Interval POMDP Shielding for Imperfect-Perception Agents

2026-04-22 · William Scarbro, Ravi Mangal 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.

📄 PDF Abstract BibTeX arXiv:2604.20728

Code (0)

등록된 구현이 없습니다.

Conformal Safety Shielding for Imperfect-Perception Agents

2025-06-12 · William Scarbro, Calum Imrie, Sinem Getir Yaman, Kavan Fatehi 외

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 con…

Conformal Prediction State Estimation

Safe POMDP Online Planning via Shielding

2023-09-19 · Shili Sheng, David Parker, Lu Feng

Partially observable Markov decision processes (POMDPs) have been widely used in many robotic applications for sequential decision-making under uncertainty. POMDP online planning algorithms such as Partially Observable M…

Autonomous Driving Decision Making Decision Making Under Uncertainty Sequential Decision Making

Multi-agent active perception with prediction rewards

2020-10-22 · NeurIPS 2020 12 · Mikko Lauri, Frans A. Oliehoek

Multi-agent active perception is a task where a team of agents cooperatively gathers observations to compute a joint estimate of a hidden variable. The task is decentralized and the joint estimate can only be computed af…

Prediction

Mobile Target Search with Imperfect Perception: A Partially Observable Stochastic Game Theoretical Approach

2026-06-18 · Hanzheng Zhang, Shu Liang, Shuyu Liu arxiv

This paper investigates mobile target search under imperfect perceptions caused by sensor limitations, malicious jamming, or communication noise. Searchers and targets operate in a grid-shaped area with bounded mobility,…

Safe Multi-Agent Reinforcement Learning via Shielding

2021-01-27 · Ingy Elsayed-Aly, Suda Bharadwaj, Christopher Amato, Rüdiger Ehlers 외

Multi-agent reinforcement learning (MARL) has been increasingly used in a wide range of safety-critical applications, which require guaranteed safety (e.g., no unsafe states are ever visited) during the learning process.…

Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)