Loading [a11y]/accessibility-menu.js
CARLA Simulator-Based Evaluation Framework Development of Lane Detection Accuracy Performance Under Sensor Blockage Caused by Heavy Rain for Autonomous Vehicle | IEEE Journals & Magazine | IEEE Xplore

CARLA Simulator-Based Evaluation Framework Development of Lane Detection Accuracy Performance Under Sensor Blockage Caused by Heavy Rain for Autonomous Vehicle


Abstract:

As self-driving cars have been developed targeting level 4 and 5 autonomous driving, the capability of the vehicle to handle environmental effects has been considered imp...Show More

Abstract:

As self-driving cars have been developed targeting level 4 and 5 autonomous driving, the capability of the vehicle to handle environmental effects has been considered importantly. The sensors installed on autonomous vehicles can be easily affected by blockages (e.g., rain, snow, dust, fog, and others) covering the surface of them. In a virtual environment, we can safely observe the behavior of the vehicle and the degradation of the sensors by blockages. In this letter, the CARLA simulator-based evaluation framework has been developed and the assessment of lane detection performance under sensor blockage by heavy rain, which was analyzed by using the experimental data. Thus, we thoroughly note that the accuracy of lane detection for the autonomous vehicle has been decreased as the rainfall rate increases, and the impact of the blockage is more critical to curved lanes than straight lanes. Finally, we have suggested a critical rainfall rate causing safety failures of the autonomous vehicles, based on reasonably established rainfall equation based on experimental rain datasets.
Published in: IEEE Robotics and Automation Letters ( Volume: 7, Issue: 4, October 2022)
Page(s): 9977 - 9984
Date of Publication: 20 July 2022

ISSN Information:

Funding Agency:


I. Introduction

Recently, with increasing interests and needs for autonomous vehicles, many researches of the self-driving cars have been aiming for the level 4 and 5 in autonomous driving technology [21], [22], [24]. When it comes to beyond level 4 in autonomous driving technology, the vehicle should be able to deal with various kinds of situations around the self-driving vehicle in order to arrive at the targeted destination successfully. Thus, to accomplish its goal even under adverse weather conditions, the autonomous vehicle need to detect its surrounding situations and classify them to solve the threating features in the diverse driving environments. For the identification and classification of the threats, it is necessary to study on sensor blockages (e.g., rain, snow, dust, fog, and others), which are caused by direct contact on sensors or indirect effects on the sensors according to their properties [23], [24]. Since autonomous vehicles in the future should be robust enough against harsh weather conditions, it is necessary for the engineers to scientifically investigate what kinds of difficulties and effectiveness due to abnormal weather conditions with diverse sensors installed the autonomous vehicle are involved in recognizing properly the environmental situations [25]–[27].

Contact IEEE to Subscribe

References

References is not available for this document.