RoboSafe: Safeguarding Embodied Agents via Executable Safety Logic

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wang, Le, Ying, Zonghao, Yang, Xiao, Zou, Quanchen, Yin, Zhenfei, Li, Tianlin, Yang, Jian, Yang, Yaodong, Liu, Aishan, Liu, Xianglong
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909975725473792
author Wang, Le
Ying, Zonghao
Yang, Xiao
Zou, Quanchen
Yin, Zhenfei
Li, Tianlin
Yang, Jian
Yang, Yaodong
Liu, Aishan
Liu, Xianglong
author_facet Wang, Le
Ying, Zonghao
Yang, Xiao
Zou, Quanchen
Yin, Zhenfei
Li, Tianlin
Yang, Jian
Yang, Yaodong
Liu, Aishan
Liu, Xianglong
contents Embodied agents powered by vision-language models (VLMs) are increasingly capable of executing complex real-world tasks, yet they remain vulnerable to hazardous instructions that may trigger unsafe behaviors. Runtime safety guardrails, which intercept hazardous actions during task execution, offer a promising solution due to their flexibility. However, existing defenses often rely on static rule filters or prompt-level control, which struggle to address implicit risks arising in dynamic, temporally dependent, and context-rich environments. To address this, we propose RoboSafe, a hybrid reasoning runtime safeguard for embodied agents through executable predicate-based safety logic. RoboSafe integrates two complementary reasoning processes on a Hybrid Long-Short Safety Memory. We first propose a Backward Reflective Reasoning module that continuously revisits recent trajectories in short-term memory to infer temporal safety predicates and proactively triggers replanning when violations are detected. We then propose a Forward Predictive Reasoning module that anticipates upcoming risks by generating context-aware safety predicates from the long-term safety memory and the agent's multimodal observations. Together, these components form an adaptive, verifiable safety logic that is both interpretable and executable as code. Extensive experiments across multiple agents demonstrate that RoboSafe substantially reduces hazardous actions (-36.8% risk occurrence) compared with leading baselines, while maintaining near-original task performance. Real-world evaluations on physical robotic arms further confirm its practicality. Code will be released upon acceptance.
format Preprint
id arxiv_https___arxiv_org_abs_2512_21220
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RoboSafe: Safeguarding Embodied Agents via Executable Safety Logic
Wang, Le
Ying, Zonghao
Yang, Xiao
Zou, Quanchen
Yin, Zhenfei
Li, Tianlin
Yang, Jian
Yang, Yaodong
Liu, Aishan
Liu, Xianglong
Artificial Intelligence
Computer Vision and Pattern Recognition
Robotics
Embodied agents powered by vision-language models (VLMs) are increasingly capable of executing complex real-world tasks, yet they remain vulnerable to hazardous instructions that may trigger unsafe behaviors. Runtime safety guardrails, which intercept hazardous actions during task execution, offer a promising solution due to their flexibility. However, existing defenses often rely on static rule filters or prompt-level control, which struggle to address implicit risks arising in dynamic, temporally dependent, and context-rich environments. To address this, we propose RoboSafe, a hybrid reasoning runtime safeguard for embodied agents through executable predicate-based safety logic. RoboSafe integrates two complementary reasoning processes on a Hybrid Long-Short Safety Memory. We first propose a Backward Reflective Reasoning module that continuously revisits recent trajectories in short-term memory to infer temporal safety predicates and proactively triggers replanning when violations are detected. We then propose a Forward Predictive Reasoning module that anticipates upcoming risks by generating context-aware safety predicates from the long-term safety memory and the agent's multimodal observations. Together, these components form an adaptive, verifiable safety logic that is both interpretable and executable as code. Extensive experiments across multiple agents demonstrate that RoboSafe substantially reduces hazardous actions (-36.8% risk occurrence) compared with leading baselines, while maintaining near-original task performance. Real-world evaluations on physical robotic arms further confirm its practicality. Code will be released upon acceptance.
title RoboSafe: Safeguarding Embodied Agents via Executable Safety Logic
topic Artificial Intelligence
Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2512.21220