# 物理AI中的静默故障：自主系统运行时动作授权的文献综述

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-05-23 08:00
- AIHOT 分数：43
- AIHOT 链接：https://aihot.virxact.com/items/cmpwe0tqq022rslsnbxl1xiea
- 原文链接：https://arxiv.org/abs/2606.00090

## AI 摘要

物理AI系统将多模态观测、语言指令和学习的世界表征转化为具有物理后果的动作。其安全风险在于，黑盒模型可能自信、看似合理地发出动作，但产生由传感器漂移或分布偏移等导致的“静默”故障。这篇文献综述分析了机器人基础模型、世界模型、安全控制等多个领域的进展，指出当前没有单一技术能在黑盒物理AI模型和物理执行之间提供完整的运行时授权边界。文章提出了静默故障的定义、运行时护栏的功能分类以及相应的评估框架。

## 正文

Physical AI systems increasingly map multimodal observations, language instructions, and learned world representations into physically consequential actions. Robotics foundation models, vision-language-action models, and world-model-based autonomous systems can condition decisions that move vehicles, robots, drones, and industrial machines. This transition exposes a safety problem that is not fully captured by conventional AI content moderation or by classical robot safety alone: a black-box model may issue a physically consequential action while appearing confident, plausible, and semantically aligned. The resulting failure can be silent, arising from sensor drift, occlusion, state-estimation error, distribution shift, hallucinated affordances, or invalid physical assumptions before downstream hardware controllers detect a violation. Across embodied foundation models, world models, robotics simulation, embodied safety benchmarks, safe control, runtime assurance, uncertainty estimation, verification, and guardrail evaluation, model capability and safety mechanisms have advanced along largely separate technical tracks. A recurring gap synthesized here is that no single stream surveyed in this review supplies a complete runtime authorization boundary between black-box Physical AI models and physical execution. The resulting analysis develops a bounded problem formulation, a definition of silent physical-action failure, a taxonomy of runtime guardrail functions, and evaluation requirements for comparing guardrails as Physical AI assurance mechanisms.