Measuring the Influence of Environmental Conditions on Automotive Lidar Sensors

Abstract

Safety validation of automated driving functions is a major challenge that is partly tackled by means of simulation-based testing. The virtual validation approach always entails the modeling of automotive perception sensors and their environment. In the real world, these sensors are exposed to adverse influences by environmental conditions such as rain, fog, snow, etc. Therefore, such influences need to be reflected in the simulation models. In this publication, a novel data set is introduced and analyzed. This data set contains lidar data with synchronized reference measurements of weather conditions from a stationary long-term experiment. Recorded weather conditions comprise fog, rain, snow, and direct sunlight. The data are analyzed by pairing lidar values, such as the number of detections in the atmosphere, with weather parameters such as rain rate in mm/h. This results in expectation values, which can directly be utilized for stochastic modeling or model calibration and validation. The results show vast differences in the number of atmospheric detections, range distribution, and attenuation between the different sensors of the data set.

Bayesian inference of visibility in fog and smoke artificial conditions from 3D-LiDAR point clouds

“…Future work could include the production of a better quality dataset (especially for smoke). The inference model could also be trained and tested on real outdoor acquisitions, with for example the dataset proposed in [36]. Finally, the temporal evolution of visibility could be taken into account to improve the classification over time, with for example a Bayesian histogram filter.…”

Performance Verification of Autonomous Driving LiDAR Sensors under Rainfall Conditions in Darkroom

“…During rainfalls, sensing efficacy began to decline at a rainfall intensity of 10 mm/h, and at 50 mm/h, target detection was essentially nullified. However, it was observed that varying levels of snowfall did not lead to a marked decline in the LiDAR’s sensing capabilities [ 24 ]. Recently, many researchers have been researching to improve the recognition rate of autonomous driving by converging LiDAR and image sensors.…”

Camera-LiDAR Fusion Method with Feature Switch Layer for Object Detection Networks

“…al.’s studies show that LiDAR’s intensity for cars and people or LiDAR’s point-cloud density decreases in fog and rain situations. In adverse weather, the point-cloud-based recognition study was solved by changing the network structure or input expression by analyzing data characteristics [ 15 , 24 , 25 , 26 ].…”