In this study, we investigate a context-aware status updating system consisting of multiple sensor-estimator pairs. A centralized monitor pulls status updates from multiple sensors that are monitoring several safety-critical situations (e.g., carbon monoxide density in forest fire detection, machine safety in industrial automation, and road safety). Based on the received sensor updates, multiple estimators determine the current safety-critical situations. Due to transmission errors and limited communication resources, the sensor updates may not be timely, resulting in the possibility of misunderstanding the current situation. In particular, if a dangerous situation is misinterpreted as safe, the safety risk is high. In this paper, we introduce a novel framework that quantifies the penalty due to the unawareness of a potentially dangerous situation. This situation-unaware penalty function depends on two key factors: the Age of Information (AoI) and the observed signal value. For optimal estimators, we provide an information-theoretic bound of the penalty function that evaluates the fundamental performance limit of the system. To minimize the penalty, we study a pull-based multi-sensor, multi-channel transmission scheduling problem. Our analysis reveals that for optimal estimators, it is always beneficial to keep the channels busy. Due to communication resource constraints, the scheduling problem can be modelled as a Restless Multi-armed Bandit (RMAB) problem. By utilizing relaxation and Lagrangian decomposition of the RMAB, we provide a low-complexity scheduling algorithm which is asymptotically optimal. Our results hold for both reliable and unreliable channels. Numerical evidence shows that our scheduling policy can achieve up to 100 times performance gain over periodic updating and up to 10 times over randomized policy.

翻译：本研究探讨了一种由多个传感器-估计器对构成的上下文感知状态更新系统。中央监控器从监测多种安全关键场景（例如，森林火灾探测中的一氧化碳浓度、工业自动化中的机器安全以及道路安全）的多个传感器中拉取状态更新。多个估计器基于接收到的传感器更新来判断当前的安全关键情景。由于传输错误和有限的通信资源，传感器更新可能不及时，导致对当前情景的误判风险。特别是，当危险情景被误判为安全时，安全风险极高。本文提出了一种新颖框架，量化了因未意识到潜在危险情景而产生的惩罚。这种情景未察觉惩罚函数取决于两个关键因素：信息年龄（AoI）和观测信号值。针对最优估计器，我们给出了该惩罚函数的信息论界，以评估系统的根本性能极限。为最小化惩罚，我们研究了一种基于拉取机制的多传感器、多信道传输调度问题。分析表明，对于最优估计器，始终保持信道忙碌是有益的。由于通信资源约束，该调度问题可建模为休止多臂赌博机（RMAB）问题。通过利用RMAB的松弛和拉格朗日分解，我们提出了一种低复杂度调度算法，该算法具有渐近最优性。我们的结论适用于可靠与不可靠信道。数值结果表明，所提调度策略的性能增益可比周期性更新高至100倍，比随机策略高至10倍。