Ontology-Grounded World Models for Failure Diagnosis and Closed-Loop Repair in Physical AI Systems

📄 arXiv: 2608.13901v1 📥 PDF

作者: Kailin Wang, Haoxiang Jie, Yaoyuan Yan, Jiacheng Zhou, Zhiyou Heng

分类: cs.RO

发布日期: 2026-08-14


💡 一句话要点

提出Ontology-Grounded世界模型以解决物理AI系统中的故障诊断问题

🎯 匹配领域: 支柱二:RL算法与架构 (RL & Architecture)

关键词: 故障诊断 闭环修复 本体结构 物理AI系统 任务谓词 智能机器人 自动化

📋 核心要点

  1. 现有的EV-WM方法在故障诊断中未能有效记录任务谓词和修正机制,导致修正过程不够明确。
  2. 论文提出的Onto-EV-WM通过引入本体结构,增强了故障诊断和修正过程的可解释性和有效性。
  3. 实验结果表明,Onto-EV-WM在多个任务上成功率达到85%以上,明显优于传统方法的表现。

📝 摘要(中文)

EV-WM通过特征和事件评分来表示候选质量,但这些评分未能明确记录未满足的任务谓词、可用的修正机制的路径标签或修正后的接受结果。本文提出了Onto-EV-WM,这是一个基于本体的诊断和验证门控修正接口,层叠在EV-WM之上,而非替代其世界模型架构。实现的任务局部TBox定义了实体类型、谓词签名和约束;源特定的基础映射将预测或模拟观察到的状态映射到任务ABoxes;确定性规则在分配路径标签时保留每个缺失谓词及其参数。实验结果显示,Onto-EV-WM在多个任务上表现优异,成功率显著提升。

🔬 方法详解

问题定义:本文旨在解决物理AI系统中的故障诊断和闭环修复问题。现有的EV-WM方法未能有效记录未满足的任务谓词和修正机制,导致修正过程不够明确和高效。

核心思路:论文提出的Onto-EV-WM通过引入本体结构,增强了故障诊断和修正过程的可解释性。该方法在EV-WM的基础上,增加了任务局部的TBox和源特定的基础映射,以更好地管理和记录任务状态。

技术框架:整体架构包括任务局部的TBox、源特定的基础映射和确定性规则模块。TBox定义了实体类型和谓词签名,基础映射将状态映射到任务ABoxes,确定性规则则用于保留缺失谓词及其参数。

关键创新:最重要的创新在于引入了本体结构,使得故障诊断过程更加系统化和可解释。与现有方法相比,Onto-EV-WM能够更有效地记录和处理任务谓词,提升了修正的成功率。

关键设计:在设计中,任务局部TBox和源特定的基础映射是关键模块,确保了系统能够准确地映射和记录状态。确定性规则的设计也确保了在分配路径标签时,能够保留每个缺失谓词及其参数。

🖼️ 关键图片

fig_0
img_1
img_2

📊 实验亮点

实验结果显示,Onto-EV-WM在PointMaze评估中与EV-WM均报告94%的成功率,但最终状态距离显著降低,分别为0.90573和0.61177。此外,在LIBERO-Goal任务中,成功率达到93.8%,在LIBERO-Plus注册任务中成功完成85%的任务,表现优异。

🎯 应用场景

该研究的潜在应用领域包括智能机器人、自动化生产线和复杂系统的故障诊断与修复。通过提升物理AI系统的故障处理能力,能够显著提高系统的可靠性和效率,具有重要的实际价值和广泛的应用前景。

📄 摘要(原文)

EV-WM represents candidate quality with feature and event scores, but these scores do not explicitly record an unmet task predicate, a route label for an available correction mechanism, or a post-correction acceptance result. We present Onto-EV-WM, an ontology-grounded diagnosis and verification-gated correction interface layered above EV-WM rather than a replacement world-model architecture. The implemented task-local TBox defines entity types, predicate signatures, and constraints; source-specific grounding maps predicted or simulator-observed states to task ABoxes; and deterministic rules retain each missing predicate and its arguments when assigning a route label. Learned or heuristic proposers remain separate from this symbolic interface; native task predicates determine acceptance, and the bounded protocol determines whether a failed verification is retried. In the aligned PointMaze evaluation, EV-WM and Onto-EV-WM both report 94% success, with mean final-state distances of 0.90573 and 0.61177, respectively; the separately budgeted search reaches 100% success. On LIBERO-Goal, the ontology represents failed task conditions as typed records, retains their predicate arguments, and associates them with the declared source/joint correction route and predicate-gated acceptance; the complete configuration reports 93.8% corrected-window success on seed 0 and 94.05 +- 0.30% across four evaluation-sampling seeds. On the fixed 10,030-task LIBERO-Plus registry, Onto-EV-WM succeeds on 8,526 tasks (85.00%), with suite-level success rates of 65.98% for LIBERO-10, 91.39% for LIBERO-Goal, and 91.38% for both LIBERO-Object and LIBERO-Spatial. These numbers report the performance of the complete ontology-grounded configurations under the tested simulator protocols; an ontology-only causal share is not measured separately, and real-robot recovery is not evaluated.