Optimization tools for Twin-in-the-Loop vehicle control design: analysis and yaw-rate tracking case study

TL;DR

The paper tackles efficient tuning of the compensator $C_{\delta}$ in Twin-in-the-Loop Control for yaw-rate tracking. It compares Bayesian Optimization, SMGO-$\Delta$, and VRFT within a high-fidelity simulation, showing that VRFT achieves near-optimal performance in one experiment, while BO/SMGO require multiple iterations; SMGO-$\Delta$ notably reduces computational burden. Through a detailed MPC-based baseline and a realistic vehicle/digital-twin setup, the study demonstrates TiL-C's ability to improve yaw-rate tracking and sideslip control across maneuvers, with practical implications for safer and faster end-of-line tuning. The results highlight the value of leveraging VRFT as a prior for global optimization and suggest that physics-informed, data-driven calibration can substantially reduce tuning time in automotive controllers. The work advances TiL-C by broadening its validation to yaw-rate tracking and comparing optimization strategies in terms of convergence speed, safety, and real-time feasibility.

Abstract

Given the urgent need of simplifying the end-of-line tuning of complex vehicle dynamics controllers, the Twin-in-the-Loop Control (TiL-C) approach was recently proposed in the automotive field. In TiL-C, a digital twin is run on-board to compute a nominal control action in run-time and an additional block C_delta is used to compensate for the mismatch between the simulator and the real vehicle. As the digital twin is assumed to be the best replica available of the real plant, the key issue in TiL-C becomes the tuning of the compensator, which must be performed relying on data only. In this paper, we investigate the use of different black-box optimization techniques for the calibration of C_delta. More specifically, we compare the originally proposed Bayesian Optimization (BO) approach with the recently developed Set Membership Global Optimization (SMGO) and Virtual Reference Feedback Tuning (VRFT), a one-shot direct data-driven design method. The analysis will be carried out within a professional multibody simulation environment on a novel TiL-C application case study -- the yaw-rate tracking problem -- so as to further prove the TiL-C effctiveness on a challenging problem. Simulations will show that the VRFT approach is capable of providing a well tuned controller after a single iteration, while 10 to 15 iterations are necessary for refining it with global optimizers. Also, SMGO is shown to significantly reduce the computational effort required by BO.

Figures (17)

• Figure 1: Twin-in-the-Loop vehicle control scheme.
• Figure 2: Single-track vehicle model.
• Figure 3: Steer-by-wire actuator model, featuring transfer function, rate limiter and saturation.
• Figure 4: Static component of $r_{ref}$ against driver steer request $s_{ref}$. For each showed speed value, the solid line represents the digital twin behaviour, whereas the dashed one is the static model.
• Figure 5: High-level control system architecture, depicting the software elements, namely the reference generator and the controller, the employed measurements and the control variable.

Theorems & Definitions (1)

• Remark