SilGAN: Generating driving maneuvers for scenario-based software-in-the-loop testing

TL;DR

SilGAN is a deep generative model that creates realistic vehicle scenarios from concise specifications, enabling more efficient and automated automotive software testing to reduce reliance on costly field tests.

Contribution

The paper introduces SilGAN, a novel deep generative model trained on real vehicle data that automates scenario generation and testing in automotive software-in-the-loop environments.

Findings

Generates realistic vehicle state transitions for specified scenarios.

Automates code coverage testing using learned information.

Expands simulation-based testing scope and credibility.

Abstract

Automotive software testing continues to rely largely upon expensive field tests to ensure quality because alternatives like simulation-based testing are relatively immature. As a step towards lowering reliance on field tests, we present SilGAN, a deep generative model that eases specification, stimulus generation, and automation of automotive software-in-the-loop testing. The model is trained using data recorded from vehicles in the field. Upon training, the model uses a concise specification for a driving scenario to generate realistic vehicle state transitions that can occur during such a scenario. Such authentic emulation of internal vehicle behavior can be used for rapid, systematic and inexpensive testing of vehicle control software. In addition, by presenting a targeted method for searching through the information learned by the model, we show how a test objective like code coverage can be automated. The data driven end-to-end testing pipeline that we present vastly expands the scope and credibility of automotive simulation-based testing. This reduces time to market while helping maintain required standards of quality.