Towards Dependable Autonomous Systems Based on Bayesian Deep Learning Components
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 13 Oct 2026). Builds on 26 of its 42 references that are in the map. First posted on arXiv 12 Jan 2023.
Builds on
26 of 42 references.
References · 26
- 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,430
- 2013Auto-Encoding Variational Bayescited by 4,024
- 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,902
- 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,340
- 2017AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehiclescited by 518
- 2018Accurate Uncertainties for Deep Learning Using Calibrated Regressioncited by 422
- 2019A Survey of Deep Learning Techniques for Autonomous Drivingcited by 402
- 2017Concrete Dropoutcited by 227
- 2019Evaluating Scalable Bayesian Deep Learning Methods for Robust Computer Visioncited by 182
- 2019A General Framework for Uncertainty Estimation in Deep Learningcited by 119
- 2020Implicit Latent Variable Model for Scene-Consistent Motion Forecastingcited by 116
- 2018Cross-modal Deep Variational Hand Pose Estimationcited by 89
14 more
- 2018Safe Reinforcement Learning with Model Uncertainty Estimatescited by 70
- 2020Identifying Causal-Effect Inference Failure with Uncertainty-Aware Modelscited by 57
- 2018Evaluating Uncertainty Quantification in End-to-End Autonomous Driving Controlcited by 55
- 2021Autonomous Drone Racing with Deep Reinforcement Learningcited by 51
- 2016Learning and Policy Search in Stochastic Dynamical Systems with Bayesian Neural Networkscited by 49
- 2019Bayesian Variational Autoencoders for Unsupervised Out-of-Distribution Detectioncited by 35
- 2020Technology Readiness Levels for AI & MLcited by 30
- 2021Heterogeneous-Agent Trajectory Forecasting Incorporating Class Uncertaintycited by 19
- 2019Learning Visuomotor Policies for Aerial Navigation Using Cross-Modal Representationscited by 18
- 2019Practical Solutions for Machine Learning Safety in Autonomous Vehiclescited by 15
- 2020AirSim Drone Racing Labcited by 15
- 2019Learning Resilient Behaviors for Navigation Under Uncertaintycited by 11
- 2021On the Implementation of Behavior Trees in Roboticscited by 9
- 2021Improving Robustness of Deep Neural Networks for Aerial Navigation by Incorporating Input Uncertaintycited by 2
Built on by
Citing papers per year: 2024: 1.
1 paper.