Identification of Tire Characteristics Using Physics-Informed Neural Network for Road Vehicles

Abstract

In this paper, a technique is presented for estimating tire characteristics using a Physics-Informed Neural Network (PINN). By integrating physics-based information during the training process the accuracy of the network is enhanced. Utilizing a probabilistic approach, not only individual parameters are identified but also a confidence interval is determined. Additionally, the paper outlines an iterative algorithm for the case when one of the input signals is not measurable or cannot be estimated accurately. Finally, the approach is validated through simulated and real-world test scenarios.