# Interval POMDP Shielding for Imperfect-Perception Agents

arXiv: https://arxiv.org/abs/2604.20728 · HTML: https://mlsanity.com/paper/2604.20728/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 42 references that are in the map.
- First posted on arXiv 22 Apr 2026.

## Builds on (most cited first, 18 of 18)

- [Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift](https://mlsanity.com/paper/1906.02530/) (2019)
- [Conformal Prediction Under Covariate Shift](https://mlsanity.com/paper/1904.06019/) (2019)
- [Safe Reinforcement Learning via Shielding](https://mlsanity.com/paper/1708.08611/) (2017)
- [Adaptive Conformal Inference Under Distribution Shift](https://mlsanity.com/paper/2106.00170/) (2021)
- [Control Barrier Functions: Theory and Applications](https://mlsanity.com/paper/1903.11199/) (2019)
- [Safe Reinforcement Learning via Shielding under Partial Observability](https://mlsanity.com/paper/2204.00755/) (2022)
- [Formal Analysis and Redesign of a Neural Network-Based Aircraft Taxiing System with VerifAI](https://mlsanity.com/paper/2005.07173/) (2020)
- [Automated Verification and Synthesis of Stochastic Hybrid Systems: A Survey](https://mlsanity.com/paper/2101.07491/) (2021)
- [Closed-loop Analysis of Vision-based Autonomous Systems: A Case Study](https://mlsanity.com/paper/2302.04634/) (2023)
- [Extending Conformal Prediction to Hidden Markov Models with Exact Validity via de Finetti's Theorem for Markov Chains](https://mlsanity.com/paper/2210.02271/) (2022)
- [Computing Probabilistic Controlled Invariant Sets](https://mlsanity.com/paper/1905.04117/) (2019)
- [Conformal Off-Policy Evaluation in Markov Decision Processes](https://mlsanity.com/paper/2304.02574/) (2023)
- [Conformal Predictive Systems Under Covariate Shift](https://mlsanity.com/paper/2404.15018/) (2024)
- [Conservative Inference Rule for Uncertain Reasoning under Incompleteness](https://mlsanity.com/paper/1401.3471/) (2014)
- [Conformal Safety Shielding for Imperfect-Perception Agents](https://mlsanity.com/paper/2506.17275/) (2025)
- [Distribution Bisimilarity via the Power of Convex Algebras](https://mlsanity.com/paper/1707.02344/) (2017)
- [Towards Unified Probabilistic Verification and Validation of Vision-Based Autonomy](https://mlsanity.com/paper/2508.14181/) (2025)
- [Perception-Based Beliefs for POMDPs with Visual Observations](https://mlsanity.com/paper/2602.05679/) (2026)

## 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.