Quantification of Uncertainty and Its Applications to Complex Domain for Autonomous Vehicles Perception System

Over the last decades,deep neural networks have been penetrated into all fields of science and the real world. As a result of the lack of quantifiable data and model uncertaint, deep learning is frequently brittle,illogical, and challenging to provide trustworthy assurance for autonomous vehicles(AV) perception.This hole is filled by the suggested approach to uncertainty quantification. Nevertheless, most of the previous studies focused on the methodology and there is still a lack of research on the application of AV. To our knowledge, this paper is the first time to review the application of uncertainty in the field of AV perception and localization. In the first place, this paper analyzes the sources of uncertainty in autonomous perception,including the uncertainty brought on by sensor internal and external factors as well as the sensor distortion caused on by complex scenes. In the second place,we propose an evaluation criterion and use the criterion to carry out a quantitative analysis of perception field of application for autonomous vehicles,and we discuss the mainstream datasets. Thirdly, we put forward a number of open issues and raise some future research directions, which is of guiding significance to readers who are beginning to enter this field.We believe that epistemic uncertainty is currently the dominant research direction and that there is still a long way to go in the study of aleatoric uncertainty.And our paper will be devoted to promoting the development of uncertainty research of AV perception.