This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Physics-Based Simulation Solutions for Testing Performance of Sensors and Perception Algorithm under Adverse Weather Conditions

Journal Article
12-05-04-0024
ISSN: 2574-0741, e-ISSN: 2574-075X
Published April 13, 2022 by SAE International in United States
Physics-Based Simulation Solutions for Testing Performance of Sensors
                    and Perception Algorithm under Adverse Weather Conditions
Sector:
Citation: Ozarkar, S., Gely, S., and Zhou, K., "Physics-Based Simulation Solutions for Testing Performance of Sensors and Perception Algorithm under Adverse Weather Conditions," SAE Intl. J CAV 5(4):297-312, 2022, https://doi.org/10.4271/12-05-04-0024.
Language: English

Abstract:

Weather conditions such as rain, fog, snow, and dust can adversely impact sensing and perception, limit operational envelopes, and compromise the safety and reliability of advanced driver-assistance systems and autonomous vehicles. Physical testing of an autonomous system in a weather laboratory and on-road is costly and slow and exposes the system to only a limited set of weather conditions. To overcome the limitations of physical testing, a physics-based simulation workflow was developed by coupling computational fluid dynamics (CFD) with optical simulations of camera and lidar sensors. The computational data of various weather conditions can be rapidly generated by CFD and used to assess the impact of weather conditions on the sensors and perception algorithms. The developed CFD-optical workflow was tested using rainy conditions as a test case, the data for which were generated using CFD and exported to optical simulation software to assess how rainy conditions affect the performance of a visible camera, lidar, and an open-source perception algorithm. The results of the analysis indicate that the rainy conditions and intensification of the conditions by other vehicles on the road degrade the performance of camera and lidar sensors. The ability of the perception algorithm to detect vehicles significantly deteriorated when rainy conditions changed to moderate rain. Finally, a systematic perturbation of the rain data produced inconsistent predictions from the perception algorithm, indicating the need to develop weather-aware perception algorithms.