mlsanityData to 14 Oct 2026

Efficient Dynamic Shielding for Parametric Safety Specifications

arXiv 2505.22104 ↗First posted 28 May 2025cs.AI cs.LG cs.LOcited by 0

Not on the map. Why?

Abstract (arXiv)

Shielding has emerged as a promising approach for ensuring safety of AI-controlled autonomous systems. The algorithmic goal is to compute a shield, which is a runtime safety enforcement tool that needs to monitor and intervene the AI controller's actions if safety could be compromised otherwise. Traditional shields are designed statically for a specific safety requirement. Therefore, if the safety requirement changes at runtime due to changing operating conditions, the shield needs to be recomputed from scratch, causing delays that could be fatal. We introduce dynamic shields for parametric safety specifications, which are succinctly represented sets of all possible safety specifications that may be encountered at runtime. Our dynamic shields are statically designed for a given safety parameter set, and are able to dynamically adapt as the true safety specification (permissible by the parameters) is revealed at runtime. The main algorithmic novelty lies in the dynamic adaptation procedure, which is a simple and fast algorithm that utilizes known features of standard safety shields, like maximal permissiveness. We report experimental results for a robot navigation problem in unknown territories, where the safety specification evolves as new obstacles are discovered at runtime. In our experiments, the dynamic shields took a few minutes for their offline design, and took between a fraction of a second and a few seconds for online adaptation at each step, whereas the brute-force online recomputation approach was up to 5 times slower.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 32 of its 53 references that are in the map. First posted on arXiv 28 May 2025.

Builds on

32 of 53 references.

References · 32

  1. 2018World Modelscited by 1,513
  2. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 744
  3. 2017Safe Reinforcement Learning via Shieldingcited by 449
  4. 2018Verisig: verifying safety properties of hybrid systems with neural network controllerscited by 84
  5. 2021Safe Multi-Agent Reinforcement Learning via Shieldingcited by 61
  6. 2022Safe Reinforcement Learning via Shielding under Partial Observabilitycited by 56
  7. 2019Robust Model Predictive Shielding for Safe Reinforcement Learning with Stochastic Dynamicscited by 47
  8. 2015Shield Synthesis: Runtime Enforcement for Reactive Systemscited by 42
  9. 2023Safe Reinforcement Learning via Probabilistic Logic Shieldscited by 42
  10. 2021Towards Scalable Verification of Deep Reinforcement Learningcited by 33
  11. 2016Funnel Libraries for Real-Time Robust Feedback Motion Planningcited by 29
  12. 2022Online Shielding for Reinforcement Learningcited by 22
20 more
  1. 2020Adaptive Shielding under Uncertaintycited by 18
  2. 2024Dynamic Model Predictive Shielding for Provably Safe Reinforcement Learningcited by 15
  3. 2021TEMPEST -- Synthesis Tool for Reactive Systems and Shields in Probabilistic Environmentscited by 13
  4. 2024Verification-Guided Shielding for Deep Reinforcement Learningcited by 13
  5. 2021SHARP: Shielding-Aware Robust Planning for Safe and Efficient Human-Robot Interactioncited by 12
  6. 2024Shield Synthesis for LTL Modulo Theoriescited by 12
  7. 2022Dynamic Shielding for Reinforcement Learning in Black-Box Environmentscited by 11
  8. 2019Shield Synthesis for Real: Enforcing Safety in Cyber-Physical Systemscited by 8
  9. 2017Planning, Fast and Slow: A Framework for Adaptive Real-Time Safe Trajectory Planningcited by 7
  10. 2014Discounting in LTLcited by 6
  11. 2015Feedback Refinement Relations for the Synthesis of Symbolic Controllerscited by 6
  12. 2020EVA-Planner: Environmental Adaptive Quadrotor Planningcited by 5
  13. 2025Adaptive Shielding via Parametric Safety Proofscited by 5
  14. 2023Forward LTLf Synthesis: DPLL At Workcited by 4
  15. 2023Context-triggered Abstraction-based Control Designcited by 4
  16. 2024Efficient Shield Synthesis via State-Space Transformationcited by 4
  17. 2023Synthesizing Permissive Winning Strategy Templates for Parity Gamescited by 3
  18. 2023Safety Shielding under Delayed Observationcited by 3
  19. 2024Realizable Continuous-Space Shields for Safe Reinforcement Learningcited by 3
  20. 2021Symbolic Control for Stochastic Systems via Finite Parity Gamescited by 1

Built on by

Not cited yet.