The uncertainty quantification of prediction models (e.g., neural networks) is crucial for their adoption in many robotics applications. This is arguably as important as making accurate predictions, especially for safety-critical applications such as self-driving cars. This paper proposes our approach to uncertainty quantification in the context of visual localization for autonomous driving, where we predict locations from images. Our proposed framework estimates probabilistic uncertainty by creating a sensor error model that maps an internal output of the prediction model to the uncertainty. The sensor error model is created using multiple image databases of visual localization, each with ground-truth location. We demonstrate the accuracy of our uncertainty prediction framework using the Ithaca365 dataset, which includes variations in lighting, weather (sunny, snowy, night), and alignment errors between databases. We analyze both the predicted uncertainty and its incorporation into a Kalman-based localization filter. Our results show that prediction error variations increase with poor weather and lighting condition, leading to greater uncertainty and outliers, which can be predicted by our proposed uncertainty model. Additionally, our probabilistic error model enables the filter to remove ad hoc sensor gating, as the uncertainty automatically adjusts the model to the input data

翻译：预测模型（如神经网络）的不确定性量化对于其在机器人领域中的实际应用至关重要。其重要性可与准确预测相提并论，尤其对于自动驾驶等安全关键应用而言。本文提出了一种面向自动驾驶视觉定位场景的不确定性量化方法，该方法通过图像预测位置信息。我们提出的框架通过构建传感器误差模型来估计概率不确定性，该模型将预测模型的内部输出映射为不确定性度量。该传感器误差模型利用多个带有真实位置标注的视觉定位图像数据库构建而成。我们采用包含光照变化、天气条件（晴天、雪天、夜间）及数据库间对齐误差的Ithaca365数据集，验证了所提不确定性预测框架的准确性。我们分析了预测不确定性及其在基于卡尔曼滤波的定位滤波器中的融合效果。结果表明，恶劣天气和光照条件会导致预测误差变化增大，从而产生更大的不确定性和离群值，而本文提出的不确定性模型能够有效预测这些变化。此外，我们的概率误差模型使滤波器能够移除启发式传感器门控机制，因为不确定性会自动根据输入数据调整模型参数。