An Empirical Testing of Autonomous Vehicle Simulator System for Urban Driving

TL;DR

This paper empirically evaluates an autonomous vehicle simulator system combining SVL and Apollo, demonstrating its effectiveness in realistic testing scenarios while identifying some limitations in pedestrian and vehicle detection.

Contribution

It presents a comprehensive empirical testing framework with 1062 scenarios, integrating naturalistic driving situations and metamorphic testing to assess AV simulator system performance.

Findings

SVL can simulate realistic safe and collision scenarios

Apollo drives safely in tested scenarios

System failed to detect pedestrians or vehicles in 10% of scenarios

Abstract

Safety is one of the main challenges that prohibit autonomous vehicles (AV), requiring them to be well tested ahead of being allowed on the road. In comparison with road tests, simulators allow us to validate the AV conveniently and affordably. However, it remains unclear how to best use the AV-based simulator system for testing effectively. Our paper presents an empirical testing of AV simulator system that combines the SVL simulator and the Apollo platform. We propose 576 test cases which are inspired by four naturalistic driving situations with pedestrians and surrounding cars. We found that the SVL can imitate realistic safe and collision situations; and at the same time, Apollo can drive the car quite safely. On the other hand, we noted that the system failed to detect pedestrians or vehicles on the road in three out of four classes, accounting for 10.0% total number of scenarios tested. We further applied metamorphic testing to identify inconsistencies in the system with additional 486 test cases. We then discussed some insights into the scenarios that may cause hazardous situations in real life. In summary, this paper provides a new empirical evidence to strengthen the assertion that the simulator-based system can be an indispensable tool for a comprehensive testing of the AV.