发表机构
Robotics Innovation Center, German Research Center for AI (DFKI GmbH); Airbus Defence and Space GmbH（机器人创新中心，德国人工智能研究中心（DFKI有限公司）; 空客防务与航天有限公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究基于深度学习的陀螺仪偏差校正框架的不确定性分解与可解释性，用一维卷积神经网络预测校正，通过模型集合估计认知不确定性，经实验揭示特定轴行为及扰动影响，表明两种不确定性协同良好，为状态估计和故障检测提供见解。
AI 中文摘要
这项工作研究了基于深度学习的陀螺仪偏差校正框架中的不确定性分解和可解释性。训练一维卷积神经网络从包括陀螺仪和星跟踪器测量在内的多传感器输入中预测残余角速率校正。偏差校正被发送到具有飞行代表性的陀螺恒星估计器。该网络产生平均校正和与输入相关的（异方差）偶然不确定性，而认知不确定性则通过独立训练的模型集合来估计。所提出的方法在标称条件下进行训练，并在包括加性和时间相关噪声的标称和结构化扰动中进行评估。基于梯度的归因方法应用于校正和不确定性输出，从而能够分解驱动状态更新和不确定性估计的证据。通过汇总旋转轴和状态下的归因模式，我们揭示了特定轴的行为，并表征了结构化扰动如何影响偶然和认知不确定性之间的协作。不确定性分析表明，偶然不确定性随扰动强度增加，但分布重叠且不同状态下的校准不一致。另一方面，认知不确定性给出了一个清晰的信号，随着分布偏移的发生，这个信号会变得更清晰，表示模型之间的分歧更大。这些结果表明，偶然和认知不确定性协同工作良好，并且认知不确定性在区分标称和扰动操作条件方面表现更好。这些结果为基于混合学习的状态估计组件的行为提供了见解，并激发了将不确定性用于下游监测和故障检测的应用。
英文摘要
This work investigates uncertainty decomposition and explainability in a deep learning-based framework for gyroscope bias correction. A 1-D Convolutional Neural Network is trained to predict residual angular rate corrections from multi-sensor inputs, including gyroscope and star tracker measurements. The bias corrections are sent to a flight-representative Gyro-Stellar Estimator. The network produces both mean corrections and input-dependent (heteroscedastic) aleatoric uncertainty, while epistemic uncertainty is estimated via an ensemble of independently trained models. The proposed approach is trained under nominal conditions and evaluated in both nominal and structured perturbations that include additive and temporally correlated noise. Gradient-based attribution methods are applied to both the correction and uncertainty outputs, enabling a decomposition of the evidence that drives state updates and uncertainty estimates. By aggregating attribution patterns across rotational axes and regimes, we reveal axis-specific behaviors and characterize how structured perturbations influence the collaboration between aleatoric and epistemic uncertainty. Uncertainty analysis shows that aleatoric uncertainty increases with perturbation intensity, but the distributions overlap and the calibration is not consistent across regimes. On the other hand, epistemic uncertainty gives a clear signal that gets clearer as the distributional shift happens, showing that the models disagree more. These results show that aleatoric and epistemic uncertainty work well together and that epistemic uncertainty is better at distinguishing between nominal and perturbed operating conditions. The results provide insight into the behavior of hybrid learning-based state estimation components and motivate the use of uncertainty for downstream monitoring and fault detection.
Comments21 pages, 9 Figures, EASi-Explimed Workshop within IJCAI 2026
