Modern advances in the technical developments of Advanced Driver Assistance
Systems (ADAS) have elevated autonomous vehicle (AV) operations to a new height.
Vehicles equipped with sensor based ADAS have been positively contributing to
safer roads. As the automotive industry strives for SAE Level 5 full driving
autonomy, challenges inevitably arise to ensure ADAS performance and reliability
in all driving scenarios, especially in adverse weather conditions, during which
ADAS sensors such as optical cameras and LiDARs suffer performance degradation,
leading to inaccuracy and inability to provide crucial environmental information
for object detection. Currently, the difficulty to simulate realistic and
dynamic adverse weather scenarios experienced by vehicles in a controlled
environment becomes one of the challenges that hinders further ADAS development.
While outdoor testing encounters unpredictable environmental variables, indoor
testing methods, such as using spray nozzles in a wind tunnel, are often
unrealistic due to the atomization of the spray droplets, causing the droplet
size distributions to deviate from real-life conditions. A novel full-scale rain
simulation system is developed and implemented into the ACE Climatic Aerodynamic
Wind Tunnel at Ontario Tech University with the goal of quantifying ADAS sensor
performance when driving in rain. The designed system is capable of recreating a
wide range of dynamic rain intensity experienced by the vehicle at different
driving speeds, along with the corresponding droplet size distributions.
Proposed methods to evaluate optical cameras are discussed, with sample results
of object detection performance and image evaluation metrics presented.
Additionally, the rain simulation system showcases repeatable testing
environments for soiling mitigation developments. It also demonstrates the
potential to further broaden the scope of testing, such as training object
detection datasets, as well as exploring the possibilities of using artificial
intelligence to expand and predict the rain system control strategies and target
rain conditions.