A Two-Layered Approach for the Validation of an Operational Autonomous Shuttle

To embrace safety while bringing autonomous vehicles (AVs) to public roads, AV manufacturers need validate and verify the functionality reliability of control software. Real-road testing is time-consuming, tedious, costly, unsafe for validation. Hence, simulation has been playing an important role in market as a viable solution. This paper presents approach that exploits both methods find edge case scenarios evaluates software existing shuttle, iseAuto, currently operating at Tallinn University Technology campus. show method’s effectiveness, range are generated simulated avoidance maneuvers by means low-fidelity simulator. Then, found be jeopardizing filtered high-fidelity simulator with loop. Finally, investigate methodology reliability, real study proposed using shuttle. Results suggest toolchain capable tuning models automated driving development well validating safe operations.