Robots are increasingly operating in open-world environments where safe behavior depends on context: the same hallway may require different navigation strategies when crowded versus empty, or during an emergency versus normal operations. Traditional safety approaches enforce fixed constraints in user-specified contexts, limiting their ability to handle the open-ended contextual variability of real-world deployment. We address this gap via CORE, a safety framework that enables online contextual reasoning, grounding, and enforcement without prior knowledge of the environment (e.g., maps or safety specifications). CORE uses a vision-language model (VLM) to continuously reason about context-dependent safety rules directly from visual observations, grounds these rules in the physical environment, and enforces the resulting spatially-defined safe sets via control barrier functions. We provide probabilistic safety guarantees for CORE that account for perceptual uncertainty, and we demonstrate through simulation and real-world experiments that CORE enforces contextually appropriate behavior in unseen environments, significantly outperforming prior semantic safety methods that lack online contextual reasoning. Ablation studies validate our theoretical guarantees and underscore the importance of both VLM-based reasoning and spatial grounding for enforcing contextual safety in novel settings. We provide additional resources at https://zacravichandran.github.io/CORE.

翻译：机器人在开放世界环境中的运行日益增多，其安全行为取决于上下文：同一条走廊在拥挤与空旷时，或在紧急情况与正常操作期间，可能需要不同的导航策略。传统安全方法在用户指定的上下文中强制执行固定约束，限制了其处理现实世界部署中开放式上下文变化的能力。我们通过CORE框架来填补这一空白，该框架能够在无需环境先验知识（如地图或安全规范）的情况下实现在线上下文推理、基础化与执行。CORE利用视觉语言模型（VLM）直接从视觉观测中持续推理上下文相关的安全规则，将这些规则基础化到物理环境中，并通过控制屏障函数执行由此产生的空间定义安全集。我们为CORE提供了考虑感知不确定性的概率安全保证，并通过仿真和真实世界实验证明，CORE在未见环境中强制执行了符合上下文的行为，显著优于缺乏在线上下文推理的先前语义安全方法。消融研究验证了我们的理论保证，并强调了基于VLM的推理和空间基础化对于在新场景中执行上下文安全的重要性。更多资源请访问 https://zacravichandran.github.io/CORE。