Correlation of Software-in-the-Loop Simulation with Physical Testing for Autonomous Driving

TL;DR

This paper presents a case study validating an in-house SIL toolchain (CSPAS) for autonomous driving by mirroring scenarios on a test track and aligning them through data synchronization and scenario tuning. It introduces an integrated validation workflow, defines synchronization methods (including the key relation $S_{sync} = \frac{S_{at}-S_{min}}{2}$), and uses KPI-based correlation metrics (Pearson r and Relative RMSE) to compare simulated and real-world behavior. The findings show strong linear correlation (many $r$ values > 0.9) and highlight that longitudinal speed $v_{lon}$ is the most accurately matched signal, with some variability in acceleration signals, especially in challenging cut-out scenarios. The study demonstrates a practical, repeatable approach to validating SIL toolchains for ADS safety and regulatory alignment, with future work aimed at richer metrics for deeper insight.

Abstract

Software-in-the-loop (SIL) simulation is a widely used method for the rapid development and testing of autonomous vehicles because of its flexibility and efficiency. This paper presents a case study on the validation of an in-house developed SIL simulation toolchain. The presented validation process involves the design and execution of a set of representative scenarios on the test track. To align the test track runs with the SIL simulations, a synchronization approach is proposed, which includes refining the scenarios by fine-tuning the parameters based on data obtained from vehicle testing. The paper also discusses two metrics used for evaluating the correlation between the SIL simulations and the vehicle testing logs. Preliminary results are presented to demonstrate the effectiveness of the proposed validation process

Figures (15)

• Figure 1: SIL simulation environment with CSPAS.
• Figure 2: The proposed validation process.
• Figure 3: The AV under testing and the GST vehicle on AstaZero.
• Figure 4: Unsynchronized plot for the relative distance to the target for the cut-in scenario in Table \ref{['tab:scenarioparameters']}.
• Figure 5: Synchronized plot for the relative distance to the target for the cut-in scenario in Table \ref{['tab:scenarioparameters']}.