Challenges Of Testing Highly Automated Vehicles: A Literature Review

Abstract

With the advent of the autonomous vehicle, there is potential to reduce the accident rate to a minimum level. Modern automated vehicles will undoubtedly include machine learning (ML) and probabilistic techniques. These algorithms with a non-deterministic world significantly complicate the safety assessment process. In addition, the autonomous system handles the responsibility of safe navigation, so the vehicle has to ensure its safety by itself. Due to these reasons, it is essential to thoroughly assess the system before deploying it on public roads. However, there are many testing challenges for highly automated vehicles (HAVs) to overcome before the wide-scale deployment. In this paper, we conducted a semi-systematic literature review on several issues and challenges related to the testing of HAVs.