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 propose a demonstration-efficient strategy to compress a computationallyexpensive Model Predictive Controller (MPC) into a more computationallyefficient representation based on a deep neural network and Imitation Learning(IL). By generating a Robust Tube variant (RTMPC) of the MPC and leveragingproperties from the tube, we introduce a data augmentation method that enableshigh demonstration-efficiency, being capable to compensate the distributionshifts typically encountered in IL. Our approach opens the possibility ofzero-shot transfer from a single demonstration collected in a nominal domain,such as a simulation or a robot in a lab/controlled environment, to a domainwith bounded model errors/perturbations. Numerical and experimental evaluationsperformed on a trajectory tracking MPC for a quadrotor show that our methodoutperforms strategies commonly employed in IL, such as DAgger and DomainRandomization, in terms of demonstration-efficiency and robustness toperturbations unseen during training.

Demonstration-Efficient Guided Policy Search via Imitation of Robust Tube MPC