Effect of Weather on the Performance of Autonomous Vehicle LiDAR Sensors

Abstract

Given the significant technological advances over the past few years, autonomous vehicles are gradually entering the industrialization stage. Light detection and ranging (LiDAR) sensors are seeing increased use in autonomous vehicles. However, the final implementation of the technology remains undetermined because major automotive manufacturers have just started selecting providers for data-collection units that can be introduced in commercial vehicles. Autonomous driving tests are, up to now, handled mostly in sunny environments, such as California or Texas. However, the quality of the detection under fog, rain and snow, especially if they are extreme, becomes severely degraded, especially regarding range. In this work the performance of LiDAR sensors under adverse weather conditions and the effects of LiDAR channels on object detection were investigated. Results showed that fog severely affected LiDAR performance. Rain also had a slight effect on performance, but snow did not affect LiDAR performance. Results also showed that both dense fog and heavy rain affected object and operating range detection by LiDAR sensors.