AWARE：仅靠外部摄像头实现机器人动力学预测与异常识别的世界模型框架

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

AI 导读

AWARE 是一个仅依赖外部摄像头监控、通过系统动力学估计与状态预测完成异常检测的世界模型框架，无需电机编码器等机载传感器。在 240 条真实机器人吊车轨迹（含负载碰撞与电机退化）上，其异常分类性能在噪声条件下比最强基线提升 26%。推断出的动力学参数还可解码定位故障源，识别退化电机的准确率达 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)

来源：arXiv cs.AI · arxiv.org