Related papers: A Comparison of Uncertainty Estimation Approaches in Deep Learning Components for Autonomous Vehicle Applications

A Comparison of Uncertainty Estimation Approaches in Deep Learning Components for Autonomous Vehicle Applications

URL: http://arxiv.org/abs/2006.15172v2
Date: Thu, 2 Jul 2020 15:11:31 GMT
Title: A Comparison of Uncertainty Estimation Approaches in Deep Learning Components for Autonomous Vehicle Applications
Authors: Fabio Arnez (1), Huascar Espinoza (1), Ansgar Radermacher (1) and Fran\c{c}ois Terrier (1) ((1) CEA LIST)
Abstract summary: Key factor for ensuring safety in Autonomous Vehicles (AVs) is to avoid any abnormal behaviors under undesirable and unpredicted circumstances. Different methods for uncertainty quantification have recently been proposed to measure the inevitable source of errors in data and models. These methods require a higher computational load, a higher memory footprint, and introduce extra latency, which can be prohibitive in safety-critical applications.
Score: 0.0
License: http://creativecommons.org/licenses/by/4.0/
Abstract: A key factor for ensuring safety in Autonomous Vehicles (AVs) is to avoid any abnormal behaviors under undesirable and unpredicted circumstances. As AVs increasingly rely on Deep Neural Networks (DNNs) to perform safety-critical tasks, different methods for uncertainty quantification have recently been proposed to measure the inevitable source of errors in data and models. However, uncertainty quantification in DNNs is still a challenging task. These methods require a higher computational load, a higher memory footprint, and introduce extra latency, which can be prohibitive in safety-critical applications. In this paper, we provide a brief and comparative survey of methods for uncertainty quantification in DNNs along with existing metrics to evaluate uncertainty predictions. We are particularly interested in understanding the advantages and downsides of each method for specific AV tasks and types of uncertainty sources.