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

We consider the problem of optimizing a robot morphology to achieve the bestperformance for a target task, under computational resource limitations. Theevaluation process for each morphological design involves learning a controllerfor the design, which can consume substantial time and computational resources.To address the challenge of expensive robot morphology evaluation, we present acontinuous multi-fidelity Bayesian Optimization framework that efficientlyutilizes computational resources via low-fidelity evaluations. We identify theproblem of non-stationarity over fidelity space. Our proposed fidelity warpingmechanism can learn representations of learning epochs and tasks to modelnon-stationary covariances between continuous fidelity evaluations which provechallenging for off-the-shelf stationary kernels. Various experimentsdemonstrate that our method can utilize the low-fidelity evaluations toefficiently search for the optimal robot morphology, outperformingstate-of-the-art methods.

Neural fidelity warping for efficient robot morphology design