Systematic Situation Coverage versus Random Situation Coverage for Safety Testing in an Autonomous Car Simulation

What is it about?

Autonomous vehicles (AV) have the potential to improve road transport, but faults in the autonomous driving software can result in serious accidents. To assess the safety of AV driving software, we need to consider the wide variety and diversity of situations that it may encounter. Explicit situation coverage has previously been presented, but its usefulness has received a little empirical scrutiny. In this study, we evaluate a situation coverage based safety testing approach by comparing the performance of random and situation coverage-based test generation in terms of its ability to detect seeded faults in our ego AV at a road intersection under diverse environmental conditions.

Featured Image

Photo by Steve Johnson on Unsplash

Photo by Steve Johnson on Unsplash

Why is it important?

In order to assure safety and give strength to the public in the safety of AVs, we work on the safety assurance of AVs by considering situation coverage. Autonomous vehicles on the road can get into a wide-range of situations, and they needs to tackle every challenging situation independently, without direct human assistance. It is thus highly desirable to simulate and test diverse situations that AVs may face while driving without any human interpretation. Therefore, situation coverage for AV is necessary to avoid any unwanted situations

Perspectives