Modular Safety Guardrails Are Necessary for Foundation-Model-Enabled Robots in the Real World

TL;DR

This paper emphasizes the importance of modular safety guardrails for foundation-model-enabled robots, addressing complex safety challenges beyond physical constraints by proposing a layered monitoring and intervention architecture.

Contribution

It introduces the concept of modular safety guardrails with cross-layer co-design to enhance safety in robots using foundation models, filling a gap in existing approaches.

Findings

Modular safety guardrails improve safety enforcement efficiency.

Cross-layer co-design enables less conservative safety interventions.

Existing methods are insufficient for open-ended, adaptive tasks.

Abstract

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.