mlsanityData to 14 Oct 2026

Conformal Safety Shielding for Imperfect-Perception Agents

arXiv 2506.17275 ↗First posted 12 Jun 2025eess.SY cs.AI cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

We consider the problem of safe control in discrete autonomous agents that use learned components for imperfect perception (or more generally, state estimation) from high-dimensional observations. We propose a shield construction that provides run-time safety guarantees under perception errors by restricting the actions available to an agent, modeled as a Markov decision process, as a function of the state estimates. Our construction uses conformal prediction for the perception component, which guarantees that for each observation, the predicted set of estimates includes the actual state with a user-specified probability. The shield allows an action only if it is allowed for all the estimates in the predicted set, resulting in local safety. We also articulate and prove a global safety property of existing shield constructions for perfect-perception agents bounding the probability of reaching unsafe states if the agent always chooses actions prescribed by the shield. We illustrate our approach with a case-study of an experimental autonomous system that guides airplanes on taxiways using high-dimensional perception DNNs.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 20 of its 33 references that are in the map. First posted on arXiv 12 Jun 2025.

Builds on

20 of 33 references.

References · 20

  1. 2021A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantificationcited by 792
  2. 2022Safe Reinforcement Learning via Shielding under Partial Observabilitycited by 56
  3. 2020Guaranteeing Safety of Learned Perception Modules via Measurement-Robust Control Barrier Functionscited by 33
  4. 2024Formal Verification and Control with Conformal Predictioncited by 26
  5. 2022Learning Safe, Generalizable Perception-based Hybrid Control with Certificatescited by 24
  6. 2022Online Shielding for Reinforcement Learningcited by 22
  7. 2020Formal Analysis and Redesign of a Neural Network-Based Aircraft Taxiing System with VerifAIcited by 21
  8. 2019Robust Guarantees for Perception-Based Controlcited by 20
  9. 2021Learning Robust Output Control Barrier Functions from Safe Expert Demonstrationscited by 20
  10. 2021Verifying Controllers with Convolutional Neural Network-based Perception: A Case for Intelligible, Safe, and Precise Abstractionscited by 19
  11. 2023Closed-loop Analysis of Vision-based Autonomous Systems: A Case Studycited by 18
  12. 2022Enforcing safety for vision-based controllers via Control Barrier Functions and Neural Radiance Fieldscited by 16
8 more
  1. 2023Safe Perception-Based Control under Stochastic Sensor Uncertainty using Conformal Predictioncited by 16
  2. 2021TEMPEST -- Synthesis Tool for Reactive Systems and Shields in Probabilistic Environmentscited by 13
  3. 2022Differentiable Control Barrier Functions for Vision-based End-to-End Autonomous Drivingcited by 10
  4. 2023Safe POMDP Online Planning via Shieldingcited by 8
  5. 2018Safe Reinforcement Learning via Probabilistic Shieldscited by 7
  6. 2024Leveraging Approximate Model-based Shielding for Probabilistic Safety Guarantees in Continuous Environmentscited by 5
  7. 2025State-Dependent Conformal Perception Bounds for Neuro-Symbolic Verification of Autonomous Systemscited by 3
  8. 2025Scenario-based Compositional Verification of Autonomous Systems with Neural Perceptioncited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Safety Generalization Under Distribution Shift in Safe Reinforcement Learning: A Diabetes Testbedcited by 1
  2. 2026Latent Q-Barrier Shielding for Safe In-Context Reinforcement Learningcited by 1
  3. 2026Interval POMDP Shielding for Imperfect-Perception Agentscited by 0