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

Learning policies in simulation is promising for reducing human effort whentraining robot controllers. This is especially true for soft robots that aremore adaptive and safe but also more difficult to accurately model and control.The sim2real gap is the main barrier to successfully transfer policies fromsimulation to a real robot. System identification can be applied to reduce thisgap but traditional identification methods require a lot of manual tuning.Data-driven alternatives can tune dynamical models directly from data but areoften data hungry, which also incorporates human effort in collecting data.This work proposes a data-driven, end-to-end differentiable simulator focusedon the exciting but challenging domain of tensegrity robots. To the best of theauthors' knowledge, this is the first differentiable physics engine fortensegrity robots that supports cable, contact, and actuation modeling. The aimis to develop a reasonably simplified, data-driven simulation, which can learnapproximate dynamics with limited ground truth data. The dynamics must beaccurate enough to generate policies that can be transferred back to theground-truth system. As a first step in this direction, the current workdemonstrates sim2sim transfer, where the unknown physical model of MuJoCo actsas a ground truth system. Two different tensegrity robots are used forevaluation and learning of locomotion policies, a 6-bar and a 3-bar tensegrity.The results indicate that only 0.25\% of ground truth data are needed to traina policy that works on the ground truth system when the differentiable engineis used for training against training the policy directly on the ground truthsystem.

Sim2Sim Evaluation of a Novel Data-Efficient Differentiable Physics Engine for Tensegrity Robots