Silent Failures in Physical AI: A Literature Review of Runtime Action Authorization for Autonomous Systems

• URL: http://arxiv.org/abs/2606.00090v1
• Date: Sat, 23 May 2026 16:48:03 GMT
• Title: Silent Failures in Physical AI: A Literature Review of Runtime Action Authorization for Autonomous Systems
• Abstract summary: Physical AI systems increasingly map multimodal observations, language instructions, and learned world representations into physically consequential actions.<n>This transition exposes a safety problem that is not fully captured by conventional AI content moderation.<n>No single stream surveyed supplies a complete runtime authorization boundary between black-box Physical AI models and physical execution.
• Score: 1.9544213396776273
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• GAUGE: A Measurement-Grounded Benchmark for Physical Fidelity in Simulation Engines and Video World Models [66.77745044586173]
  GAUGE is a real-world-grounded diagnostic benchmark for evaluating how numerical simulators and generative video world models reproduce or deviate from real-world physics.<n>We benchmark Isaac Sim, Genesis, and Newton on 14 task families using generalized trajectory errors, and evaluate 6 image-to-video models on 5 rigid-body tasks.<n>Our results reveal no uniformly faithful physics engine, with the largest discrepancies arising in impulsive contact, rapid textile motion, and volumetric deformation.
  arXiv  Detail & Related papers  (2026-08-06T12:19:38Z)
• A Physics-Grounded Benchmark for Multi-Agent Dynamics in World Models [96.64934195520802]
  We introduce CrashTwin, a physics-grounded evaluation framework designed to stress-test the physical trustworthiness of world models.<n>CrashTwin couples a diverse dataset of multi-agent collision scenarios, comprising 25K controllable synthetic 12K in-the-wild real-world collision sequences.<n>We propose a diagnostic suite that systematically evaluates three dimensions:-temporal consistency, momentum and kinetic energy conservation, and world-dynamics integrity.
  arXiv  Detail & Related papers  (2026-06-27T06:13:35Z)
• Provably Secure Agent Guardrail [89.79561918065122]
  Existing defense architectures rely on empirical semantic guardrails and probabilistic large model adjudicators.<n>This paper proposes a new security paradigm for agents based on the fundamental limitations of logical reasoning.
  arXiv  Detail & Related papers  (2026-05-28T02:12:41Z)
• Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms [61.29786895012393]
  Vision-Language-Action (VLA) models are emerging as a unified substrate for embodied intelligence.<n>This survey provides a unified and up-to-date overview of safety in Vision-Language-Action models.
  arXiv  Detail & Related papers  (2026-04-26T15:58:19Z)
• Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses [168.50301366360344]
  Embodied Artificial Intelligence (Embodied AI) integrates perception, cognition, planning, and interaction into agents that operate in safety-critical environments.<n>Unlike digital AI systems, embodied agents must act under uncertain sensing, incomplete knowledge, and dynamic human-robot interactions.<n>This survey provides a comprehensive review of safety research in embodied AI, examining attacks and defenses across the full embodied pipeline.
  arXiv  Detail & Related papers  (2026-03-28T13:21:44Z)
• What Breaks Embodied AI Security:LLM Vulnerabilities, CPS Flaws,or Something Else? [28.12412876058788]
  Embodied AI systems are rapidly transitioning from controlled environments to safety critical real-world deployments.<n>Unlike disembodied AI, failures in embodied intelligence lead to irreversible physical consequences.<n>We argue that a significant class of failures arises from embodiment-induced system-level mismatches.
  arXiv  Detail & Related papers  (2026-02-19T13:29:00Z)
• RobotArena $\infty$: Scalable Robot Benchmarking via Real-to-Sim Translation [47.79800816696372]
  Real-world testing of manipulation policies is labor-intensive at scale, and difficult to reproduce.<n>Existing simulation benchmarks are similarly limited, as they train and test policies within the same synthetic domains.<n>In this paper, we introduce a new benchmarking framework that overcomes these challenges by shifting VLA evaluation into large-scale simulated augmented environments.
  arXiv  Detail & Related papers  (2025-10-27T17:41:38Z)
• From Refusal to Recovery: A Control-Theoretic Approach to Generative AI Guardrails [12.84192844049763]
  Most AI guardrails rely on output classification based on labeled datasets and human-specified criteria.<n>We build predictive guardrails that monitor an AI system's outputs in real time and proactively correct risky outputs to safe ones.<n>Our experiments in simulated driving and e-commerce settings demonstrate that control-theoretic guardrails can reliably steer agents clear of catastrophic outcomes.
  arXiv  Detail & Related papers  (2025-10-15T16:30:57Z)
• Can AI Perceive Physical Danger and Intervene? [16.825608691806988]
  New safety challenges emerge when AI interacts with the physical world.<n>How well do state-of-the-art foundation models understand common-sense facts about physical safety?
  arXiv  Detail & Related papers  (2025-09-25T22:09:17Z)
• From Physics to Machine Learning and Back: Part II - Learning and Observational Bias in PHM [52.64097278841485]
  Review examines how incorporating learning and observational biases through physics-informed modeling and data strategies can guide models toward physically consistent and reliable predictions.<n>Fast adaptation methods including meta-learning and few-shot learning are reviewed alongside domain generalization techniques.
  arXiv  Detail & Related papers  (2025-09-25T14:15:43Z)
• ANNIE: Be Careful of Your Robots [48.89876809734855]
  We present the first systematic study of adversarial safety attacks on embodied AI systems.<n>We show attack success rates exceeding 50% across all safety categories.<n>Results expose a previously underexplored but highly consequential attack surface in embodied AI systems.
  arXiv  Detail & Related papers  (2025-09-03T15:00:28Z)
• Constrained Decoding for Robotics Foundation Models [12.916330118607918]
  We introduce SafeDec, a constrained decoding framework for autoregressive robot foundation models.<n>Task-specific safety rules are expressed as Signal Temporal Logic (STL) formulas and are enforced at inference time with minimal overhead.<n>Our method ensures that generated actions provably satisfy STL specifications under assumed dynamics at runtime without retraining.
  arXiv  Detail & Related papers  (2025-09-01T19:17:40Z)
• Real-Time Anomaly Detection and Reactive Planning with Large Language Models [18.57162998677491]
  Foundation models, e.g., large language models (LLMs), trained on internet-scale data possess zero-shot capabilities. We present a two-stage reasoning framework that incorporates the judgement regarding potential anomalies into a safe control framework. This enables our monitor to improve the trustworthiness of dynamic robotic systems, such as quadrotors or autonomous vehicles.
  arXiv  Detail & Related papers  (2024-07-11T17:59:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.