Efficient Domain Augmentation for Autonomous Driving Testing Using Diffusion Models
Authors:
- 26 April 2025
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 398-410
Abstract
Simulation-based testing is widely used to assess the reliability of Autonomous Driving Systems (ADS), but its effectiveness is limited by the operational design domain (ODD) conditions available in such simulators. To address this limitation, in this work, we explore the integration of generative artificial intelligence techniques with physics-based simulators to enhance ADS system-level testing. Our study evaluates the effectiveness and computational overhead of three generative strategies based on diffusion models, namely instruction-editing, inpainting, and inpainting with refinement. Specifically, we assess these techniques' capabilities to produce augmented simulator-generated images of driving scenarios representing new ODDs. We employ a novel automated detector for invalid inputs based on semantic segmentation to ensure semantic preservation and realism of the neural generated images. We then performed system-level testing to evaluate the ability of the ADS to generalize to newly synthesized ODDs. Our findings show that diffusion models help to increase the coverage of ODD for system-level ADS testing. Our automated semantic validator achieved a percentage of false positives as low as 3%, retaining the correctness and quality of the images generated for testing. Our approach successfully identified new ADS system failures before real-world testing.Keywords
All Related Versions
This publication has 47 references indexed in Scilit:
- A Comprehensive Survey of Image Generation Models Based on Deep LearningAnnals of Data Science, 2024
- Two is better than one: digital siblings to improve autonomous driving testingEmpirical Software Engineering, 2024
- Model vs system level testing of autonomous driving systems: a replication and extension studyEmpirical Software Engineering, 2023
- DeepGuard: a framework for safeguarding autonomous driving systems from inconsistent behaviourAutomated Software Engineering, 2021
- Population Research: Convenience Sampling StrategiesPrehospital and Disaster Medicine, 2021
- DriveGAN: Towards a Controllable High-Quality Neural Simulation2021
- Paracosm: A Test Framework for Autonomous Driving Simulations2021
- Analyzing and Improving the Image Quality of StyleGAN2020
- A survey of deep learning techniques for autonomous drivingJournal of Field Robotics, 2019
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015