Information-Driven Active Perception for k-step Predictive Safety Monitoring

TL;DR

This paper presents an active perception policy framework for predictive safety monitoring in partially observable stochastic systems, optimizing sensor queries to maximize information gain about future safety states under resource constraints.

Contribution

It introduces a novel approach using k-step Shannon entropy minimization with observable operators for efficient policy synthesis in safety-critical systems.

Findings

Effective sensor query scheduling improves safety prediction accuracy.

The method outperforms baseline approaches in dynamic congestion scenarios.

The approach efficiently computes information gain under limited sensing budgets.

Abstract

This work studies the synthesis of active perception policies for predictive safety monitoring in partially observable stochastic systems. Operating under strict sensing and communication budgets, the proposed monitor dynamically schedules sensor queries to maximize information gain about the safety of future states. The underlying stochastic dynamics are captured by a labeled hidden Markov model (HMM), with safety requirements defined by a deterministic finite automaton (DFA). To enable active information acquisition, we introduce minimizing k-step Shannon conditional entropy of the safety of future states as a planning objective, under the constraint of a limited sensor query budget. Using observable operators, we derive an efficient algorithm to compute the k-step conditional entropy and analyze key properties of the conditional entropy gradient with respect to policy parameters. We validate the effectiveness of the method for predictive safety monitoring through a dynamic congestion game example.