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
Silent Failures in Physical AI: A Literature Review of Runtime Action Authorization for Autonomous Systems
AI总结：
本文综述了物理AI系统中黑箱模型发出看似合理但实际错误的物理动作导致的静默故障问题，提出了运行时防护栏的分类和评估要求。
摘要：
物理AI系统越来越多地将多模态观测、语言指令和学习的世界表示映射为具有物理后果的动作。机器人基础模型、视觉-语言-动作模型和基于世界模型的自主系统可以决定移动车辆、机器人、无人机和工业机器的决策。这种转变暴露了一个传统AI内容审核或经典机器人安全无法完全捕获的安全问题：黑箱模型可能发出一个物理后果的动作，同时表现出自信、合理和语义对齐。由此产生的故障可能是静默的，源于传感器漂移、遮挡、状态估计误差、分布偏移、幻觉的可供性，或在下游硬件控制器检测到违规之前的无效物理假设。在具身基础模型、世界模型、机器人仿真、具身安全基准、安全控制、运行时保证、不确定性估计、验证和防护栏评估中，模型能力和安全机制沿着大致分离的技术轨道发展。这里综合的一个反复出现的差距是，本综述调查的单一流都没有提供黑箱物理AI模型与物理执行之间的完整运行时授权边界。由此产生的分析发展了一个有界的问题表述、静默物理动作故障的定义、运行时防护栏功能的分类，以及比较防护栏作为物理AI保证机制的评估要求。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
