EMBGuard: Constructing Hazard-Aware Guardrails for Safe Planning in Embodied Agents
EMBGuard:为具身智能体安全规划构建危险感知护栏
机构 * Independent Researcher(独立研究者) ; Department of Biomedical Engineering(生物医学工程系) ; the Department of Intelligent Precision Healthcare Convergence, Sungkyunkwan University(智能精准医疗融合系,全州大学) ; Department of Artificial Intelligence, Yonsei University(人工智能系,延世大学)
专题命中 机器人数据与评测 :embodied agent(title,abstract)
AI总结 提出首个基于MLLM的具身安全护栏EMBGuard,通过解耦物理风险推理与智能体策略,评估(视觉观察,动作)对来识别危险配置并提供自然语言解释,同时构建训练数据集EMBHazard和基准测试EMBGuardTest,在紧凑模型尺寸下达到与专有MLLM竞争的性能并降低误报率。
Comments Accepted at ICML 2026