Design and Validation of Edge Case Test Artifact for Evaluation of Automated Driving LiDAR and Radar Sensors

ABSTRACT With the advent of technologies to support autonomous vehicles (AVs), there is a proliferation of different AV technologies from a variety of companies and organizations. With this increase in options comes the need to evaluate the operation of AV technologies to ensure safety and accuracy. Of particular note for physical evaluation involves the perception systems of AVs. However, there is a lack of standard methods to physically evaluate the perception system of AVs. A set of test artifacts can be used to compare the performances of perception systems, but the artifacts must be usable with different types of perception sensors. This article presents the development of an artifact that has both undetectable and detectable edge cases for light detection and ranging (LiDAR) and radar sensors. Specifically, different physical properties were investigated to design the proposed artifact with the desired capabilities of achieving detectable and undetectable edge cases under different conditions. With rigorous testing, a final design for the test artifact was completed where its detectable component reflects at least 7.47 times more radio wave energy and results in at least 1.92 times the amount of LiDAR points as compared with the undetectable component. The test artifact was further tested in outdoor conditions in addition to misaligned positions to demonstrate the versatility and potential weakness of the test artifact, respectively. The demonstrated test artifact in this research can therefore be used to compare the performance of different LiDAR and radar models within AV perception systems.