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

This paper proposes and develops a physics-inspired neural network (PiNN) forlearning the parameters of commercially implemented adaptive cruise control(ACC) systems in automotive industry. To emulate the core functionality ofstock ACC systems, which have proprietary control logic and undisclosedparameters, the constant time-headway policy (CTHP) is adopted. Leveraging themulti-layer artificial neural networks as universal approximators, thedeveloped PiNN serves as a surrogate model for the longitudinal dynamics ofACC-engaged vehicles, efficiently learning the unknown parameters of the CTHP.The ability of the PiNN to infer the unknown ACC parameters is meticulousevaluated using both synthetic and high-fidelity empirical data of space-gapand relative velocity involving ACC-engaged vehicles in platoon formation. Theresults have demonstrated the superior predictive ability of the proposed PiNNin learning the unknown design parameters of stock ACC systems from differentcar manufacturers. The set of ACC model parameters obtained from the PiNNrevealed that the stock ACC systems of the considered vehicles in threeexperimental campaigns are neither $L_2$ nor $L_\infty$ string stable.

Physics-inspired Neural Networks for Parameter Learning of Adaptive Cruise Control Systems