Abstract Developing a dynamic model for a high-performance vehicle is a complex problem that requires extensive structural information about the system under analysis. This information is often unavailable to those who did not design the vehicle, and represents a typical issue in autonomous driving applications, which are frequently developed on top of existing vehicles; therefore, vehicle models are developed under conditions of information scarcity. This paper proposes a lightweight encoder–decoder model based on gated recurrent unit (GRU) layers to correlate the vehicle’s future state with its past states, measured onboard, and the control actions the driver performs. The contribution of this work is the targeted adaptation of a multi-branch decoder architecture to vehicle dynamics, addressing domain-specific challenges and exposure conditions that are not present in previously studied application areas. The results demonstrate that the model achieves a maximum mean relative error below 2.6% in extreme dynamic conditions. It also shows good robustness when subject to noisy input data, up to approximately 20 Hz, across the useful frequency components. Furthermore, being entirely data-driven and free from physical constraints, the model exhibits good consistency in the prediction of output signals, such as longitudinal and lateral accelerations, yaw rate and the vehicle’s longitudinal velocity.
Oddo et al. (Wed,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: