mlsanityData to 7 Oct 2026

Interval POMDP Shielding for Imperfect-Perception Agents

arXiv 2604.20728 ↗First posted 22 Apr 2026cs.AI cs.SY eess.SYcited by 0

Not on the map. Why?

Abstract (arXiv)

Autonomous systems that rely on learned perception can make unsafe decisions when sensor readings are misclassified. We study shielding for this setting: given a proposed action, a shield blocks actions that could violate safety. We consider the common case where system dynamics are known but perception uncertainty must be estimated from finite labeled data. From these data we build confidence intervals for the probabilities of perception outcomes and use them to model the system as a finite Interval Partially Observable Markov Decision Process with discrete states and actions. We then propose an algorithm to compute a conservative set of beliefs over the underlying state that is consistent with the observations seen so far. This enables us to construct a runtime shield that comes with a finite-horizon guarantee: with high probability over the training data, if the true perception uncertainty rates lie within the learned intervals, then every action admitted by the shield satisfies a stated lower bound on safety. Experiments on four case studies show that our shielding approach (and variants derived from it) improves the safety of the system over state-of-the-art baselines.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 18 of its 42 references that are in the map. First posted on arXiv 22 Apr 2026.

Builds on

18 of 42 references.

References · 18

  1. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,274
  2. 2019Conformal Prediction Under Covariate Shiftcited by 511
  3. 2017Safe Reinforcement Learning via Shieldingcited by 427
  4. 2021Adaptive Conformal Inference Under Distribution Shiftcited by 360
  5. 2019Control Barrier Functions: Theory and Applicationscited by 332
  6. 2022Safe Reinforcement Learning via Shielding under Partial Observabilitycited by 49
  7. 2020Formal Analysis and Redesign of a Neural Network-Based Aircraft Taxiing System with VerifAIcited by 21
  8. 2021Automated Verification and Synthesis of Stochastic Hybrid Systems: A Surveycited by 20
  9. 2023Closed-loop Analysis of Vision-based Autonomous Systems: A Case Studycited by 18
  10. 2022Extending Conformal Prediction to Hidden Markov Models with Exact Validity via de Finetti's Theorem for Markov Chainscited by 8
  11. 2023Conformal Off-Policy Evaluation in Markov Decision Processescited by 6
  12. 2024Conformal Predictive Systems Under Covariate Shiftcited by 5
6 more
  1. 2019Computing Probabilistic Controlled Invariant Setscited by 4
  2. 2014Conservative Inference Rule for Uncertain Reasoning under Incompletenesscited by 3
  3. 2025Conformal Safety Shielding for Imperfect-Perception Agentscited by 3
  4. 2017Distribution Bisimilarity via the Power of Convex Algebrascited by 1
  5. 2025Towards Unified Probabilistic Verification and Validation of Vision-Based Autonomycited by 1
  6. 2026Perception-Based Beliefs for POMDPs with Visual Observationscited by 1

Built on by

Not cited yet.