Probabilistic Uncertainty Quantification of Prediction Models with Application to Visual Localization
Probabilistic Uncertainty Quantification of Prediction Models with Application to Visual Localization
复制标题
DOI：
10.1109/icra48891.2023.10160298
复制
发表时间：
2023-05
期刊：
影响因子：
--
通讯作者：
Junan Chen;Josephine Monica;Wei-Lun Chao;Mark E. Campbell
中科院分区：
文献类型：
--
作者：
Junan Chen;Josephine Monica;Wei-Lun Chao;Mark E. Campbell
预测模型的不确定性量化（例如，神经网络）对于它们在许多机器人应用中的采用至关重要。这可以说与准确预测一样重要，特别是对于安全关键型应用，如自动驾驶汽车。本文提出了我们的方法，不确定性量化的背景下，自动驾驶的视觉定位，我们预测的位置从图像。我们提出的框架估计概率的不确定性，通过创建一个传感器误差模型，将预测模型的内部输出映射到不确定性。使用多个视觉定位图像数据库创建传感器误差模型，每个图像数据库具有地面实况位置。我们使用Ithaca365数据集证明了我们的不确定性预测框架的准确性，该数据集包括照明，天气（晴天，下雪，夜晚）和数据库之间的对齐误差的变化。我们分析了预测的不确定性，并将其纳入到一个基于卡尔曼定位滤波器。我们的研究结果表明，预测误差的变化与恶劣的天气和照明条件，导致更大的不确定性和离群值，这可以预测我们提出的不确定性模型。此外，我们的概率误差模型使过滤器能够去除特设传感器门控，因为不确定性会自动调整模型以适应输入数据。
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.