# Capture Uncertainties in Deep Neural Networks for Safe Operation of Autonomous Driving Vehicles

arXiv: https://arxiv.org/abs/2108.05118 · HTML: https://mlsanity.com/paper/2108.05118/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Aug 2021.

## Built on by (most cited first, 3 of 3)

- [Confidence Estimation Using Unlabeled Data](https://mlsanity.com/paper/2307.10440/) (2023)
- [Nonlinear MCMC for Bayesian Machine Learning](https://mlsanity.com/paper/2202.05621/) (2022)
- [CTS: Sim-to-Real Unsupervised Domain Adaptation on 3D Detection](https://mlsanity.com/paper/2406.18129/) (2024)

## Abstract (arXiv)

Uncertainties in Deep Neural Network (DNN)-based perception and vehicle's motion pose challenges to the development of safe autonomous driving vehicles. In this paper, we propose a safe motion planning framework featuring the quantification and propagation of DNN-based perception uncertainties and motion uncertainties. Contributions of this work are twofold: (1) A Bayesian Deep Neural network model which detects 3D objects and quantitatively captures the associated aleatoric and epistemic uncertainties of DNNs; (2) An uncertainty-aware motion planning algorithm (PU-RRT) that accounts for uncertainties in object detection and ego-vehicle's motion. The proposed approaches are validated via simulated complex scenarios built in CARLA. Experimental results show that the proposed motion planning scheme can cope with uncertainties of DNN-based perception and vehicle motion, and improve the operational safety of autonomous vehicles while still achieving desirable efficiency.