A Comparison of Uncertainty Estimation Approaches in Deep Learning Components for Autonomous Vehicle Applications
This is an incremental survey for researchers and practitioners in autonomous vehicles, focusing on evaluating methods to improve safety under uncertain conditions.
The paper compares uncertainty estimation approaches in deep neural networks for autonomous vehicles, highlighting that these methods often require higher computational resources and latency, which can be prohibitive in safety-critical applications.
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.