Abstract
Operating autonomous vehicles at the absolute limits of handling requires precise, real-time identification of highly non-linear tire dynamics. However, traditional online optimization methods suffer from "cold-start" initialization failures and struggle to model high-frequency transient dynamics. To address these bottlenecks, this paper proposes a novel vision-augmented, iterative system identification framework. First, a lightweight CNN (MobileNetV3) translates visual road textures into a continuous heuristic friction prior, providing a robust "warm-start" for parameter optimization. Next, a S4 model captures complex temporal dynamic residuals, circumventing the memory and latency limitations of traditional MLPs and RNNs. Finally, a derivative-free Nelder-Mead algorithm iteratively extracts physically interpretable Pacejka tire parameters via a hybrid virtual simulation. Co-simulation in CarSim demonstrates that the lightweight vision backbone reduces friction estimation error by 76.1 using 85 fewer FLOPs, accelerating cold-start convergence by 71.4. Furthermore, the S4-augmented framework improves parameter extraction accuracy and decreases lateral force RMSE by over 60 by effectively capturing complex vehicle dynamics, demonstrating superior performance compared to conventional neural architectures.
Abstract (translated)
运行自动驾驶车辆时，在处理能力的极限下操作需要对高度非线性的轮胎动力学进行精确且实时的识别。然而，传统的在线优化方法会遇到“冷启动”初始化失败的问题，并且难以建模高频瞬态动态特性。为了解决这些问题，本文提出了一种新型的视觉增强迭代系统辨识框架。 首先，该框架使用一种轻量级CNN（MobileNetV3）将路面纹理转化为连续的摩擦先验信息，这为参数优化提供了一个稳健的“暖启动”。其次，S4模型捕捉复杂的时变动态残差，从而克服了传统MLP和RNN在内存和延迟上的限制。最后，一种无导数Nelder-Mead算法通过混合虚拟仿真迭代提取物理可解释的Pacejka轮胎参数。 在CarSim中的共仿真表明：轻量级视觉骨干网络使摩擦估算误差减少了76.1%，同时仅使用了85更少的FLOPs（浮点运算次数），加速冷启动收敛速度提高了71.4%。此外，经过S4增强的框架不仅提升了参数提取精度，还通过有效捕捉复杂的车辆动态特性将横向力均方根误差降低了超过60%，其性能明显优于传统的神经网络架构。 综上所述，该论文提出的视觉增强迭代系统辨识框架为解决自动驾驶汽车在极限条件下操作时遇到的问题提供了一种有效的解决方案。
URL
https://arxiv.org/abs/2603.09399
