Assessing Quality Metrics for Neural Reality Gap Input Mitigation in Autonomous Driving Testing

TL;DR

This study evaluates how different image-to-image translation methods impact the mitigation of the sim2real gap in autonomous driving testing, highlighting the importance of task-specific perception metrics for better assessment.

Contribution

It introduces a task-specific perception metric that improves the evaluation of I2I techniques in reducing the sim2real gap for autonomous driving tasks.

Findings

Effectiveness of I2I varies across tasks

Existing metrics do not align well with ADS behavior

Task-specific semantic perception metrics improve evaluation

Abstract

Simulation-based testing of automated driving systems (ADS) is the industry standard, being a controlled, safe, and cost-effective alternative to real-world testing. Despite these advantages, virtual simulations often fail to accurately replicate real-world conditions like image fidelity, texture representation, and environmental accuracy. This can lead to significant differences in ADS behavior between simulated and real-world domains, a phenomenon known as the sim2real gap. Researchers have used Image-to-Image (I2I) neural translation to mitigate the sim2real gap, enhancing the realism of simulated environments by transforming synthetic data into more authentic representations of real-world conditions. However, while promising, these techniques may potentially introduce artifacts, distortions, or inconsistencies in the generated data that can affect the effectiveness of ADS testing. In our empirical study, we investigated how the quality of image-to-image (I2I) techniques influences the mitigation of the sim2real gap, using a set of established metrics from the literature. We evaluated two popular generative I2I architectures, pix2pix, and CycleGAN, across two ADS perception tasks at a model level, namely vehicle detection and end-to-end lane keeping, using paired simulated and real-world datasets. Our findings reveal that the effectiveness of I2I architectures varies across different ADS tasks, and existing evaluation metrics do not consistently align with the ADS behavior. Thus, we conducted task-specific fine-tuning of perception metrics, which yielded a stronger correlation. Our findings indicate that a perception metric that incorporates semantic elements, tailored to each task, can facilitate selecting the most appropriate I2I technique for a reliable assessment of the sim2real gap mitigation.