A data-driven approach to nonlinear braking control

Abstract

In modern road vehicles, active braking control systems are crucial elements to ensure safety and lateral stability. Unfortunately, the wheel slip dynamics is highly nonlinear and the on-line estimation of the road-tire conditions is still a challenging open research problem. These facts make it difficult to devise a braking control system that is reliable in any situation without being too conservative. In this paper, we propose the Data-Driven Inversion Based Control (D2-IBC) approach to overcome the above issues. The method relies on a two degrees of freedom architecture, with a linear controller and a nonlinear controller in parallel, both designed using only experimental data. The effectiveness of the proposed approach is shown by means of an extensive simulation campaign.