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

Model predictive control has been widely used in the field of autonomousracing and many data-driven approaches have been proposed to improve theclosed-loop performance and to minimize lap time. However, it is oftenoverlooked that a change in the environmental conditions, e.g., when it startsraining, it is not only required to adapt the predictive model but also thecontroller parameters need to be adjusted. In this paper, we address thischallenge with the goal of requiring only few data. The key novelty of theproposed approach is that we leverage the learned dynamics model to encode theenvironmental condition as context. This insight allows us to employ contextualBayesian optimization, thus accelerating the controller tuning problem when theenvironment changes and to transfer knowledge across different cars. Theproposed framework is validated on an experimental platform with 1:28 scale RCrace cars. We perform an extensive evaluation with more than 2'000 driven lapsdemonstrating that our approach successfully optimizes the lap time acrossdifferent contexts faster compared to standard Bayesian optimization.

Model Learning and Contextual Controller Tuning for Autonomous Racing