Modular Safety Guardrails Are Necessary for Foundation-Model-Enabled Robots in the Real World
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910011034173440 |
|---|---|
| author | Kim, Joonkyung Chen, Wenxi Soleymanzadeh, Davood Ding, Yi Gao, Xiangbo Tu, Zhengzhong Zhang, Ruqi Fei, Fan Veer, Sushant Lyu, Yiwei Zheng, Minghui Gu, Yan |
| author_facet | Kim, Joonkyung Chen, Wenxi Soleymanzadeh, Davood Ding, Yi Gao, Xiangbo Tu, Zhengzhong Zhang, Ruqi Fei, Fan Veer, Sushant Lyu, Yiwei Zheng, Minghui Gu, Yan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_04056 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Modular Safety Guardrails Are Necessary for Foundation-Model-Enabled Robots in the Real World Kim, Joonkyung Chen, Wenxi Soleymanzadeh, Davood Ding, Yi Gao, Xiangbo Tu, Zhengzhong Zhang, Ruqi Fei, Fan Veer, Sushant Lyu, Yiwei Zheng, Minghui Gu, Yan Systems and Control Robotics 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. |
| title | Modular Safety Guardrails Are Necessary for Foundation-Model-Enabled Robots in the Real World |
| topic | Systems and Control Robotics |
| url | https://arxiv.org/abs/2602.04056 |