An Approach for Evaluating the Completeness of the Test Scenarios for the Vehicle Environmental Perception-Based Systems

An environmental perception aims to detect and classify objects existing in the vehicle's surroundings to build a virtual representation of the world. It can be considered as an essential building block in modern advanced safety and automated driving systems. These systems implement functionalities that are very often classified as safety-critical. Testing is actually the only method to assure the required system quality and compliance with safety standards. Testing the safety aspects of automated driving systems creates a number of challenges related to the adequacy and completeness of the test cases being developed. This is because the number of possible test scenarios on the road is actually infinite and such scenarios are time- and space-dependent. In this paper, we define a qualitative and quantitative measure that can be used to evaluate the completeness and adequacy of the test scenarios and consequently limit the amount of tests needed. The measure allows to consider static aspects of the perception systems such as detection and classification, as well as dynamic aspects related to object tracking.