MMRHP: A Miniature Mixed-Reality HIL Platform for Auditable Closed-Loop Evaluation

TL;DR

This work shows that a structured process, combined with a platform offering a unified spatio-temporal benchmark, enables reproducible, interpretable, and quantitative closed-loop evaluation of autonomous driving systems.

Abstract

Validation of autonomous driving systems requires a trade-off between test fidelity, cost, and scalability. While miniaturized hardware-in-the-loop (HIL) platforms have emerged as a promising solution, a systematic framework supporting rigorous quantitative analysis is generally lacking, limiting their value as scientific evaluation tools. To address this challenge, we propose MMRHP, a miniature mixed-reality HIL platform that elevates miniaturized testing from functional demonstration to rigorous, reproducible quantitative analysis. The core contributions are threefold. First, we propose a systematic three-phase testing process oriented toward the Safety of the Intended Functionality(SOTIF)standard, providing actionable guidance for identifying the performance limits and triggering conditions of otherwise correctly functioning systems. Second, we design and implement a HIL platform centered around a unified spatiotemporal measurement core to support this process, ensuring consistent and traceable quantification of physical motion and system timing. Finally, we demonstrate the effectiveness of this solution through comprehensive experiments. The platform itself was first validated, achieving a spatial accuracy of 10.27 mm RMSE and a stable closed-loop latency baseline of approximately 45 ms. Subsequently, an in-depth Autoware case study leveraged this validated platform to quantify its performance baseline and identify a critical performance cliff at an injected latency of 40 ms. This work shows that a structured process, combined with a platform offering a unified spatio-temporal benchmark, enables reproducible, interpretable, and quantitative closed-loop evaluation of autonomous driving systems.

Figures (12)

• Figure 1: An overview of the MMRHP platform.(a) The virtual town scene rendered in the CARLA simulator. (b) The 4.2m x 4.2m real-world, scaled-down sandbox environment, which includes various road elements and a scaled-physical vehicle.
• Figure 2: HIL Loop Timing Diagram. This diagram illustrates the complete timing chain from ground truth acquisition to the R2V link, and then to the V2R link transmitting control commands to the physical actuator, with the measurement aperture for each latency segment $\Delta T$ indicated.
• Figure 3: MMRHP System implementation and data pathways within HIL loop.
• Figure 4: The logical management and execution hierarchy of the MMRHP.
• Figure 5: Visualization of the calibration pipeline and alignment results. (a)Raw data from the Tracker (blue) and LiDAR (orange) sensors, illustrating the large initial misalignment (RMSE $>7000$ mm). (b)The 3,433 matched point pairs after preprocessing and coarse alignment, still showing significant residual error (RMSE $\approx 3230$ mm). (c)Final alignment of the test set data after correction by the proposed hybrid model, achieving a precise overlay and a final RMSE of 10.27 mm.