Interval POMDP Shielding for Imperfect-Perception Agents

• URL: http://arxiv.org/abs/2604.20728v1
• Date: Wed, 22 Apr 2026 16:12:37 GMT
• Title: Interval POMDP Shielding for Imperfect-Perception Agents
• Abstract summary: Autonomous systems that rely on learned perception can make unsafe decisions when sensor readings are misclassified.<n>We study shielding: given a proposed action, a shield blocks actions that could violate safety.<n>Experiments show that our shielding approach improves the safety of the system over state-of-the-art baselines.
• Score: 0.5729426778193399
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Adaptive Probabilistic Shielding by Learning MDPs for Safe Reinforcement Learning [13.82610991481171]
  We study the problem of computing a shield in the setting where the transition graph of the MDP is known.<n>As the RL agent explores the environment, we estimate the transition probabilities.<n>While the shield may be conservative initially, it adapts as the model estimate becomes more precise.
  arXiv  Detail & Related papers  (2026-08-20T09:37:44Z)
• Conformal Safety Shielding for Imperfect-Perception Agents [7.5422935754618825]
  We consider the problem of safe control in discrete autonomous agents that use learned components for imperfect perception.<n>We propose a shield construction that provides run-time safety guarantees under perception errors.
  arXiv  Detail & Related papers  (2025-06-12T17:37:29Z)
• Safety Margins for Reinforcement Learning [53.10194953873209]
  We show how to leverage proxy criticality metrics to generate safety margins. We evaluate our approach on learned policies from APE-X and A3C within an Atari environment.
  arXiv  Detail & Related papers  (2023-07-25T16:49:54Z)
• Safety Shielding under Delayed Observation [59.86192283565134]
  Shields are correct-by-construction enforcers that guarantee safe execution. Shields should pick the safe corrective actions in such a way that future interferences are most likely minimized. We present the first integration of shields in a realistic driving simulator.
  arXiv  Detail & Related papers  (2023-07-05T10:06:10Z)
• Approximate Shielding of Atari Agents for Safe Exploration [83.55437924143615]
  We propose a principled algorithm for safe exploration based on the concept of shielding. We present preliminary results that show our approximate shielding algorithm effectively reduces the rate of safety violations.
  arXiv  Detail & Related papers  (2023-04-21T16:19:54Z)
• Safe Perception-Based Control under Stochastic Sensor Uncertainty using Conformal Prediction [27.515056747751053]
  We propose a perception-based control framework that quantifies estimation uncertainty of perception maps. We also integrate these uncertainty representations into the control design. We demonstrate the effectiveness of our proposed perception-based controller for a LiDAR-enabled F1/10th car.
  arXiv  Detail & Related papers  (2023-04-01T01:45:53Z)
• ProBF: Learning Probabilistic Safety Certificates with Barrier Functions [31.203344483485843]
  The control barrier function is a useful tool to guarantee safety if we have access to the ground-truth system dynamics. In practice, we have inaccurate knowledge of the system dynamics, which can lead to unsafe behaviors. We show the efficacy of this method through experiments on Segway and Quadrotor simulations.
  arXiv  Detail & Related papers  (2021-12-22T20:18:18Z)
• Sampling-Based Robust Control of Autonomous Systems with Non-Gaussian Noise [59.47042225257565]
  We present a novel planning method that does not rely on any explicit representation of the noise distributions. First, we abstract the continuous system into a discrete-state model that captures noise by probabilistic transitions between states. We capture these bounds in the transition probability intervals of a so-called interval Markov decision process (iMDP)
  arXiv  Detail & Related papers  (2021-10-25T06:18:55Z)
• CertainNet: Sampling-free Uncertainty Estimation for Object Detection [65.28989536741658]
  Estimating the uncertainty of a neural network plays a fundamental role in safety-critical settings. In this work, we propose a novel sampling-free uncertainty estimation method for object detection. We call it CertainNet, and it is the first to provide separate uncertainties for each output signal: objectness, class, location and size.
  arXiv  Detail & Related papers  (2021-10-04T17:59:31Z)
• Learning Uncertainty For Safety-Oriented Semantic Segmentation In Autonomous Driving [77.39239190539871]
  We show how uncertainty estimation can be leveraged to enable safety critical image segmentation in autonomous driving. We introduce a new uncertainty measure based on disagreeing predictions as measured by a dissimilarity function. We show experimentally that our proposed approach is much less computationally intensive at inference time than competing methods.
  arXiv  Detail & Related papers  (2021-05-28T09:23:05Z)
• Learning to Act Safely with Limited Exposure and Almost Sure Certainty [1.0323063834827415]
  This paper aims to put forward the concept that learning to take safe actions in unknown environments, even with probability one guarantees, can be achieved without the need for exploratory trials. We first focus on the canonical multi-armed bandit problem and seek to study the intrinsic trade-offs of learning safety in the presence of uncertainty.
  arXiv  Detail & Related papers  (2021-05-18T18:05:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.