一句话：提出 ODiSAR，用 Transformer 数字孪生预测机器人状态，结合重构误差与 MC dropout 检测并解释 OOD 行为。
复杂不确定环境中的自适应机器人需主动检测异常行为，包括分布外（OOD）情形。论文提出基于数字孪生的 OOD 检测方法 ODiSAR：使用 Transformer 数字孪生预测机器人状态，以重构误差和 Monte Carlo dropout 量化不确定性，并融合二者检测未见条件下的 OOD；同时提供可解释层，将潜在 OOD 关联到具体机器人状态以支持自适应。作者为办公室导航机器人和海上船舶导航分别构建数字孪生，评估轨迹与船舶运动预测及 OOD 事件检测。结果显示最高约 98% AUROC、96% TNR@TPR95 和 95% F1，并能给出可解释洞见。
Self-adaptive robots (SARs) in complex, uncertain environments must proactively detect and address abnormal behaviors, including out-of-distribution (OOD) cases. To this end, digital twins offer a valuable solution for OOD detection. Thus, we present a digital twin-based approach for OOD detection (ODiSAR) in SARs. ODiSAR uses a Transformer-based digital twin to forecast SAR states and employs reconstruction error and Monte Carlo dropout for uncertainty quantification. By combining reconstruction error with predictive variance, the digital twin effectively detects OOD behaviors, even in previously unseen conditions. The digital twin also includes an explainability layer that links potential OOD to specific SAR states, offering insights for self-adaptation. We evaluated ODiSAR by creating digital twins of two industrial robots: one navigating an office environment, and another performing maritime ship navigation. In both cases, ODiSAR forecasts SAR behaviors (i.e., robot trajectories and vessel motion) and proactively detects OOD events. Our results showed that ODiSAR achieved high detection performance—up to 98% AUROC, 96% TNR@TPR95, and 95% F1-score—while providing interpretable insights to support self-adaptation.
@inproceedings{paperbot9442,
title = {Out of Distribution Detection in Self-adaptive Robots with AI-powered Digital Twins},
author = {Erblin Isaku and Hassan Sartaj and Shaukat Ali and Beatriz Sanguino and Tongtong Wang and Guoyuan Li and Houxiang Zhang and Thomas Peyrucain},
booktitle = {ASE},
year = {2025},
doi = {10.1109/ase63991.2025.00281}
}