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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Variable stiffness actuator (VSA) designs are manifold. Conventionalmodel-based control of these nonlinear systems is associated with high effortand design-dependent assumptions. In contrast, machine learning offers apromising alternative as models are trained on real measured data andnonlinearities are inherently taken into account. Our work presents auniversal, learning-based approach for position and stiffness control of softactuators. After introducing a soft pneumatic VSA, the model is learned withinput-output data. For this purpose, a test bench was set up which enablesautomated measurement of the variable joint stiffness. During control, Gaussianprocesses are used to predict pressures for achieving desired position andstiffness. The feedforward error is on average 11.5% of the total pressurerange and is compensated by feedback control. Experiments with the softactuator show that the learning-based approach allows continuous adjustment ofposition and stiffness without model knowledge.

Learning-based Position and Stiffness Feedforward Control of Antagonistic Soft Pneumatic Actuators using Gaussian Processes