SilGAN: Generating driving maneuvers for scenario-based software-in-the-loop testing
On the map: End-to-end autonomous driving → Adversarial scenarios and safety testing
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Adversarial scenarios and safety testing, one of 9 directions in End-to-end autonomous driving. Builds on 15 of its 30 references that are in the map. First posted on arXiv 5 Jul 2021.
Builds on
15 of 30 references.
References · 15
- 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
- 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
- 2016Least Squares Generative Adversarial Networkscited by 1,000
- 2018Multimodal Unsupervised Image-to-Image Translationcited by 795
- 2018A Survey of Unsupervised Deep Domain Adaptationcited by 361
- 2017Real-valued (Medical) Time Series Generation with Recurrent Conditional GANscited by 329
- 2016C-RNN-GAN: Continuous recurrent neural networks with adversarial trainingcited by 132
- 2019Quant GANs: Deep Generation of Financial Time Seriescited by 107
- 2020Formal Scenario-Based Testing of Autonomous Vehicles: From Simulation to the Real Worldcited by 38
- 2018Painting Outside the Box: Image Outpainting with GANscited by 30
- 2019Transfer Learning for Clinical Time Series Analysis using Deep Neural Networkscited by 22
- 2020Controlled time series generation for automotive software-in-the-loop testing using GANscited by 4
3 more
- 2020MTS-CycleGAN: An Adversarial-based Deep Mapping Learning Network for Multivariate Time Series Domain Adaptation Applied to the Ironmaking Industrycited by 2
- 2018REAS: Combining Numerical Optimization with SAT Solvingcited by 1
- 2019Enhancing Temporal Logic Falsification with Specification Transformation and Valued Booleanscited by 1
Built on by
Citing papers per year: 2021: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2023Scaling Planning for Automated Driving using Simplistic Synthetic Data
- 2025David vs. Goliath: A comparative study of different-sized LLMs for code generation in the domain of automotive scenario generation
- 2026Teach-to-Crash: A Closed-Loop Student-Teacher LLM Framework for Collision-Inducing Test Scenario Generation
- 2024Generating Critical Scenarios for Testing Automated Driving Systems
- 2026Chat2Scenic: An Iterative RAG-Based Framework for Scenario Generation in Autonomous Driving
- 2025MultiDrive: A Co-Simulation Framework Bridging 2D and 3D Driving Simulation for AV Software Validation
- 2024Efficient Domain Augmentation for Autonomous Driving Testing Using Diffusion Models
- 2022Learning Critical Scenarios in Feedback Control Systems for Automated Driving