As autonomous systems increasingly rely on Deep Neural Networks (DNN) to implement the navigation pipeline functions, uncertainty estimation methods have become paramount for estimating confidence in DNN predictions. Bayesian Deep Learning (BDL) offers a principled approach to model uncertainties in DNNs. However, in DNN-based systems, not all the components use uncertainty estimation methods and typically ignore the uncertainty propagation between them. This paper provides a method that considers the uncertainty and the interaction between BDL components to capture the overall system uncertainty. We study the effect of uncertainty propagation in a BDL-based system for autonomous aerial navigation. Experiments show that our approach allows us to capture useful uncertainty estimates while slightly improving the system's performance in its final task. In addition, we discuss the benefits, challenges, and implications of adopting BDL to build dependable autonomous systems.
翻译:由于自主系统日益依赖深神经网络来履行导航管道功能,不确定性估计方法已成为估计对DNN预测的信心的首要方法。巴伊西亚深层学习(BDL)为DNN的不确定性模型提供了原则性方法。然而,在基于DNN的系统中,并非所有组成部分都使用不确定性估计方法,通常忽视两者之间的不确定性传播。本文提供了一种方法,考虑到BDL各组成部分之间的不确定性和相互作用,以捕捉整个系统的不确定性。我们研究了以BDL为基础的自动空中导航系统中不确定性传播的影响。实验表明,我们的方法使我们能够捕捉有用的不确定性估计数,同时略微改进系统在最后任务中的绩效。此外,我们讨论了采用BDL来建立可依赖的自主系统的好处、挑战和影响。