Improving Robustness of Deep Neural Networks for Aerial Navigation by Incorporating Input Uncertainty

TL;DR

This paper proposes a method to incorporate input uncertainty into Bayesian Deep Learning control policies for aerial navigation, enhancing robustness in Out-of-Distribution scenarios.

Contribution

It introduces a novel approach to handle input uncertainty in deep learning for autonomous aerial navigation, improving system robustness.

Findings

Improved robustness of navigation policy in OoD scenarios

Effective propagation of input uncertainty through the system

Potential for safer autonomous aerial operations

Abstract

Uncertainty quantification methods are required in autonomous systems that include deep learning (DL) components to assess the confidence of their estimations. However, to successfully deploy DL components in safety-critical autonomous systems, they should also handle uncertainty at the input rather than only at the output of the DL components. Considering a probability distribution in the input enables the propagation of uncertainty through different components to provide a representative measure of the overall system uncertainty. In this position paper, we propose a method to account for uncertainty at the input of Bayesian Deep Learning control policies for Aerial Navigation. Our early experiments show that the proposed method improves the robustness of the navigation policy in Out-of-Distribution (OoD) scenarios.