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

10/26/2021
by   Fabio Arnez, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/12/2023

Towards Dependable Autonomous Systems Based on Bayesian Deep Learning Components

As autonomous systems increasingly rely on Deep Neural Networks (DNN) to...
research
04/29/2022

Tailored Uncertainty Estimation for Deep Learning Systems

Uncertainty estimation bears the potential to make deep learning (DL) sy...
research
06/04/2022

Quantifying and Using System Uncertainty in UAV Navigation

As autonomous systems increasingly rely on Deep Neural Networks (DNN) to...
research
10/15/2020

Certifying Neural Network Robustness to Random Input Noise from Samples

Methods to certify the robustness of neural networks in the presence of ...
research
07/05/2023

Transgressing the boundaries: towards a rigorous understanding of deep learning and its (non-)robustness

The recent advances in machine learning in various fields of application...
research
05/20/2020

A Bayesian - Deep Learning model for estimating Covid-19 evolution in Spain

This work proposes a semi-parametric approach to estimate Covid-19 (SARS...
research
07/31/2019

Uncertainty Quantification in Deep Learning for Safer Neuroimage Enhancement

Deep learning (DL) has shown great potential in medical image enhancemen...

Please sign up or login with your details

Forgot password? Click here to reset