Improving Robustness of Deep Neural Networks for Aerial Navigation by Incorporating Input Uncertainty
arXiv:2110.13729 · doi:10.1007/978-3-030-83906-2_17
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.
arXiv commentAccepted at the Fourth International Workshop on Artificial Intelligence Safety Engineering, WAISE 2021
References in corpus (6)
- What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
- A Survey of Deep Learning Techniques for Autonomous Driving
- A General Framework for Uncertainty Estimation in Deep Learning
- Driving Policy Transfer via Modularity and Abstraction
- Decomposition of Uncertainty in Bayesian Deep Learning for Efficient and Risk-sensitive Learning
- Model-Predictive Policy Learning with Uncertainty Regularization for Driving in Dense Traffic