The integration of foundation models (FMs) into robotics has accelerated real-world deployment, while introducing new safety challenges arising from open-ended semantic reasoning and embodied physical action. These challenges require safety notions beyond physical constraint satisfaction. In this paper, we characterize FM-enabled robot safety along three dimensions: action safety (physical feasibility and constraint compliance), decision safety (semantic and contextual appropriateness), and human-centered safety (conformance to human intent, norms, and expectations). We argue that existing approaches, including static verification, monolithic controllers, and end-to-end learned policies, are insufficient in settings where tasks, environments, and human expectations are open-ended, long-tailed, and subject to adaptation over time. To address this gap, we propose modular safety guardrails, consisting of monitoring (evaluation) and intervention layers, as an architectural foundation for comprehensive safety across the autonomy stack. Beyond modularity, we highlight possible cross-layer co-design opportunities through representation alignment and conservatism allocation to enable faster, less conservative, and more effective safety enforcement. We call on the community to explore richer guardrail modules and principled co-design strategies to advance safe real-world physical AI deployment.

翻译：将基础模型（FMs）集成到机器人学中加速了其在现实世界的部署，同时也带来了由开放式语义推理和具身物理行为所引发的新安全挑战。这些挑战要求的安全概念超越了物理约束满足的范畴。本文中，我们从三个维度刻画基于基础模型的机器人安全：行为安全（物理可行性与约束合规性）、决策安全（语义与情境适当性）以及以人为中心的安全（符合人类意图、规范与期望）。我们认为，在任务、环境及人类期望具有开放性、长尾性并随时间动态适应的场景下，现有方法——包括静态验证、单体控制器和端到端学习策略——均存在不足。为弥补这一差距，我们提出模块化安全护栏，其由监控（评估）层与干预层构成，作为在整个自主栈中实现全面安全的架构基础。除了模块化，我们强调了通过表征对齐和保守性分配实现跨层协同设计的可能性，以实现更快速、更少保守且更有效的安全执行。我们呼吁学界探索更丰富的护栏模块和原则性的协同设计策略，以推动安全的现实世界物理人工智能部署。