AWARE：用于机器人动力学预测与自省的自适应世界模型异常识别框架

Adaptive World-Models for Anomaly Recognition (AWARE): A Framework for Robot Dynamics Prediction and Introspection

AI 导读

AWARE 是一个世界模型框架，仅通过外部相机监测即可完成异常检测，无需依赖机载传感器接入被监控系统。在 240 条真实机器人吊臂轨迹（含载荷碰撞与电机退化）的评估中，AWARE 在噪声较大的纯相机状态估计下，异常分类比最强基线提升 26%。其推断的动力学参数还可解码定位故障源，对退化电机的识别准确率达 88%。

正文 · 原文

View PDF HTML (experimental)

Abstract:Unrecognized anomalies in critical infrastructure can rapidly cascade into catastrophic physical or operational failures. Current anomaly detection approaches often rely on direct access to the monitored system by utilizing onboard sensors, such as motor encoders, to detect anomalous states. However, legacy hardware often lacks these sensors, or strict security protocols may prohibit access altogether. We therefore present AWARE, a world model framework that is capable of anomaly detection using only external camera monitoring via system dynamics estimation and state prediction. Evaluated across 240 real-world robotic crane trajectories, including payload collisions and motor degradations, AWARE demonstrates a 26% improvement in anomaly classification over our strongest baseline under noisy, camera-only state estimation. Furthermore, the inferred dynamics parameter can be decoded to identify the source of faults, localizing the degrading motor with 88% accuracy.

Subjects:	Robotics (cs.RO); Artificial Intelligence (cs.AI)
Cite as:	arXiv:2610.32742 [cs.RO]
	(or arXiv:2610.32742v1 [cs.RO] for this version)
	https://doi.org/10.48550/arXiv.2610.32742 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: George Mavroghenis [view email]
[v1] Fri, 23 Oct 2026 14:54:36 UTC (25,927 KB)