English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Most state-of-the-art works in trajectory forecasting for automotive targetpredicting the pose and orientation of the agents in the scene. This representsa particularly useful problem, for instance in autonomous driving, but it doesnot cover a spectrum of applications in control and simulation that requireinformation on vehicle dynamics features other than pose and orientation. Also,multi-step dynamic simulation of complex multibody models does not seem to be aviable solution for real-time long-term prediction, due to the highcomputational time required. To bridge this gap, we present a deep-learningframework to model and predict the evolution of the coupled driver-vehiclesystem dynamics jointly on a complex road geometry. It consists of twocomponents. The first, a neural network predictor, is based on Long Short-TermMemory autoencoders and fuses the information on the road geometry and the pastdriver-vehicle system dynamics to produce context-aware predictions. Thesecond, a Bayesian optimiser, is proposed to tune some significanthyperparameters of the network. These govern the network complexity, as well asthe features importance. The result is a self-tunable framework with real-timeapplicability, which allows the user to specify the features of interest. Theapproach has been validated with a case study centered on motion cueingalgorithms, using a dataset collected during test sessions of anon-professional driver on a dynamic driving simulator. A 3D track with complexgeometry has been employed as driving environment to render the prediction taskchallenging. Finally, the robustness of the neural network to changes in thedriver and track was investigated to set guidelines for future works.

Real-Time Forecasting of Driver-Vehicle Dynamics on 3D Roads: a Deep-Learning Framework Leveraging Bayesian Optimisation