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

Optimizing lower-body exoskeleton walking gaits for user comfort requiresunderstanding users' preferences over a high-dimensional gait parameter space.However, existing preference-based learning methods have only exploredlow-dimensional domains due to computational limitations. To learn userpreferences in high dimensions, this work presents LineCoSpar, ahuman-in-the-loop preference-based framework that enables optimization overmany parameters by iteratively exploring one-dimensional subspaces.Additionally, this work identifies gait attributes that characterize broaderpreferences across users. In simulations and human trials, we empiricallyverify that LineCoSpar is a sample-efficient approach for high-dimensionalpreference optimization. Our analysis of the experimental data reveals acorrespondence between human preferences and objective measures of dynamicity,while also highlighting differences in the utility functions underlyingindividual users' gait preferences. This result has implications forexoskeleton gait synthesis, an active field with applications to clinical useand patient rehabilitation.

Human Preference-Based Learning for High-dimensional Optimization of Exoskeleton Walking Gaits