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

A reliable controller is critical and essential for the execution of safe andsmooth maneuvers of an autonomous vehicle.The controller must be robust toexternal disturbances, such as road surface, weather, and wind conditions, andso on.It also needs to deal with the internal parametric variations of vehiclesub-systems, including power-train efficiency, measurement errors, timedelay,so on.Moreover, as in most production vehicles, the low-control commandsfor the engine, brake, and steering systems are delivered through separateelectronic control units.These aforementioned factors introduce opaque andineffectiveness issues in controller performance.In this paper, we design afeed-forward compensate process via a data-driven method to model and furtheroptimize the controller performance.We apply the principal component analysisto the extraction of most influential features.Subsequently,we adopt a timedelay neural network and include the accuracy of the predicted error in afuture time horizon.Utilizing the predicted error,we then design a feed-forwardcompensate process to improve the control performance.Finally,we demonstratethe effectiveness of the proposed feed-forward compensate process in simulationscenarios.

A Data Driven Method of Optimizing Feedforward Compensator for Autonomous Vehicle