 2024CommonPower: A Framework for Safe Data-Driven Smart Grid Controlcited by 4
  31. 2024Efficient Shield Synthesis via State-Space Transformationcited by 4
  32. 2025Deep FlexQP: Accelerated Nonlinear Programming via Deep Unfoldingcited by 4
  33. 2026Pixels to Proofs: Probabilistically-Safe Latent World Model Control via Parallel Conformal Robust MPCcited by 4
  34. 2022Safe Imitation Learning of Nonlinear Model Predictive Control for Flexible Robotscited by 3
  35. 2023Learning Predictive Safety Filter via Decomposition of Robust Invariant Setcited by 3
  36. 2024Safe Reinforcement Learning for Power System Control: A Reviewcited by 3
  37. 2025Provably Optimal Reinforcement Learning under Safety Filteringcited by 3
  38. 2021Safe multi-agent deep reinforcement learning for joint bidding and maintenance scheduling of generation unitscited by 2

50 most cited of 118 All 118 (JSON)